Search

• This paper proposes a bidirectional artificial potential field ant colony optimization algorithm (BAPFACO) to solve the path planning problem of mobile robots. • This paper proposes a bidirectional artificial potential field to initialize the grid environment model and restrict direction selection to escape traps. • An adaptive heuristic function is presented to strengthen directionality of the algorithm and reduce the turning times. • A pseudo-random state transition rule based on potential difference between starting and ending nodes is used to accelerate the convergence speed. • A pheromone update strategy incorporating pheromone diffusion mechanism and elite ants is proposed to help getting out of local optima. Ant colony optimization (ACO) is a common approach for addressing mobile robot path planning problems. However, it still encounters some challenges including slow convergence speed, susceptibility to local optima, and a tendency to falling into traps. We propose a bidirectional artificial potential field-based ant colony optimization (BAPFACO) algorithm to solve these issues. First, the bidirectional artificial potential field is introduced to initialize the grid environment model and restrict direction selection to jump out of the trap. Second, an adaptive heuristic function is presented to strengthen directionality of the algorithm and reduce the turning times. Third, a pseudo-random state transition rule based on potential difference between starting and ending nodes is developed to accelerate convergence speed. Finally, an improved pheromone update strategy incorporating pheromone diffusion mechanism and elite ants update strategy is proposed to help getting out of local optima. To demonstrate the advantages of BAPFACO, the validation of the performance in six different complexity environments and comparative experiments with other conventional search algorithms and ACO variants are conducted. The results of experiment show that compared to various ACO variants, BAPFACO have advantages in terms of reducing the turning times, shortening path length, improving convergence speed and avoiding ant loss. In complex environments, compared to IHMACO, the average path length enhancement percentage (PLE) of BAPFACO is 20.98%, the average iterations enhancement percentage (IE) of BAPFACO is 20.00% and the average turning times enhancement percentage (TE) of BAPFACO is 49.43%. These results firmly demonstrate the efficiency and practicality of the BAPFACO algorithm for mobile robot in path planning. [ABSTRACT FROM AUTHOR]

A purely geometric planning method for a mobile robot in unknown environments is proposed to ensure collision avoidance with obstacles within the safety time interval while moving toward the goal. The robot initially detects a point cloud of obstacles using a 2D LiDAR. Euclidean clustering is employed to classify the point cloud into distinct point classes. Each point class is then identified as a directed closed-loop rectangle representing the obstacle. A relative orientation k d-tree is designed to store the vertices of the obstacles and determine which obstacles should be considered in the obstacle avoidance algorithm. A velocity divider is introduced to obtain a linear convex area of possible obstacle avoidance velocities. Linear planning is then used to calculate the optimal obstacle avoidance velocity for control. A virtual reference point method is proposed to address the problem of an unreachable goal in a singular configuration. Experimental results show that the directed closed-loop rectangle and relative orientation k d-tree facilitate rapid updates of required obstacle points with low-cost sensor equipment. A deterministic path for a given scenario is demonstrated, confirming the reliability of the geometric planning method for the obstacle avoidance velocity region and the optimal obstacle avoidance velocity. The proposed algorithm is further validated in scenarios with multiple obstacles and dynamic environments involving moving obstacles. [ABSTRACT FROM AUTHOR]

Mobile robots have become more and more common in public space. This increases the importance of meeting safety requirements of autonomous robots. Simple mechanisms, such as emergency braking, alone do not suffice in these highly dynamic situations. Moreover, actual robotic control approaches in literature and practice do not take safety particularly into account. A more sophisticated situational approach for assessment and planning is needed as part of the high-level process control. This paper presents the concept of a safety-critical Robot Control Architecture for mobile robots based on microservices and a Hierarchical Finite State Machine. It expands already existing architectures by drastically reducing the amount of centralized logic and thus increasing the overall system's level of concurrency, interruptibility and fail-safety. Furthermore, it introduces new potential for code reuse that allows for straightforward implementation of safety mechanisms such as internal diagnostics systems. In doing so, this concept presents the template of a new type of state machine implementation. It is demonstrated with the application of a delivery robot, which was implemented and operated in real public during a broader research project. • Concurrency and interruptibility can improve fault tolerance and stability. • Division of states into atomic functionality increases reusability. • Distribution of robot functionality for increased fault tolerance. [ABSTRACT FROM AUTHOR]

Wheel-legged robots are a type of mobile robot that combines the advantages of wheeled robots, such as fast and stable movement and high efficiency, with the adaptability of legged robots to complex and unstructured environments. Therefore, wheel-legged robots have great potential for application in fields such as deep space exploration, disaster relief, and wilderness exploration. This paper categorizes and summarizes the structural forms and driving modes of wheel-legged robots, dividing them into three categories: wheel-legged hybrid robots, wheel-legged separation robots, and wheel-legged transformation robots based on their structural characteristics. Finally, this paper summarizes the structure and driving aspects of wheel-legged robots and provides an outlook on their development in these two areas. The research results presented in this paper help researchers understand the development process of wheel-legged robots and serve as a valuable reference for future research. [ABSTRACT FROM AUTHOR]

• Intelligent machines were designed to execute tasks in hazardous environments. • The robot is required to perceive and identify objects in the vicinity. • Path planning is another important aspect of mobile robot navigation. This paper uses robot programming techniques, such as Deep Q Network, Artificial Neural Network, and Artificial Deep Q Network, to address challenges related to controlling robotic arms through demonstration learning. Static and dynamic states of the subjects were the subjects of experiments. Each method's classification accuracy process success values and experimental condition combination were evaluated. The DQN method demonstrated favourable classification accuracy outcomes, achieving an Accuracy value of 0.64 for the fixed dice and 0.52 for the moving dice. The Response value was 0.51 for the fixed dice and 0.41 for the moving dice, indicating a moderate level. The ANN method demonstrated lower accuracy, with Accuracy values of 0.59 and 0.56 and Response values of 0.61 and 0.58, respectively. The ADQN method demonstrated superior outcomes, with Accuracy values of 0.66 and 0.59 and Response values of 0.67 and 0.61. During the initial learning iterations, ADQN demonstrated the highest success rate at 33.67 %, whereas DQN and ANN achieved 28.39 % and 20.13 % success rates, respectively. As the number of iterations increased, all methods demonstrated improvement in their results. ADQN maintained a high success rate of 97.59 %, while DQN and ANN attained 82.16 % and 88.66 %, respectively. As the number of iterations increases, the results of all methods improve, but the success rate of the Artificial Deep Q Network remains high. As the number of iterations increases, both Deep Q Network and Artificial Neural Network demonstrate the potential to achieve good results. Overall, the findings support the efficacy of robot programming techniques that incorporate demonstration learning. The Artificial Deep Q Network is the most successful and fast-converging method suitable for various robot control tasks. These findings provide a foundation for future research and large-scale, comprehensive learning applications for complex rot control. [ABSTRACT FROM AUTHOR]

Mobile robotic platforms that are expected to be engaged in applications domains characterized by unstructured terrains and environment settings will unavoidably face mobility constraints that may not be overcome by classical navigation planning and obstacle avoidance/negotiation tools. Endowing these robots with additional skills, which enable them to interact and manipulate obstacles blocking their pathway, will significantly enhance their ability to deal with such conditions, permitting them to perform their mission more robustly when encountering such unstructured and cluttered scenes. This paper proposes a novel hierarchical simulation-based push planner framework that searches for a sequence of pushing actions to move obstacles toward a planned goal position. This aims at overcoming obstacle challenges that block the navigation of the robot toward a target location and, therefore, can lead to the failure of the navigation plan and the overall mission of the robot. The planned pushing actions enable the robot to relocate objects in the scene avoiding obstacles and considering environmental constraints identified by an elevation or an occupancy map. The online simulations of the pushing actions are carried out by exploiting the Mujoco physics engine. The framework was validated in the Gazebo simulation environment and in real platforms such as the hybrid wheeled-legged robot CENTAURO and the mobile cobot RELAX. • Constrained two-level push planner framework based on parallelized simulation steps. • Evaluate environmental data for collision-free planning and robot pose adaptation. • Autonomous selection of the object to push and its target location to solve the task. • Extensive validation on the real robots RELAX and CENTAURO, in blocked scenarios. [ABSTRACT FROM AUTHOR]

