Search

This paper details the design and preliminary demonstrations for a compact climbing robot named EEWOC (Extended-reach Enhanced Wheeled Orb for Climbing). This novel platform utilizes the EEMMMa limb (Elastic Extending Mechanism for Mobility and Manipulation), detailed in previous work. This highly extendable and bendable robotic limb utilizes a unique tape spring structure for long reach in a small, lightweight package. EEWOC combines this limb with additional degrees of freedom and two magnetic grippers to allow it to ascend vertical metal surfaces by consecutively extending and gripping. It is also equipped with wheels for horizontal mobility. A key advantage of this system is EEWOC's ability to bend to place its grippers around obstacles or corners and above ledges. The prototype is small and lightweight, with a profile of 25x30x30 cm and weight of 1.8 kg, while able to extend its limb up to 1.2 m away. With versatile movement options, EEWOC has the potential to fully traverse large metal structures such as ships or buildings for use in inspection tasks. This paper presents a detailed view of the overall system and mechanism design, and successful climbing demonstrations are shown on steel structures. The paper concludes by detailing EEWOC's future capabilities and additional tests and theories needed to refine its maneuvers and control.

For autonomous navigation, a mobile robot is required to move toward a destination while avoiding obstacles. In this paper, we present a motion planner based on CNN. In terms of obstacle avoidance, since a position of a dynamic obstacle changes with time, it is important for the robot to plan avoidance motions in consideration of the time series variation in the images. For this purpose, an LSTM block is applied to the CNN. The policy of the motion planner represented by CNN with LSTM is trained through imitation learning. In this regard, however, it is difficult for the robot to recognize unknown objects as obstacles. For obstacle recognition, a perception process is further provided between the image inputs and CNN with LSTM in the motion planner. Moreover, the robot plans different avoidance motions depending on the velocity of the dynamic obstacle. For this purpose, an obstacle state classifier based on CNN is used ahead of the motion planner. A depth-difference image generated from two depth images is fed as the input to the classifier. A classified state that indicates the velocity of the obstacle is fed as the input to the following motion planner. In the navigation experiments, we show that the robot based on the proposed motion planner is able to move toward a destination autonomously while avoiding standing and walking persons, respectively. Furthermore, we show that the robot based on the motion planner with the obstacle state input is able to plan different avoidance motions for a person walking slowly or fast using the obstacle state classifier.

The stability of the Tracking Wheel Mobile Robot with Teleoperation System and Path Following Method is discussed in this study. The path is to be tracked by the host computer which is the master robot. The response from the robot is captured on camera. As the slave robot approaches the target position, the camera captures the response robot's position and as well as moving trajectory. The host computer receives all of the images, enabling mobile robot deviation recoveries. The slave robot can use teleoperation to follow the sensor based on the decisions made by the master robot. The Lyapunov function in the Fuzzy Neural Network (FNN) control structure assures the system's stability and satisfactory performance. It supports a mobile robot's ability to adhere to a reference trajectory without deviating from it. Finally, the outcome of the simulation demonstrates that our controller is capable of tracking different environmental conditions and maintaining stability. [ABSTRACT FROM AUTHOR]

Fires are one of the most dangerous hazards and the leading cause of death in construction sites. This paper proposes a video-based firefighting mobile robot (FFMR), which is designed to patrol the desired territory and will constantly observe for fire-related events to make sure the camera without any occlusions. Once a fire is detected, the early warning system will send sound and light signals instantly and the FFMR moves to the right place to fight the fire source using the extinguisher. To improve the accuracy and speed of fire detection, an improved YOLOv3-Tiny (namely as YOLOv3-Tiny-S) model is proposed by optimizing its network structure, introducing a Spatial Pyramid Pooling (SPP) module, and refining the multi-scale anchor mechanism. The experiments show the proposed YOLOv3-Tiny-S model based FFMR can detect a small fire target with relatively higher accuracy and faster speed under the occlusions by outdoor environment. The proposed FFMR can be helpful to disaster management systems, avoiding huge ecological and economic losses, as well as saving a lot of human lives. [ABSTRACT FROM AUTHOR]