Several frameworks for robot control platforms have been developed in recent years. However, strategies that incorporate automatic replanning have to be explored, which is a requirement for Autonomous Robotic Systems (ARS) to be widely adopted. Ontologies can play an essential role by providing a structured representation of knowledge. This paper proposes a new framework capable of replanning high-level tasks in failure situations for ARSs. The framework utilizes an ontology-based reasoning engine to overcome constraints and execute tasks through Behavior Trees (BTs). The proposed framework was implemented and validated in a real experimental environment using an Autonomous Mobile Robot (AMR) sharing a plan with a human operator. The proposed framework uses semantic reasoning in the planning system, offering a promising solution to improve the adaptability and efficiency of ARSs. • Proposing a framework that leverages semantic reasoning to optimize task planning. • Optimized execution based on Behavior Trees and an ontology-based reasoning engine. • The framework has the capability of replanning high-level tasks in failure situations. • The proposed framework was implemented and validated in practice. [ABSTRACT FROM AUTHOR]

Building a map representation of the surrounding environment is crucial for the successful operation of autonomous robots. While extensive research has concentrated on mapping geometric structures and static objects, the environment is also influenced by the movement of dynamic objects. Integrating information about spatial motion patterns in an environment can be beneficial for planning socially compliant trajectories, avoiding congested areas, and aligning with the general flow of people. In this paper, we introduce a deep state-space model designed to learn map representations of spatial motion patterns and their temporal changes at specific locations. Thus enabling the robot for human-compliant operation and improved trajectory forecasting in environments with evolving motion patterns. Validation of the proposed method is conducted using two datasets: one comprising generated motion patterns and the other featuring real-world pedestrian data. The model's performance is assessed in terms of learning capability, mapping quality, and its applicability to downstream robotics tasks. For comparative assessment of mapping quality, we employ CLiFF-Map as a baseline, and CLiFF-LHMP serves as another baseline for evaluating performance in downstream motion prediction tasks. The results demonstrate that our model can effectively learn corresponding motion patterns and holds promising potential for application in robotic tasks. • A generative model to encode the spatial motion pattern into a map representation. • A solution for modelling gradually changing patterns of human motion. • Outperforms existing models in quality and downstream applications. • A deep learning approach remains robust with smaller datasets. [ABSTRACT FROM AUTHOR]

In the real world, multi-robot systems need to deal with on-the-fly (runtime) arrivals of new sets of tasks. This entails repeated adjustments of their current task allocations to include the newer ones while also ensuring that the overall performance does not degrade. This paper proposes a decentralized and distributed dynamic task allocation algorithm to handle this issue in a multi-robot scenario. The proposed work provides a conflict-free allocation of a set of tasks constituting a job to robots and minimizes the total execution time. These jobs can comprise multiple independent and/or dependent tasks or a combination thereof, which are injected on-the-fly into a network of robots. The dependent tasks of a job are related by precedence constraints that specify the ordering or dependencies between pairs of tasks. The work also describes a decentralized adaptive energy threshold mechanism for determining whether or not a robot needs to visit a battery stockpile after the execution of a task. Conflicting task selections among the robots in this decentralized set-up are resolved using mobile agents during runtime. Apart from allocating tasks to the robots, these mobile agents exploit the benefits of centralized and decentralized systems and provide an advantage over auction-based task allocation algorithms. The proposed algorithm takes into consideration the energy requirements, both during the task allocation process and actual execution. The proposed algorithm also caters to strategies to deal with delays caused by obstacles and congestion during the actual execution of the tasks. Experiments conducted using Webots , an open-source robot simulator, and Tartarus , a multi-agent platform, authenticate the efficacy of the proposed algorithm compared to other prominent task allocation algorithms in terms of minimization of average waiting time , total task allocation time , total job allocation time , and total execution time of an experiment. • Decentralized, distributed, and dynamic precedence-constrained MRTA algorithm • Mobile agents are used to resolve task conflicts and to allocate tasks among robots. • An adaptive energy threshold for recharging the robots is used. • Energy consumption is considered both during task allocation and actual execution. • Strategies to overcome delays due to obstacles during actual execution are proposed. [ABSTRACT FROM AUTHOR]

• Geometric and the dynamic models were established in obstacle crossing process. • The multi-objective optimization of robot motion during obstacle crossing was formed. • An improved NSGA-II was applied to the structural optimal design of tracked mobile robot. • Some meaningful relationships were obtained through sensitivity analysis. Stability of obstacle–crossing and structural optimization are important issues in the research of tracked mobile robots. In this paper, in order to fully understand the obstacle–surmounting ability of the robot, the relationship between the position of the center of gravity and the posture of the front and rear swing arms is analyzed. Based on the motion mechanism of the robot crossing obstacles, the geometric model and the dynamic model are established for the key states in the obstacle crossing process. Based on these models, a multi-objective optimization problem for the maximum obstacle–crossing height and minimum driving torque is established during the obstacle crossing process of the robot, which must meet geometric, slip, and stability constraints. To effectively handle the optimization problem of tracked mobile robots, an improved non–dominated sorting genetic algorithm with elite strategy version II based on adaptive genetic strategy (NSGA-II-AGS) is proposed in this paper. Some meaningful relationships between the objective function and the design variables are obtained through sensitivity analysis. Finally, the robot's obstacle-crossing ability was verified through virtual simulation and prototype experiments. These excellent performances enable the proposed NSGA-II-AGS to be qualified for dealing with the multi-objective optimization problem. [ABSTRACT FROM AUTHOR]

High-temperature industrial inspection has several challenges, especially if it is an autonomous inspection through mobile robots. This paper introduces the mobile robot CRAS (Climbing Robot for Advanced inSpection) for autonomous non-destructive testing (NDT) of weld beads from industrial super-duplex stainless steel vessels. It covers the design process, previous works, main challenges, and field testing. The main objective of the robot is to perform ultrasonic inspection over a heated separator tank while it operates. The metallic surfaces of the structure to be inspected are under constant high temperatures (80 °C–135 °C) when in operation. CRAS presents magnetic wheels as an adhesion method and a perception system able to identify and follow weld beads. The NDT method uses the phased-array ultrasonic technique. This paper approaches and proposes a solution for three challenges due to the high temperature: the loss of robot adhesion, ultrasound signal deformation, and the risk of damaging sensitive equipment such as sensors, cameras, and any electronic component. The CRAS adopted solutions are detailed and future steps of CRAS development are also addressed. • Robotic weld bead inspection using phased-array ultrasonic non-destructive testing (NDT). • High-temperature in-service NDT inspection of large metallic structures of the oil and gas sector. • Independent steering and driving magnetic four-wheel climbing robot. • Weld bead identification for semi-autonomous inspection. [ABSTRACT FROM AUTHOR]

• Design three path planning methods for mobile robots. • Combining the ACO algorithm and the improved artificial potential field method. • Improve the ant colony algorithm through firefly algorithm and heuristic function. • Provide technical support for path planning of mobile robots. The rapid development of robotics technology has driven the growth of robot types and the development of related technologies. As an important aspect of robot research, path planning technology plays an irreplaceable role in practical production and application. Ant colony algorithm has a wide range of applications in robot path planning, but there is also a problem of performance overly relying on initial parameter selection. In order to solve this problem and improve the performance of mobile robot path planning, an improved ant colony algorithm based on firefly algorithm was studied and designed in a two-dimensional environment. In order to further explore the performance of ant colony algorithm in solving robot coordinated path planning problems, an improved ant colony algorithm based on heuristic function was also designed. In a three-dimensional environment, an improved ant colony algorithm based on the improved artificial potential field method was designed. The research results show that the maximum running time of the improved ant colony algorithm based on the firefly algorithm in different grid environments is 819.36 s, 847.01 s, and 811.54 s, respectively. The average running time of the improved ant colony algorithm based on heuristic function in different grid environments is 5.19 s, 5.97 s, and 9.09 s, with average path lengths of 29.90 cm, 31.08 cm, and 37.01 cm, and path length variances of 0.35, 0.87, and 2.21, respectively. The ant colony algorithm based on the improved artificial potential field method has a running time of 1.930 s, 3.182 s, and 4.662 s in different grid environments, and a path length of 29.275 cm, 49.447 cm, and 67.057 cm, respectively. The ant colony algorithm for research and design optimization has good performance. The contribution of the research lies in the design of three path planning methods for mobile robots, including two-dimensional path planning and three-dimensional path planning, which improves the time of path planning and shortens the average path length. The novelty of the research is reflected in the design of a path planning method for mobile robots in two-dimensional and three-dimensional environments, which improves the ant colony algorithm through firefly algorithm and heuristic function, and combines the ant colony algorithm with the improved artificial potential field method. The method designed by the research institute can provide technical support for path planning of mobile robots. [ABSTRACT FROM AUTHOR]

The integration of robotics in nursing is a significant shift in healthcare, driven by the aging global population and the increasing demand for care. Robots in nursing can handle less technical tasks such as patient transport and rehabilitation activities. This support allows caregivers to focus on less strenuous nursing duties and more direct patient care. Human-Robot Interaction (HRI) plays an important role in this challenging context. In this research, we present an autonomous hospital transport system based on the ROS 2 framework, focusing on enhancing HRI in the healthcare environment. It encompasses the development of a control architecture for autonomous robot behavior, the implementation of machine learning for emergency detection, and the creation of a user-friendly interface for both patients and staff. The proposed concepts were validated in real-world scenarios in three different hospitals in Germany. This not only demonstrates the practical application of this system but also shares insights and methods, encouraging further advancement in the field of healthcare robotics. • Presentation of the mobile robot PeTRA and its modes of human-robot interaction. • A novel framework for high-level task control, combining BT with ROS 2 using an HFSM. • A novel dataset for patient emergency detection during transportation. • Evaluation of different models for emergency classification optimized for recall. • A multi-modal UI optimized for elderly persons and evaluated with the target group. [ABSTRACT FROM AUTHOR]

In this paper, the performance criteria for various four-wheeled mobile robots that are crucial for assessing a robot's fitness for mobility to successfully complete missions are introduced. The seven proposed performance indices, the root mean squared acceleration (RMSA), posture variance index (PVI), static stability margin (SSM), force angle stability margin (FASM), energy stability margin (ESM), friction requirement (μ r), and velocity constraint violation (VCV), address the fluctuation, rollover, and slippage problems in four-wheeled mobile robots. The simulations considered a square bump-shaped obstacle, and the dimensions of the robot were based on nine simulation cases in a 3D environment. Additionally, a methodology for evaluating these seven criteria is outlined. To streamline the simulation process, Taguchi's catalog of orthogonal arrays (OAs) was used for the experimental design, specifically L9 OA with four factors and three levels was used. Analysis of means (ANOM) was applied to assess the influence of each design factor on the seven criteria, leveraging the OA orthogonality. Finally, the sensitivity analysis and potential for evaluating general mobile robots in the future are discussed. • Seven performance criteria for four-wheeled mobile robots are introduced. • The evaluation method for seven criteria in a 3D environment is proposed. • The design factor effects of the four-wheeled mobile robot are analyzed. • Taguchi's Orthogonal Array (OA) is applied to achieve the lowest experimental number. • Analysis Of Means (ANOM) is used for sensitive analysis with L9 OA. [ABSTRACT FROM AUTHOR]

The robotics community has witnessed a growing demand for long-term navigation of autonomous robots in diverse environments, including factories, homes, offices, and public places. The core challenge in long-term navigation for autonomous robots lies in effectively adapting to varying degrees of dynamism in the environment. In this paper, we propose a long-term navigation method for autonomous robots based on spatio-temporal map prediction. The time series model is introduced to learn the changing patterns of different environmental structures or objects on multiple time scales based on the historical maps and forecast the future maps for long-term navigation. Then, an improved global path planning algorithm is performed based on the time-variant predicted cost maps. During navigation, the current observations are fused with the predicted map through a modified Bayesian filter to reduce the impact of prediction errors, and the updated map is stored for future predictions. We run simulation and conduct several weeks of experiments in multiple scenarios. The results show that our algorithm is effective and robust for long-term navigation in dynamic environments. [ABSTRACT FROM AUTHOR]

In this paper, a motion planning algorithm for floating planar under-actuated hyper-redundant snake robots is proposed. The presented algorithm generates locally optimal shape trajectories, i.e., continuous trajectories in the base space of the robot. Such shape trajectories produce a desired rotation of the snake robot, i.e., change in the uncontrolled orientation fiber variable. The proposed method formulates the motion planning problem as an optimization problem where the objective function could be defined to minimize various metrics, such as energy-based cost functions. Additionally, the proposed motion planning algorithm uses a heuristic to generate shape trajectories that avoid self-intersections and obstacle collision. Hence, the motion planning method generates shape trajectories that locally minimize user-defined cost functions and eliminate self-intersections or obstacle collision. The proposed gait generation method is validated using numerical simulations of five-link and seven-link snake robots. • Motion planning algorithm for reorienting snake robots in force-free environments. • The proposed algorithm is applicable to snake robots having any number of links. • The proposed algorithm generates optimal shape trajectories. • Generated shape trajectories are optimized based on user-defined cost functions. • The algorithm facilitates obstacle avoidance and inter-link collision avoidance. • Introduction of a novel heuristic for inter-link collision avoidance. [ABSTRACT FROM AUTHOR]

The article presents a novel idea to construct a smooth navigation function for a wheeled robot based on grid-based search, that enables replanning in dynamic environments. Since the dynamic constraints of the robot are also considered, the navigation function is combined with the model predictive control (MPC) to guide the robot safely to the defined goal location. The main novelty of this work is the definition of this navigation function and its MPC application with guaranteed closed-loop convergence in finite time for a non-holonomic robot with speed and acceleration constraints. The navigation function consists of an interpolated potential function derived from the grid-based search and a term that guides the orientation of the robot on continuous gradients. The navigation function guarantees convergent trajectories to the desired goal, results in smooth motion between obstacles, has no local minima, and is computationally efficient. The proposed navigation is also suitable in dynamic environments, as confirmed by experiments with a Husky mobile robot. • Navigation function created from the grid-based search enables real-time replanning. • Continuous navigation function is obtained by interpolating discrete grid-based costs. • MPC-based navigation takes velocity and acceleration constraints into account. • MPC with the control sequence generation scheme allows fast on-line computation. • The navigation approach guarantees closed-loop convergence for unicycle-type robots. [ABSTRACT FROM AUTHOR]

The ability to avoid collisions with moving robots is critical in many applications. Moreover, if the robots have limited battery life, the goal is not only to avoid collisions but also to design efficient trajectories in terms of energy consumption and total mission time. This paper proposes a novel strategy for assigning turn angles for collision-free path planning in scenarios where a small team of robots cooperate in a certain mission. The algorithm allows each robot to reach a predetermined destination safely. It establishes consecutive, short time intervals, and at each interval, possible conflicts are solved centrally in an optimal manner. This is done by keeping constant speeds but generating a discrete set of possible directions for each robot, and solving efficiently the turn-angle allocation for a collision-free path that minimizes the path deviation from the shortest one. Due to the discretization, the final paths are not optimal, but the system can react to possible failures during execution, as conflicts are resolved at each time interval. Computational results and Software-In-The-Loop simulations are presented in order to evaluate the proposed algorithm. A comparison with a state-of-the-art approach shows that our algorithm is more energy-efficient and achieves lower mission completion time. [ABSTRACT FROM AUTHOR]

• A novel mobile robot is designed to remove debris from high-voltage power lines. • A novel mobile robot that can be integrated with a drone for transportation. • A mobile robot was developed and tested in high-voltage power lines up to 138 kV. The importance of electrical energy in human life has grown considerably, resulting in a great surge in demand for this energy form. As a consequence, numerous power transmission lines are continuously under construction. Periodic inspections and maintenance of equipment and accessories associated with these lines are crucial to ensuring their proper functioning. Thus, this paper introduces a novel mobile robot designed to remove debris from high-voltage power lines up to 138 kV. This robot offers several advantages, including reduced costs related to maintenance operations that require specialized human labor, increased task efficiency, and reduced risks to human physical integrity by eliminating the need for manual tasks in direct contact with high-voltage lines. This paper outlines the development and validation of a novel robot that can be integrated with a drone for transportation, bringing an innovation to the format for carrying out maintenance in the electric power distribution system. After reviewing robots applied to debris removal, our study presents the novel robot's design and control system. The robot was developed and tested in both simulated and real environments, proving to be efficient and cost-effective in improving debris removal from high-voltage lines while ensuring linemen's safety. [ABSTRACT FROM AUTHOR]