Inspired by natural swarm systems, robotic swarms aim to solve complicated problems through the emergent behaviour of coordinating robots (agents). Communication among the robots is of paramount importance for their effective coordination, cooperation, and overall performance. This research presents a colour light-based communication system for miniature mobile swarm robots, on which a pre-trained supervised machine learning model runs and is responsible for effective colour recognition, enhancing inter-robot local communication. The performance of various supervised machine learning techniques was examined, and XGBoost performed best overall, with a classification accuracy of 96.66%, an execution time of 0.403 ms, an average sensing distance of 87.38 cm, and an acceptable size of 402.1 kilobytes while running on a 32-bit embedded microcontroller. The current work also demonstrates various swarming behaviours, utilising the developed communication as proof of concept. [ABSTRACT FROM AUTHOR]

In the field of autonomous mobile robots, sampling-based motion planning methods have demonstrated their efficiency in complex environments. Although the Rapidly-exploring Random Tree (RRT) algorithm and its variants have achieved significant success in known static environment, it is still challenging in achieving optimal motion planning in unknown dynamic environments. To address this issue, this paper proposes a novel motion planning algorithm Bi-HS-RRT X , which facilitates asymptotically optimal real-time planning in continuously changing unknown environments. The algorithm swiftly determines an initial feasible path by employing the bidirectional search. When dynamic obstacles render the planned path infeasible, the bidirectional search is reactivated promptly to reconstruct the search tree in a local area, thereby significantly reducing the search planning time. Additionally, this paper adopts a hybrid heuristic sampling strategy to optimize the planned path quality and search efficiency. The convergence of the proposed algorithm is accelerated by merging local biased sampling with nominal path and global heuristic sampling in hyper-ellipsoid region. To verify the effectiveness and efficiency of the proposed algorithm in unknown dynamic environments, numerous comparative experiments with existing algorithms were conducted. The experimental results indicate that the proposed planning algorithm has significant advantages in planned path length and planning time. [ABSTRACT FROM AUTHOR]

Copyright of Baghdad Science Journal is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Volatility in supply and demand caused by global disruptions such as wars or pandemics requires adaptable and changeable production systems. Since assembly accounts for significant production time and costs, the demand for changeable, line-less assembly systems is advancing. Controlling mobile robots in line-less assembly depends on understanding task executability. We propose the implementation of performance maps to evaluate the executability of assembly tasks within robot workspaces. Firstly, established performance metrics and typical assembly tasks are categorized to identify which metrics evaluate the executability of which type of tasks. The assembly tasks are grouped according to the type of movement (continuous or discrete), the required execution precision (high or low), and the amount of poses for execution (reachable or dexterous). The metrics are categorized according to their range (local or global), their physics (kinematic or dynamic), task reference (intrinsic or extrinsic), and scale (absolute or relative). Metrics are then matched to task types. This matching provides a systematic way to identify metrics to assess the executability of a task. Secondly, the performance map is presented. The performance map is a discretized representation of the distribution of chosen performance metrics for a specific robot. The current implementation is restricted to calculating the manipulability, dexterity, and condition number. Based on the input of a robot model and a task type, the metrics are calculated in distributed poses for a given resolution in the robot's workspace to form the performance map. The performance map is applied to exemplary tasks and robots. Previous approaches to workspace evaluation fail to consider the suitability of performance metrics to evaluate specific tasks, as different metrics are more or less relevant for different tasks. Consequently, the paper contributes by introducing performance maps and providing quantific metrics for comparing base placements of mobile robots according to the executability of specific assembly tasks. [ABSTRACT FROM AUTHOR]

Summary: The event‐triggered joint sensor fault estimation and mobile robot (MR) localization (MRL) problem (MRLP) subject to the potential fluctuations of the estimator gain are investigated. From the external sensor to the estimator, to decrease the consumption of sensor energy and cut down network bandwidth resources, an event‐triggered scheme is considered. For the sake of characterizing the phenomenon induced by the inaccurate calculation of estimator gain, an uncertainty with the bounded second moment is employed. The purpose of this study is theoretically to find a feasible and effective approach to the addressed joint estimation problem such that the estimation error (EE) covariance (EEC) meets the given performance index. First, a minimum upper bound (UB) of the EEC is derived. Subsequently, in terms of the proposed joint estimation approach and the corresponding results obtained, an algorithm to address the resilient joint sensor fault estimation and MRLP is summarized. At the end, the effectiveness of the proposed algorithm is validated through conducting a set of comparisive experiments. [ABSTRACT FROM AUTHOR]

This paper presents an improved Model Predictive Control (MPC) for path tracking of a nonholonomic mobile robot with a differential drive. Nonlinear dynamics and nonholonomic constraints make the optimisation problem of MPC for the robot challenging. Nonlinear dynamics of the robots are expressed by a Linear Parameter Varying (LPV), and a Recurrent Neural Network (RNN) solves the constrained optimisation problem, providing optimal velocities. Moreover, an interpolation-based approach has been introduced to augment the region of attraction. The algorithm ensures stability in the presence of bounded disturbances through the inclusion of free control moves in the control law. The controller efficiency has been evaluated in two scenarios in a hospital setting. The simulation results illustrate that the proposed method performs better than nonlinear MPC and standard LPV-based MPC in terms of computational cost, disturbance rejection, and region of attraction. [ABSTRACT FROM AUTHOR]

• A novel redundantly actuated series-parallel manipulator is proposed. • Unified recursive kinematics and statics models of the manipulator are established. • The theoretical model is validated by comprehensive numerical results. • Load/mass ratio of the tested manipulator in non-redundant actuation mode is 1.34. • The manipulator has higher load-carrying capacity in redundant actuation mode. Construction robots with mobile systems are an integral part of automatic building processes. However, with the vigorous development of prefabricated buildings, traditional manipulators have progressively failed to satisfy the requirements of handling heavy materials on construction sites. Thus, this paper proposes a redundantly actuated series-parallel manipulator (RAS-PM). To explore the feasibility of applying the manipulator in construction tasks, this paper establishes the unified recursive kinematics and statics of the manipulator and verifies the validity and reliability of the theoretical modeling method through comprehensive numerical results. The prototype of the manipulator is developed and installed on a bionic hexapod construction robot. The test results demonstrate that the manipulator exhibits an excellent load/mass ratio in non-redundant actuation mode, and its load-carrying capacity can be further enhanced with the optimized force/position hybrid actuation. In the on-site test, the robot can freely switch between modes to handle horizontal and vertical states of materials, such as curtain walls and large panels, thereby contributing to modern prefabricated construction. [ABSTRACT FROM AUTHOR]

Environmental mapping serves as a crucial element in Simultaneous Localization and Mapping (SLAM) algorithms, playing a pivotal role in ensuring the accurate representation necessary for autonomous robot navigation guided by SLAM. Current SLAM systems predominantly rely on grid-based map representations, encountering challenges such as measurement discretization for cell fitting and grid map interpolation for online posture prediction. Splines present a promising alternative, capable of mitigating these issues while maintaining computational efficiency. This paper delves into the efficiency disparities between B-Spline surface mapping and discretized cell-based approaches, such as grid mapping, within indoor environments. B-Spline Online SLAM and FastSLAM, utilizing Rao-Blackwellized Particle Filter (RBPF), are employed to achieve range-based mapping of the unknown 2D environment. The system incorporates deep learning networks in the B-Spline curve estimation process to compute parameterizations and knot vectors. The research implementation utilizes the Intel Research Lab benchmark dataset to conduct a comprehensive qualitative and quantitative analysis of both approaches. The B-Spline surface approach demonstrates significantly superior performance, evidenced by low error metrics, including an average squared translational error of 0.0016 and an average squared rotational error of 1.137. Additionally, comparative analysis with Vision Benchmark Suite demonstrates robustness across different environments, highlighting the effectiveness of B-Spline SLAM for real-world applications. [ABSTRACT FROM AUTHOR]

This work aims to develop a mobile robot utilizing neural network technology. The algorithm, programmed in Python on a Raspberry Pi 4B platform, is detailed across four main chapters. These chapters cover the fundamental assumptions of deep learning, the construction of the platform, and the research validating pattern recognition accuracy under various disturbances. The mobile platform employs a neural network to analyze selected traffic signs and translates the recognized patterns into corresponding motor movements. [ABSTRACT FROM AUTHOR]

Abstract This paper explores two non‐linear control techniques for designing an effective control system for an omnidirectional autonomous mobile robot with four Mecanum wheels. Due to the unique wheel structure and four separate wheels, the robot has non‐linear dynamics, multiple inputs and outputs. The first technique uses the state‐dependent Riccati equation (SDRE) to address optimal non‐linear control while considering energy and time constraints. The second technique, using an intermediate variable θ, has expanded the Hamilton‐Jacobi‐Belman equation in terms of the power series. Consequently, these equations are reduced to a set of recursive Lyapunov algebraic equations, leading to a closed‐form solution for solving the non‐linear optimal control problem. Finally, the maneuverability and path‐tracking capability of the robot are examined by highlighting the non‐linear term through numerical simulation.