• The issue featured with concurrent job operations - mobile robots scheduling problems in complex FMS environment. • A logical and practical approach for the selection of GA parameters based on fuzzy rules to improve the solution to the complex combinatorial NP-hard scheduling problem. • Adaptively adjustment of genetic operator, i.e., crossover and mutation for better exploration and exploitation activities in searching process. Flexible Manufacturing Systems (FMS) is known as one of the recurring themes that possess these promising characteristics with a synergistic combination of productivity-efficiency transport and flexibility through a number of machine tools alongside other material handling devices. In FMS, mobile robots are commonly deployed in material handling system for the purpose of increasing the efficiency and productivity of the manufacturing process. A reliable, efficient, and optimal scheduling is the most important in manufacturing system. The scheduling problems can become highly complex, especially in large-scale systems with numerous tasks and constraints. Thus, schedule optimization becomes crucial to enhance target performance by determining the best allocations and sequences of resources under specified constraints. Recently, Genetic Algorithm (GA) is a remarkably applicable search algorithm to solve scheduling problems to the way that near optimal could be found. While the performance of GA much depends on the selection of the main parameters, a standard GA may suffer from the issue of premature convergence due to the lack of control on its parameters especially crossover and mutation operators. As there is no specific method or way to tune these parameters, the algorithm is prone to converge on the local optimum, thereby leading to performance degradation. To overcome such flaw, this paper proposed an improved Genetic Algorithm using an adaptive Fuzzy Logic to control crossover and mutation operators (FGAOC) for the solution to the NP-hard problem of scheduling mobile robot within Job-Shop FMS environment. The proposed algorithm has been evaluated in several case studies such as small and large-scale problem, various numbers of mobile robots and the 40-test benchmark problem. The results have demonstrated that the proposed FGAOC has delivered a good performance in exploration-exploitation activities with better solution quality. [ABSTRACT FROM AUTHOR]

We address a motion planning and control problem for mobile robots to satisfy rich, time-varying tasks expressed as Signal Temporal Logic (STL) specifications. The specifications may include tasks with nested temporal operators or time-conflicting requirements (e.g., achieving periodic tasks or tasks defined within the same time interval). Moreover, the tasks can be defined in locations changing with time (i.e., dynamic targets), and their future motions are not known a priori. This unpredictability requires an online control approach which motivates us to investigate the use of control barrier functions (CBFs). The proposed CBFs take into account the actuation limits of the robots and a feasible sequence of STL tasks. They define time-varying feasible sets of states the system must always stay inside. We show the feasible sequence generation process that even includes the decomposition of periodic tasks and alternative scenarios due to disjunction operators. The sequence is used to define CBFs, ensuring STL satisfaction. We also show some theoretical results on the correctness of the proposed method. We illustrate the benefits of the proposed method and analyze its performance via simulations and experiments with aerial robots. • A robot must satisfy a signal temporal logic (STL) specification by visiting time-varying regions. • The future trajectories of time-varying regions are unknown. • The STL specification may include nested temporal operators or time-conflicting requirements. • We propose Sequential CBFs to drive a robot to its dynamic targets based on its STL specification. • The proposed algorithm is supported by theoretical results and tested via experiments. [ABSTRACT FROM AUTHOR]

• A constrained path planning algorithm for Ackerman mobile robot is proposed. • An improved ant colony algorithm with angle constraint is introduced. • An improved B-spline curve smoothing method with curvature constraint is proposed to ensure that the smooth path follows the maximum curvature limit of the mobile robot. In this paper, a new approach is proposed for the smooth path planning of Ackermann mobile robots based on an improved ant colony algorithm and B-spline curves. Firstly, by incorporating path length constraints and path smoothing constraints into the objective function, the smooth path planning problem for Ackermann mobile robots is transformed into a multi-objective optimization problem. Secondly, to address the limitations of the traditional ant colony algorithm, an improved ant colony algorithm based on the turning angle constraint (IACO-TAC) is proposed. IACO-TAC incorporates the distance factor and steering angle penalty factor in the heuristic function to reduce the path search's blindness. Moreover, the pheromone update method is improved, consisting of local pheromone update and global pheromone update, which uses a reward penalty mechanism to improve the convergence speed of the algorithm and increases the pheromone concentration of the global optimal path, respectively. Thirdly, an improved B-spline curve smoothing algorithm that considers the minimum turning radius constraint is proposed to generate a path that satisfies the kinematic constraints of the Ackermann mobile robot. Finally, the proposed method is evaluated by conducting gradient comparison experiments and ant colony algorithm comparison experiments on maps of different sizes. The experimental results demonstrate that our method exhibits a fast convergence rate and plans a path that balances path length and turn frequency while satisfying the kinematic constraints of the mobile robot. Thus, the proposed method offers an efficient and smooth path planning solution for Ackermann mobile robots in complex environments. [ABSTRACT FROM AUTHOR]

Path planning is an important primitive in robotics. In this paper, a new Informed Sampling Space (ISS) driven Informative Path Planning (IPP) approach is developed to facilitate autonomous robots to navigate and explore unknown and hazardous environments for in-situ resource utilization efficiently. The developed ISS-driven IPP approach is targeted on multi-objective optimization enabling the robot to plan its path from start to target locations in the environment and simultaneously explore multiple high-interest areas efficiently. The high-interest areas could be locations advised by a human supervisor or from the robot's prior knowledge of the environment. Typically, a cost function (time, distance, etc.) is used in sampling-based path planners. A new cost function is also developed to incorporate the high-interest spots in this paper, which is based on Multivariate normal (MVN) probability density function (PDF) and a normalization function. Two different IPP models are developed using the new cost function to assist robot navigation. IPP with RRT* is used in the first model with no heuristics, while IPP with RRT* and heuristic ISS is used in the second model. Simulation and comparative analysis substantiate the efficacy and robustness of our approach. The simulation results corroborate that our proposed ISS-driven IPP with RRT* converges rapidly towards the near-optimal solution with respect to both navigation time and environment exploration. • Adaptive cost function incorporates the influence of prior information states. • Multivariate normal probability density function is used to disseminate information. • IPP framework is developed using information map and a sampling-based path planner. • ISS-driven IPP addresses the global sampling problem by ignoring trivial states. • Tree pruning after each subsequent optimization minimizes computational complexity. [ABSTRACT FROM AUTHOR]

An underactuated nonholonomic Dubins-vehicle-like robot with a lower-limited turning radius travels with a constant speed in a plane, which hosts unknown complex objects. In its local frame, the robot has sensorial access only to the part of the scene that is within a finite zone of visibility and in direct line of sight. It is required to approach and then circumnavigate the objects, with maintaining a given distance to the currently nearest of them, so that the ideal targeted path is the equidistant curve of the set of the objects. The focus is on the case where this curve cannot be perfectly traced due to excessive contortions and singularities. So the objective is restated as that of automatically finding, approaching and repeatedly tracing an approximation of the equidistant curve that is the best among those trackable by the robot with respecting safety concerns. Though pre-computation of this approximation is a hard problem of computational geometry, we show that autonomously seeking and tracking this approximation can be performed on-the-fly at a miserable computational cost via implementation of the proposed navigation law. This law is hybrid and operates in only a few discrete modes; within any mode, it is reactive, i.e., it directly converts the current observation into the current control. Nonlocal convergence of this law is justified by mathematically rigorous results and is confirmed by computer simulations and real-world experiments. • Underactuated nonholonomic Dubins-vehicle-like robot with a lower-limited turning radius. • Circumnavigation of unknown objects, with desirably maintaining a given distance to them. • Equidistant curve that is untrackable due to excessive contortion and singularities. • On-the-fly generation of the optimal trackable approximation at a miserable computational cost. • Computationally cheap (reactive) controller that simultaneously generates the path and ensures its tracking. [ABSTRACT FROM AUTHOR]

We develop an algorithm for the motion and task planning of a system composed of multiple robots and unactuated objects under tasks expressed as Linear Temporal Logic (LTL) constraints. The robots and objects evolve subject to uncertain dynamics in an obstacle-cluttered environment. The key part of the proposed solution is the intelligent construction of a coupled transition system that encodes the motion and tasks of the robots and the objects. We achieve such a construction by designing appropriate adaptive control protocols in the lower level, which guarantee the safe robot navigation/object transportation in the environment while compensating for the dynamic uncertainties. The transition system is efficiently interfaced with the temporal logic specification via a sampling-based algorithm to output a discrete path as a sequence of synchronized actions of the robots; such actions satisfy the robots' as well as the objects' specifications. The robots execute this discrete path by using the derived low level control protocol. Numerical experiments verify the proposed framework. • Robot tasks expressed by temporal logics offer great versatility and efficiency. • Simple items/objects often have to undergo processes and tasks. • New algorithm provides robot actions that satisfy theirs and objects' tasks. • Robot actions consist of robot navigation and cooperative object transportation. • Adaptive control is used to tackle uncertainty in robots' and objects' dynamics. [ABSTRACT FROM AUTHOR]