This article focuses on the trajectory tracking control for a perturbed wheeled mobile robot (WMR) with slipping and skidding. The external disturbances and uncertainties caused by the slipping and skidding compose the "total" disturbance. By analyzing the stable state of the controlled system, the WMR reference model driven by a favorable disturbance is constructed. This article proposes an enhanced extended state observer (EESO) to reckon the difference between the "total" disturbance and the favorable disturbance. Then, a practical prescribed time tracking method is developed. By introducing a time‐dependent scaling function, the initial value restriction can be relaxed, and the peaking phenomenon caused by the EESO can be tolerated. With the proposed EESO and the prescribed time tracking controller, the estimation error is input‐to‐state stable, and the tracking control of WMR with global prescribed performance is achieved. Simulation results show the advantages. [ABSTRACT FROM AUTHOR]

The paper focuses on the problem of formal synthesis of controllers for control‐affine nonlinear systems against complex properties. Our goal is to design a closed‐form control policy that guarantees the satisfaction of complex properties that are expressed using (ω$$ \omega $$)‐regular languages and equivalently recognized by nondeterministic Büchi automata (NBA). We propose leveraging a funnel‐based control approach to provide a closed‐form solution to the problem. Our approach decomposes the specification represented by NBA into a sequence of reachability problems, which we solve using a funnel‐based control approach. Controllers associated with each reachability problem are then combined to design a hybrid control policy enforcing the desired (ω$$ \omega $$)‐regular property. We demonstrate the effectiveness of the proposed results on room temperature control and mobile robot motion control case studies. [ABSTRACT FROM AUTHOR]

Recent technological advancements and a growing emphasis on circular and adaptable architectural designs within established built environments have catalyzed innovative approaches in the realm of human-building interfaces (HBIs). HBIs represent a transformative paradigm in architecture and construction, centered on integrating interactive technologies into pre-existing building surfaces. In this study, we investigate the design potential of novel interfaces tailored for existing building surfaces, employing readily available responsive materials and mobile robots. Leveraging accessible interactive technologies, we present a comprehensive review of three early-stage strategies of HBIs: PainterFace, PixelFace, and PixelGreen. These HBIs were aimed at enriching user interaction and experience within their surroundings, fostering spaces that are both adaptive and interactive. Experimental HBIs are constructed using a range of responsive materials and mobile robots, including conductive paints, spherical mobile robots, and unmanned aerial vehicles functioning as “agents” to facilitate communication, interactivity, and responsiveness on existing building surfaces. The multifaceted nature of HBIs showcased in this paper presents diverse approaches with substantial potential to transform established building surfaces into interactive and responsive environments. A comparative analysis of the three HBIs highlights potential implications and future avenues for HBIs. Moreover, the findings of these studies provide valuable insights into design considerations, challenges, and future trajectories for the development and implementation of HBIs on existing building surfaces, ushering in a new era of intelligent and responsive built environments. Future endeavors will focus on further research to address challenges and unlock the full potential of HBIs, ultimately leading to the advancement of enhanced, adaptable, circular, and sustainable architectural designs. [ABSTRACT FROM AUTHOR]

Cognitive scientists believe that adaptable intelligent agents like humans perform spatial reasoning tasks by learned causal mental simulation. The problem of learning these simulations is called predictive world modeling. We present the first framework for a learning open-vocabulary predictive world model (OV-PWM) from sensor observations. The model is implemented through a hierarchical variational autoencoder (HVAE) capable of predicting diverse and accurate fully observed environments from accumulated partial observations. We show that the OV-PWM can model high-dimensional embedding maps of latent compositional embeddings representing sets of overlapping semantics inferable by sufficient similarity inference. The OV-PWM simplifies the prior two-stage closed-set PWM approach to the single-stage end-to-end learning method. CARLA simulator experiments show that the OV-PWM can learn compact latent representations and generate diverse and accurate worlds with fine details like road markings, achieving 69 mIoU over six query semantics on an urban evaluation sequence. We propose the OV-PWM as a versatile continual learning paradigm for providing spatio-semantic memory and learned internal simulation capabilities to future general-purpose mobile robots. [ABSTRACT FROM AUTHOR]