• Smart agriculture system: Precision agriculture, often known as smart agriculture, is a cutting-edge agricultural method that makes use of technology to maximize resource management and crop yield. To improve decision-making and overall agricultural practices, it entails the integration of many technologies, including sensors, automation, data analytics, and remote monitoring. • Optimization: Enhancement The term "agriculture system" describes the application of data analysis and technology to enhance and optimize agricultural processes. To maximize agricultural productivity, resource management, and decision-making, it entails the integration of multiple technologies, including automation, remote sensing, data analytics, and precision agriculture. • Regulation skidding: In agriculture, regulation skidding is a technique used to manage the movement of mobile robots over dirt and water on sloping terrain. It entails building short-term, makeshift barriers or dams across the slope out of boulders, dirt, or other materials. By slowing down water flow and allowing it to seep into the ground, these barriers improve soil moisture and lessen erosion. • Four wheeled mobile robots: Certain four-wheeled mobile robots are autonomous in the context of agriculture, which means they can move and function without assistance from an operator. Some, however, are only partially autonomous, requiring human intervention in the form of direction or oversight. • Linear-quadratic regulator (LQR): To minimize a quadratic cost function of the state and control variables of a linear time-invariant system, an optimum control strategy characterized as a linear-quadratic regulator (LQR) is applied. It is a commonly utilized control theory technique with applications in the field of agriculture. Use of wheeled mobile robot systems could be crucial in addressing some of the future issues facing agriculture. However, robot systems on wheels are currently unstable and require a control mechanism to increase stability, resulting in much research requirement to develop an appropriate controller algorithm for wheeled mobile robot systems. Proportional, integral, derivative (PID) controllers are currently widely used for this purpose, but the PID approach is frequently inappropriate due to disruptions or fluctuations in parameters. Other control approaches, such as linear-quadratic regulator (LQR) control, can be used to address some of the issues associated with PID controllers. In this study, a kinematic model of a four-wheel skid-steering mobile robot was developed to test the functionality of LQR control. Three scenarios (control cheap, non-zero state expensive; control expensive, non-zero state cheap; only non-zero state expensive) were examined using the characteristics of the wheeled mobile robot. Peak time, settling time, and rising time for cheap control based on these scenarios was found to be 0.1 s, 7.82 s, and 4.39 s, respectively. [ABSTRACT FROM AUTHOR]

To effectively mitigate the spread of epidemics, disinfection robots are increasingly utilized for automatic disinfection. However, tradition robots and disinfection methods cannot ensure controllable disinfection coverage, potentially causing damage to sensitive surfaces and humans. In this paper, we introduce a novel Ultraviolet-C disinfection robot system built on the mobile manipulator structure. We propose a new multi-side disinfection end-effector to broaden the disinfection scope and improve adaptability to complex surfaces. In order to coordinate the movements of the base and manipulator, we propose a joint base placement and multi-configuration disinfected path planning(JPMDP) method. The algorithm generates the minimal number of mobile base placements and forms the disinfection path with the shortest working time. We have conducted extensive experiments in both simulated and real environments. Experimental results demonstrate that our system offers more comprehensive coverage in less time compared to traditional strategies, making it more efficient and adaptable to complex environments. • Proposing a novel UV-C disinfection robot for epidemic control. • Introducing a multi-side disinfection end-effector for complex surface adaptability. • Presenting a JPMDP method for optimal coordination of base and manipulator movements. • Validating the system's efficiency through extensive simulations and real tests. [ABSTRACT FROM AUTHOR]

Robot sequential decision-making in the real world is a challenge because it requires the robots to simultaneously reason about the current world state and dynamics, while planning actions to accomplish complex tasks. On the one hand, declarative languages and reasoning algorithms support representing and reasoning with commonsense knowledge. But these algorithms are not good at planning actions toward maximizing cumulative reward over a long, unspecified horizon. On the other hand, probabilistic planning frameworks, such as Markov decision processes (MDPs) and partially observable MDPs (POMDPs), support planning to achieve long-term goals under uncertainty. But they are ill-equipped to represent or reason about knowledge that is not directly related to actions. In this article, we present an algorithm, called iCORPP, to simultaneously estimate the current world state, reason about world dynamics, and construct task-oriented controllers. In this process, robot decision-making problems are decomposed into two interdependent (smaller) subproblems that focus on reasoning to "understand the world" and planning to "achieve the goal" respectively. The developed algorithm has been implemented and evaluated both in simulation and on real robots using everyday service tasks, such as indoor navigation, and dialog management. Results show significant improvements in scalability, efficiency, and adaptiveness, compared to competitive baselines including handcrafted action policies. • This article formally introduces the Integrated Reasoning and Planning (IRP) problem for robots. An IRP problem has a factored state space that is specified by a set of endogenous and exogenous variables. • This article introduces a sequential decision-making algorithm, called Interleaved Commonsense Reasoning and Probabilistic Planning (iCORPP), for addressing IRP problems. • This article presents systematic evaluations of iCORPP using two tasks of mobile robot navigation, and spoken dialog systems, as demonstrated on a real robot. • This article builds on our previous research that appeared in two conference papers (Zhang and Stone, 2015; Zhang et al., 2017). This article unifies their terminology, problem statements, and algorithms. • Compared to our prior work, this article introduces a new problem statement in Section 4.1, which covers the problems addressed in both conference papers. • To address the IRP problem, we have reformulated the iCORPP algorithm (Section 4.2) into a novel form that includes the three key steps of "logical reasoning," "probabilistic reasoning over world states," and "probabilistic reasoning about world dynamics." [ABSTRACT FROM AUTHOR]

The goal of this research is to devise guaranteed defense policies that allow to protect a given region from the entrance of smart mobile invaders by detecting them using a team of defending agents equipped with identical line sensors. By designing cooperative defense strategies that ensure all invaders are detected, conditions on the defenders' speed are derived. Successful accomplishment of the defense task implies invaders with a known limit on their speed cannot slip past the defenders and enter the guarded region undetected. The desired outcome of the defense protocols is to defend the area and additionally to expand it as much as possible. Expansion becomes possible if the defenders' speed exceeds a critical speed that is necessary to only defend the initial region. We present results on the total search time, critical speeds and maximal expansion possible for two types of novel pincer-movement defense processes, circular and spiral, for any even number of defenders. The proposed spiral process allows to detect invaders at nearly the lowest theoretically optimal speed, and if this speed is exceeded, it also allows to expand the protected region almost to the maximal area. • Development of guaranteed defense policies of a given region against smart invaders. • Theoretical and simulative analysis of trajectories, speeds and search times. • Introduction of two novel pincer guarding and expansion strategies. • Comparison between developed defense pincer sweep guarding and expansion strategies. • Performance of spiral defense pincer protocol provides state-of-the-art results. [ABSTRACT FROM AUTHOR]

Non-prehensile cooperative object transportation is a challenging model problem for distributed control and organization methods but also has practical applications. Therefore, it is widely studied in distributed robotics research. This paper describes and evaluates a novel transportation scheme for differential-drive mobile robots that is, to the authors' best knowledge, the most versatile scheme of its kind successfully evaluated with real-world hardware. The proposed scheme can conceptually deal with any number of robots and arbitrary polygonal objects, including non-convex ones, without having to retune, retrain, or reconfigure any of the control parameters between different scenarios. This is achieved by splitting the task into a formation control and a formation finding task, both of which are tackled with model-based approaches using distributed optimization. Formation control and formation finding are complicated by the robots' non-holonomic kinematic constraints. Therefore, a tailored distributed model predictive controller is used for formation control. Finding formations relies on a multibody-dynamics representation of the robots-object system to properly account for contact and non-holonomic constraints. Due to these measures, the transportation scheme achieves a very satisfactory performance and dexterity in real-world hardware experiments utilizing network communication and distributed computation. • First time such a versatile scheme is shown to work with non-holonomic robot hardware. • Convex and non-convex object shapes can be considered. • Fully distributed decision-making, no scenario-specific parameter tuning. • Non-holonomic constraints are naturally considered using multibody dynamics. • Distributed predictive control and distributed optimization serve as key methods. [ABSTRACT FROM AUTHOR]

Hedge algebra is gaining increasing attention due to its high efficiency and fast calculation speed compared to fuzzy logic. This paper proposes the first algebra-based formation controller with a leader–follower approach to maintain the desired formation of multiple robots. In each time step, the controller computes the desired positions of the followers and strives to minimize the distance between them and their desired positions. We evaluate the performance of this controller on our robots using ROS in a virtual environment with Gazebo. Our work proves hedge algebra's significant potential in the mobile robots' domain, specifically in formation control. HAFC allows not only the precise formation of a robot swarm into any desired formation, with minimal deviation but also adaptive transition to the different formations. Our results show that HAFC can effectively maintain the desired formation of multiple robots, even in certain extraordinary situations. Furthermore, HAFC exhibits higher efficiency than the fuzzy logic-based controller, as evidenced by its faster adaptation rate and shorter computation time. The proposed approach has the potential to be applied in various real-world scenarios, such as surveillance, transportation, and exploration, where the robot has to move in formation and change formation accordingly with the terrain. • This work is the first study in formation control of mobile robots and adaptive formation translation based on the Hedge-algebras theory. • HAFC exhibits higher efficiency compared to the fuzzy logic-based controller, as evidenced by its faster adaptation rate and shorter computation time. • The simulation is implemented on ROS and obtain a high accuracy and miniature errors. A structure is proposed so as to conduct real formation experiments. • The proposed approach has the potential to be applied in various real-world scenarios, such as surveillance, transportation, and exploration, where the robots have to move in formation and change formation accordingly with the terrain. [ABSTRACT FROM AUTHOR]

One of the main issues in robotics systems is planning and tracking a safe path in diverse environments. This paper addresses an optimal methodology for generating the desired path and thereafter forces the mobile robot to follow the designed reference path. The proposed technique has the potential to tackle the inherent challenges and intricacies of the environment, enabling the robot to navigate both static and dynamic workspaces. Several simulations are exploited to verify the captured theoretical results. Three cases were examined in a static environment, achieving average performance metrics for reference signals in the X- and Y-directions, and heading tracking of 99.62%, 99.64%, and 95.08%, respectively. For the dynamic environment, two cases were studied, with average performance in following the Y-direction and heading angle recorded as 97.58% and 86.79%, respectively. Simulation results show that the controller calculated the optimal signal with an average computational time of 7 ms per iteration for static environments and 21.3 ms per iteration for dynamic environments. • Low computational time : the computational time of path planner and path following is studied, and for the later, CasADi toolkit is used to minimize the computational time. • Path planner algorithm is complete : guarantees to find an existing path. • Systematic approach : the whole algorithm is explained in the paper facilitates further studies and enables a better understanding of the approach. • Applicable to a wide range of robot types : the proposed algorithm is suitable for any spatial search, and easily extentable to higher dimensions. [ABSTRACT FROM AUTHOR]

Mobile robots have increasingly been used in warehouses, factories, open spaces, on roads, and urban areas to transport goods and people. Path planning in complex and large environments using classical graph-based search is computationally too intensive. One of the main challenges of mobile robotics is describing the large robot's workspaces with a reduction of graph complexity and improvement of path planning efficiency. A representation by a hierarchical graph (H-graph) facilitates graph creation and reduces the complexity of path planning. In this paper, we present an algorithm for autonomously generating a hierarchical graph of the environment from floor plans. The hierarchical abstraction depicts the environment in levels, from the most detailed to the most abstract representation of the environment, where pre-computed partial paths at the most detailed level are graph edges at a higher level. We use the E* algorithm to find partial paths in the most detailed abstraction level, and we propose the extraction of higher levels automatically from lower levels. We verified the proposed H-graph creation on three cases: our University premises as an example of a multi-building environment, a large warehouse with a lot of shelves, and an outdoor urban environment which is represented by a city map. All cases result in five abstract levels. The result shows that the path planning algorithm searches about 50 to 800 times fewer nodes when using the H-graph as the environment representation than when using a plain graph representing the entire environment as an occupancy grid map. • Autonomous creation of an H-graph with five or more levels. • Generation of nodes in H-graph that represent the elevators and the passages between the buildings. • Autonomous creation of an H-Graph with natural close-to-optimal paths and autonomous identification of bridge nodes. • Analysis of partial paths and nodes of the H-graph on three cases of environment. • Analysis of the created hierarchy on the path planning examples in three cases of environment using three different resolutions. [ABSTRACT FROM AUTHOR]

We present a novel method for navigation of mobile robots in challenging dynamic environments. The method, which is based on Nonlinear Model Predictive Control (NMPC), hinges upon a specially devised constraint for dynamics-aware collision avoidance. In particular, the constraint builds on the notion of avoidable collision state , taking into account the robot actuation capabilities in addition to the robot–obstacle relative distance and velocity. The proposed approach is applied to both ground and flying robots and tested in a variety of static and dynamic environments. Comparative simulations with an NMPC using a purely distance-based collision avoidance constraint confirm the superiority of the dynamics-aware version, especially for high-speed navigation among moving obstacles. Moreover, the results indicate that the method can work with relatively short prediction horizons and is therefore amenable to real-time implementation. • Robot navigation among obstacles at high-speed using Model Predictive Control. • Dynamics-aware collision avoidance enhances robot safety. • Dynamics-aware collision avoidance outperforms its distance-based counterpart. • Integration of velocity fields aids the robot in circumventing obstacles. [ABSTRACT FROM AUTHOR]

Autonomous systems for monitoring and surveying are increasingly used in retail stores, since they improve the overall performance of the store and reduce the manpower cost. Moreover, an automated system improves the accuracy of collected data by avoiding human-related factors. This paper presents ROCKy, a mobile robot for data collection and surveying in a retail store that autonomously navigates and monitors store shelves based on real-time store heat maps; ROCKy is designed to automatically detect Shelf Out of Stock (SOOS) and Promotional Activities (PA) based on Deep Convolutional Neural Networks (DCNNs). The deep learning approach evaluates visual and textual content of an image simultaneously to classify and map SOOS and PA events during working hours. The proposed approach was applied and tested on several real scenarios, presenting a new public dataset with more than 14.000 annotated shelves images. Experimental results confirmed the effectiveness of the approach, showing high accuracy (up to 87%) in comparison with the existing state of the art SOOS and PA monitoring solutions, and a signification reduction of retail surveying time (45%). • ROCKy is a mobile robot for data collection and surveying in a retail store. • ROCKy detects Shelf Out of Stock and Promotional Activities based on Deep Learning. • The deep learning approach evaluates visual and textual content of an image. • The approach was applied on a new public dataset with annotated shelves images. • Experimental results confirmed the effectiveness of the approach. [ABSTRACT FROM AUTHOR]

This paper considers the motion planning problem for multiple tethered planar mobile robots. Each robot is attached to a fixed base by a flexible cable. Since the robots share a common workspace, the interactions amongst the robots, cables, and obstacles pose significant difficulties for planning. Previous works have studied the problem of detecting whether a target cable configuration is intersecting (or entangled). Here, we are interested in the motion planning problem: how to plan and coordinate the robot motions to realize a given non-intersecting target cable configuration. We identify four possible modes of motion, depending on whether (i) the robots move in straight lines or following their cable lines; (ii) the robots move sequentially or concurrently. We present an in-depth analysis of Straight/Concurrent, which is the most practically-interesting mode of motion. In particular, we propose algorithms that (a) detect whether a given target cable configuration is realizable by a Straight/Concurrent motion, and (b) return a valid coordinated motion plan. The algorithms are analyzed in detail and validated in simulations and in a hardware experiment. • Plan coordinated motions for tethered mobile robots, avoiding cable entanglement. • Detect realizability of a target cable configuration by Straight/Concurrent motion. • Guarantee to return a valid coordinated motion plan if there exists one. • Improve efficiency, reduce localization errors and enhance working area safety. • Demonstrate the capability of the proposed algorithms on hardware robotic system. [ABSTRACT FROM AUTHOR]

In order to synthesize controllers for wheeled mobile robots (WMRs), some design techniques are usually based on the assumption that the set of kinematic constraints are fully satisfied. Nevertheless, when a WMR moves on a trajectory, phenomena such as slipping, skidding and deformability (also related to flexibility) can cause violation of kinematic constraints as well as system instability. Previous research has shown that to make the tracking error converge toward a small neighborhood containing the origin, in WMRs that moving at different speeds, it can be used an outer closed-loop scheme based on an auxiliary control law with aid of estimations of the slipping and skidding variations. But, although these previous works use slipping/skidding variations, the flexibility parameter is not taken into account to compute the auxiliary control law, making the outer closed-loop less robust for different flexibility values in the dynamic. The work reported here proposes a control scheme fully influenced by the flexibility parameter and whose robustness will be based on an auxiliary control law that uses a nonlinear function in terms of flexibility and slipping/skidding variations. The results obtained from experimental and simulations tests will show that the flexible auxiliary control law not only ensures that the error converges to a small neighborhood close to origin but also it is more insensitive to the speed increasing of the WMR. • Wheeled mobile robots become unstable with slipping, skidding, and flexibility. • Tracking error converges toward a neighborhood of the origin when an auxiliary control law is used. • Better robustness is guaranteed when the flexibility is included in the auxiliary control law. • Dynamic confined space of velocities can be used to synthesize a flexible version of the auxiliary control law. • The flexible auxiliary control law is more insensitive to the speed increasing. [ABSTRACT FROM AUTHOR]

Emerging industrial applications involving mobile manipulation in the presence of humans is driving attention towards steerable wheeled mobile robots (SWMR), since these can perform arbitrary 2 D planar trajectories, providing a reasonable compromise between maneuverability (necessary for human avoiding algorithms) and effectiveness. Instantaneous center of rotation (ICR) based kinematic models and controllers are the most suited for such robots, as they assure the existence of a unique ICR point at all times. However, unsatisfactory behavior do exist in numerous applications requiring frequent changes in the sign of the angular velocity command. This is typically the case for robot heading control: moving the ICR point from one border of the 2 D ICR space to the other makes it pass by the robot geometric center, where only pure rotations are feasible. This behavior is not desirable and should be avoided. In this paper, we propose a novel complementary route ICR controller, where the ICR can go from one extreme to the other by means of border switching in one sample period. Thanks to this approach, fast response to the velocity commands is achieved with little steering motion. The new algorithm has been tested successfully in simulations and experiments, and is more time efficient with far more satisfactory behavior than the state-of-art direct route based controllers. These results have been also confirmed quantitatively, using a newly developed metric, the command fulfillment index (CFI). [ABSTRACT FROM AUTHOR]

Novelty detection is a very useful function for detecting abnormal data in any application. An expectation-based novelty-detection approach has been introduced that learns the dynamic relationship model among normal data in order to predict the next expected data. Most novelty-detection systems use an offline approach with a fixed structure, a system type that has limitations when the data count in the environment is unknown. A new expectation-based novelty-detection system features an online recurrent neural network approach that learns the data by inserting new nodes or deleting unused nodes from its structure. Generally, to detect novelties, a global novelty threshold is defined to filter out all input data as novel whenever the prediction error of the network exceeds the threshold. However, because a neural network cannot learn to predict all classes of input data perfectly, using a global novelty threshold leads to the misclassification of the insufficiently learned normal data as novel. To overcome this problem, the novelty-detection system has been improved to learn local novelty thresholds alongside its learning to predict expectations. The proposed algorithm is applied to an online novelty detection using colour and depth data obtained from a Kinect sensor on a mobile robot. The performance of the expected novelty detector and its limitations during experiments are analysed and shown. Furthermore, colour and depth data as inputs into the novelty filter are separately analysed and their contributions on the overall novelty detection highlighted. In conclusion, the performance of the novelty filter could further be improved by applying a better feature-selection technique to extract more interesting features from high-dimensional input data. [ABSTRACT FROM AUTHOR]

When working in dynamic environment, traditional SLAM framework performs poorly due to interference from dynamic objects. By taking advantages of deep learning in object detection, a semantic simultaneous localization and mapping framework named Dynamic-SLAM is proposed, in order to solve the problem of SLAM in dynamic environment. First, based on the convolutional neural network, an SSD object detector which combines prior knowledge is constructed to detect dynamic objects in the newly detection thread at semantic level. Then, in view of low recall rate of the existing SSD object detection network, a missed detection compensation algorithm based on the speed invariance in adjacent frames is proposed, which greatly improves the recall rate of detection. Finally, a feature-based visual SLAM system is constructed, which processes the feature points of dynamic objects through a selective tracking algorithm in the tracking thread, to significantly reduce the error of pose estimation caused by incorrect matching. The recall rate of the system is increased from 82.3% to 99.8% compared with the original SSD network. Several experiments show that the localization accuracy of Dynamic-SLAM is higher than the state-of-the-art systems. The system successfully localizes and constructs an accurate environmental map in real-world dynamic environment by using a mobile robot. In sum, our experimental demonstrations verify that Dynamic-SLAM shows improved accuracy and robustness in robot localization and mapping comparing to the state-of-the-art SLAM system in dynamic environment. • An SSD object detector is constructed to detect dynamic objects with prior knowledge in the newly detection thread. • Missed detection compensation algorithm based on the speed invariance in adjacent frames is proposed. • Selection tracking algorithm is proposed to eliminate the dynamic objects and improve the robustness and accuracy of the system. • A feature-based Dynamic-SLAM system combined semantic information is constructed to realize the detection of dynamic environment in robot localization and mapping. [ABSTRACT FROM AUTHOR]

Desert ants use the polarization of skylight and a combination of stride and ventral optic flow integration processes to track the nest and food positions when traveling, achieving outstanding performances. Navigation sensors such as global positioning systems and inertial measurement units still have disadvantages such as their low resolution and drift. Taking our inspiration from ants, we developed a 2-pixel celestial compass which computes the heading angle of a mobile robot in the ultraviolet range. The output signals obtained with this optical compass were investigated under various weather and ultraviolet conditions and compared with those obtained on a magnetometer in the vicinity of our laboratory. After being embedded on-board the robot, the sensor was first used to compensate for random yaw disturbances. We then used the compass to keep the Hexabot robot's heading angle constant in a straight forward walking task over a flat terrain while its walking movements were imposing yaw disturbances. Experiments performed under various meteorological conditions showed the occurrence of steady state heading angle errors ranging from 0. 3 ∘ (with a clear sky) to 2. 9 ∘ (under changeable sky conditions). The compass was also tested under canopies and showed a strong ability to determine the robot's heading while most of the sky was hidden by the foliage. Lastly, a waterproof, mono-pixel version of the sensor was designed and successfully tested in a preliminary underwater benchmark test. These results suggest this new optical compass shows great precision and reliability in a wide range of outdoor conditions, which makes it highly suitable for autonomous robotic outdoor navigation tasks. A celestial compass and a minimalistic optic flow sensor called M 2 APix (based on Michaelis–Menten Auto-adaptive Pixels) were therefore embedded on-board our latest insectoid robot called AntBot, to complete the previously mentioned ant-like homing navigation processes. First the robot was displaced manually and made to return to its starting-point on the basis of its absolute knowledge of the coordinates of this point. Lastly, AntBot was tested in fully autonomous navigation experiments, in which it explored its environment and then returned to base using the same sensory modes as those on which desert ants rely. AntBot produced robust, precise localization performances with a homing error as small as 0.7% of the entire trajectory. [ABSTRACT FROM AUTHOR]

Abstract As autonomous service robots become more affordable and thus available for the general public, there is a growing need for user-friendly interfaces to control these systems. Control interfaces typically get more complicated with increasing complexity of robotic tasks and environments. Traditional control modalities such as touch, speech or gesture are not necessarily suited for all users. While some users can make the effort to familiarize themselves with a robotic system, users with motor disabilities may not be capable of controlling such systems even though they need robotic assistance most. In this paper, we present a novel framework that allows these users to interact with a robotic service assistant in a closed-loop fashion, using only thoughts. The system is composed of several interacting components: a brain–computer interface (BCI) that uses non-invasive neuronal signal recording and co-adaptive deep learning, high-level task planning based on referring expressions, navigation and manipulation planning as well as environmental perception. We extensively evaluate the BCI in various tasks, determine the performance of the goal formulation user interface and investigate its intuitiveness in a user study. Furthermore, we demonstrate the applicability and robustness of the system in real-world scenarios, considering fetch-and-carry tasks, close human–robot interactions and in presence of unexpected changes. As our results show, the system is capable of adapting to frequent changes in the environment and reliably accomplishes given tasks within a reasonable amount of time. Combined with high-level task planning based on referring expressions and an autonomous robotic system, interesting new perspectives open up for non-invasive BCI-based human–robot interactions. Highlights • BCI-controlled autonomous robotic service assistant. • First online brain–computer-interface using deep learning. • Menu-driven language generation based on referring expressions. • Modular ROS-based mobile robot interaction. • Experimental evaluation with a real robot. [ABSTRACT FROM AUTHOR]

Abstract Q-learning, a type of reinforcement learning, has gained increasing popularity in autonomous mobile robot path planning recently, due to its self-learning ability without requiring a priori model of the environment. Yet, despite such advantage, Q-learning exhibits slow convergence to the optimal solution. In order to address this limitation, the concept of partially guided Q-learning is introduced wherein, the flower pollination algorithm (FPA) is utilized to improve the initialization of Q-learning. Experimental evaluation of the proposed improved Q-learning under the challenging environment with a different layout of obstacles shows that the convergence of Q-learning can be accelerated when Q-values are initialized appropriately using the FPA. Additionally, the effectiveness of the proposed algorithm is validated in a real-world experiment using a three-wheeled mobile robot. Highlights • We propose an improved Q-learning to solve path planning of a mobile robot. • The flower pollination algorithm is used to initialize the Q-table prior to the implementation of Q-learning. • Its effectiveness is tested in solving the optimal path in different test cases. • Performance comparison with classical Q-learning and other modified Q-learning is made. • The proposed model shows improvement in terms of computational time than others. [ABSTRACT FROM AUTHOR]

Abstract Robots operating in populated environments, such as hospitals, office environments or airports, encounter a large variety of people with some of them having an advanced need for cautious interaction because of their advanced age or motion impairments. To provide appropriate assistance and support robot helpers require the ability to recognize people and their potential requirements. In this article, we present a people detection framework that distinguishes people according to the mobility aids they use. Our framework uses a deep convolutional neural network for detecting people in image data. For human-aware robots it is necessary to know where people are in a 3D world reference frame instead of only locating them in a 2D image, therefore we add a 3D centroid regression output to the network to predict the Cartesian position of people. We further use a probabilistic class, position and velocity tracker to account for false detections and occlusions. Our framework comes in two variants: The depth only variant targets high privacy demands, while the RGB only framework provides improved detection performance for non-critical applications. Both variants do not require additional geometric information about the environment. We demonstrate our approach using a dedicated dataset acquired with the support of a mobile robotic platform. The dataset contains five classes: pedestrian, person in wheelchair, pedestrian pushing a person in a wheelchair, person using crutches and person using a walking frame. Our framework achieves an mAP of 0.87 for RGB and 0.79 for depth images at a detection distance threshold of 0.5 m on our dataset, with a runtime of 53 ms per image. The annotated dataset is publicly available and our framework is made open source as a ROS people detector. Highlights • Deep learning-based framework for 3D people detection. • Perception of people according to their mobility aids. • Flexible with respect to the employed sensor modality: RGB or depth. • Probabilistic position, velocity and class estimation module enhances detector. • Enables service robots to assist people according to their impairments. [ABSTRACT FROM AUTHOR]

Abstract Autonomous navigation of mobile robots is often based on information from a variety of heterogeneous sensors; hence, extrinsic sensor calibration is a fundamental step in the fusion of such information. In this paper, we address the problem of extrinsic calibration of a radar–LiDAR–camera sensor system. This problem is primarily challenging due to sparse informativeness of radar measurements. Namely, radars cannot extract rich structural information about the environment, while their lack of elevation resolution, that is nevertheless accompanied by substantial elevation field of view, introduces uncertainty in the origin of the measurements. We propose a novel calibration method which involves a special target design and two-step optimization procedure to solve the aforementioned challenges. First step of the optimization is minimization of a reprojection error based on an introduced point–circle geometric constraint. Since the first step is not able to provide reliable estimates of all the six extrinsic parameters, we introduce a second step to refine the subset of parameters with high uncertainty. We exploit a pattern discovered in the radar cross section estimation that is correlated to the missing elevation angle. Additionally, we carry out identifiability analysis based on the Fisher Information Matrix to show minimal requirements on the dataset and to verify the method through simulations. We test the calibration method on a variety of sensor configurations and address the problem of radar vertical misalignment. In the end, we show via extensive experiment analysis that the proposed method is able to reliably estimate all the six parameters of the extrinsic calibration. Highlights • Extrinsic radar–camera–LiDAR calibration estimated accurately in all 6DoF. • Radar's missing elevation angle compensated with radar cross section measurements. • Method is suitable for radar vertical misalignment detection. • Identifiability analysis confirms chosen transform parametrization. • Identifiability analysis provides minimal requirements on the dataset. [ABSTRACT FROM AUTHOR]

Abstract Accurate localization is an essential technology for flexible automation. Industrial applications require mobile platforms to be precisely localized in complex environments, often subject to continuous changes and reconfiguration. Most of the approaches use precomputed maps both for localization and for interfacing robots with workers and operators. This results in increased deployment time and costs as mapping experts are required to setup the robotic systems in factory facilities. Moreover, such maps need to be updated whenever significant changes in the environment occur in order to be usable within commanding tools. To overcome those limitations, in this work we present a robust and highly accurate method for long-term LiDAR-based indoor localization that uses CAD-based architectural floor plans. The system leverages a combination of graph-based mapping techniques and Bayes filtering to maintain a sparse and up-to-date globally consistent map that represents the latest configuration of the environment. This map is aligned to the CAD drawing using prior constraints and is exploited for relative localization, thus allowing the robot to estimate its current pose with respect to the global reference frame of the floor plan. Furthermore, the map helps in limiting the disturbances caused by structures and clutter not represented in the drawing. Several long-term experiments in changing real-world environments show that our system outperforms common state-of-the-art localization methods in terms of accuracy and robustness while remaining memory and computationally efficient. Highlights • Build a pose graph online using trajectory priors to align it to the floor plan. • Switch to pure localization whenever the environment is sufficiently mapped. • Estimate the robot pose using relative localization with respect to the pose graph. • Maintain an up-to-date pose graph in changing environments using Bayes filtering. • Bound memory consumption and runtime to enable long-term operation. [ABSTRACT FROM AUTHOR]

Abstract The problem of object localization and recognition on autonomous mobile robots is still an active topic. In this context, we tackle the problem of learning a model of visual saliency directly on a robot. This model, learned and improved on-the-fly during the robot's exploration provides an efficient tool for localizing relevant objects within their environment. The proposed approach includes two intertwined components. On the one hand, we describe a method for learning and incrementally updating a model of visual saliency from a depth-based object detector. This model of saliency can also be exploited to produce bounding box proposals around objects of interest. On the other hand, we investigate an autonomous exploration technique to efficiently learn such a saliency model. The proposed exploration, called Reinforcement Learning-Intelligent Adaptive Curiosity (RL-IAC) is able to drive the robot's exploration so that samples selected by the robot are likely to improve the current model of saliency. We then demonstrate that such a saliency model learned directly on a robot outperforms several state-of-the-art saliency techniques, and that RL-IAC can drastically decrease the required time for learning a reliable saliency model. [ABSTRACT FROM AUTHOR]

Abstract When applied in some harsh environments (e.g. in poisonous atmosphere or underwater), odor source localization robots are able to perform better than animals without being hurt. During the past three decades, robotic odor source localization has become a popular research field with various algorithms being proposed. These algorithms can be roughly divided into four categories: gradient-based algorithms, bio-inspired algorithms, multi-robot algorithms and probabilistic and map-based algorithms. In this paper, we present a literature review of these four categories and discuss their pros and cons. We also discuss the current trends and some future challenges according to some research papers published in recent years. [ABSTRACT FROM AUTHOR]

Abstract This article proposes a method for sensor fusion between odometers, gyroscope, accelerometer, magnetometer and visual landmark localization system. The method is designed for estimation of all 6 degrees of freedom (both translation and attitude) of a wheeled robot moving in uneven terrain. The fusion method is based on continuous estimation of the mean square error of each estimated value and allows different sampling rates of each sensor. Due to the simple implementation, it is suitable for real-time processing in the low-cost hardware. In order to evaluate the precision of the estimated position, stochastical models of sensors (with parameters matching real hardware sensors) were used and random trajectories were simulated. The virtual experiments showed that the method is resistant to the failure of any sensor except the odometers; however, each sensor provides improvement in the resultant precision. Highlights • Article proposes new sensor fusion method combining variety of sensors' readings. • Method utilizes inertial sensors, landmarks, odometers and magnetometer. • The method is suitable for estimating the position of a wheeled vehicle. • The simplicity of the method allows its implementation into low-cost hardware. [ABSTRACT FROM AUTHOR]

Abstract This paper presents a new approach to view-based localization and navigation in outdoor environments, which are indispensable functions for mobile robots. Several approaches have been proposed for autonomous navigation. GPS-based systems are widely used especially in the case of automobiles, however, they can be unreliable or non-operational near tall buildings. Localization with a precise 3D digital map of the target environment also enables mobile robots equipped with range sensors to estimate accurate poses, but maintaining a large-scale outdoor map is often costly. We have therefore developed a novel view-based localization method SeqSLAM++ by extending the conventional SeqSLAM in order not only to robustly estimate the robot position comparing image sequences but also to cope with changes in a robot's heading and speed as well as view changes using wide-angle images and a Markov localization scheme. According to the direction to move provided by the SeqSLAM++, the local-level path planner navigates the robot by setting subgoals repeatedly considering the structure of the surrounding environment using a 3D LiDAR. The entire navigation system has been implemented in the ROS framework, and the effectiveness and accuracy of the proposed method was evaluated through off-line/on-line navigation experiments. [ABSTRACT FROM AUTHOR]