In this paper, we address the trajectory-/target-tracking and obstacle-avoidance problem for nonholonomic mobile robots subjected to diamond-shaped velocity constraints and predefined output performance specifications. The proposed scheme leverages the adaptive performance control to dynamically adjust the user-defined output performance specifications, ensuring compliance with input and safety constraints. A key feature of this approach is the integration of multiple constraints into a single adaptive performance function, governed by a simple adaptive law. Additionally, we introduce a robust velocity estimator with a priori-determined performance attributes to reconstruct the unmeasured trajectory/target velocity. Finally, we validate the effectiveness and robustness of the proposed control scheme, through extensive simulations and a real-world experiment. [ABSTRACT FROM AUTHOR]

Communication between connected objects in the Internet of Things (IoT) often requires secure and reliable authentication mechanisms to verify identities of entities and prevent unauthorized access to sensitive data and resources. Unlike other domains, IoT offers several advantages and opportunities, such as the ability to collect real-time data through numerous sensors. These data contains valuable information about the environment and other objects that, if used, can significantly enhance authentication processes. In this paper, we propose a novel idea to building opportunistic sensor-based authentication factors by leveraging existing IoT sensors in a system of systems approach. The objective is to highlight the promising prospects of opportunistic authentication factors in enhancing IoT security. We claim that sensors can be utilized to create additional authentication factors, thereby reinforcing existing object-to-object authentication mechanisms. By integrating these opportunistic sensor-based authentication factors into multi-factor authentication schemes, IoT security can be substantially improved. We demonstrate the feasibility and effectivenness of our idea through illustrative experiments in a parking entry scenario, involving both mobile robots and cars, achieving high identification accuracy. We highlight the potential of this novel method to improve IoT security and suggest future research directions for formalizing and comparing our approach with existing techniques. [ABSTRACT FROM AUTHOR]

Cooperative localization (CL) for air-to-ground robots in a satellite-denial environment has become a current research hotspot. The traditional distance-based heterogeneous multiple-robot CL method requires at least four unmanned aerial vehicles (UAVs) with known positions. When the number of known-position UAVs in a cluster collaborative network is insufficient, the traditional distance-based CL method has a certain inapplicability. A novel adaptive CL method for air-to-ground robots based on relative distance constraints is proposed in this paper. Based on a dynamically changing number of known-position UAVs in the cluster collaborative network, the adaptive fusion estimation threshold is set. When the number of known-position UAVs in the cluster cooperative network is large, the real-time dynamic topology characteristics of multiple robots' spatial geometric configurations are considered. The optimal spatial geometric configuration between UAVs and unmanned ground vehicles (UGVs) is utilized to achieve a high-precision CL solution for UGVs. Otherwise, in the event that the number of known-position UAVs in a cluster collaborative network is insufficient, distance observation constraint information between UAVs and UGVs is retained in real time. Position observation equations for UGVs' inertial navigation system (INS) have been constructed using inertial-based high-precision relative position constraints and relative distance constraints from historical to current times. The experimental results show that the proposed method achieves adaptive fusion estimation with a dynamically changing number of known-position UAVs in the cluster collaborative network, effectively verifying the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Simultaneous Localization and Mapping (SLAM) is one of the key technologies with which to address the autonomous navigation of mobile robots, utilizing environmental features to determine a robot's position and create a map of its surroundings. Currently, visual SLAM algorithms typically yield precise and dependable outcomes in static environments, and many algorithms opt to filter out the feature points in dynamic regions. However, when there is an increase in the number of dynamic objects within the camera's view, this approach might result in decreased accuracy or tracking failures. Therefore, this study proposes a solution called YPL-SLAM based on ORB-SLAM2. The solution adds a target recognition and region segmentation module to determine the dynamic region, potential dynamic region, and static region; determines the state of the potential dynamic region using the RANSAC method with polar geometric constraints; and removes the dynamic feature points. It then extracts the line features of the non-dynamic region and finally performs the point–line fusion optimization process using a weighted fusion strategy, considering the image dynamic score and the number of successful feature point–line matches, thus ensuring the system's robustness and accuracy. A large number of experiments have been conducted using the publicly available TUM dataset to compare YPL-SLAM with globally leading SLAM algorithms. The results demonstrate that the new algorithm surpasses ORB-SLAM2 in terms of accuracy (with a maximum improvement of 96.1%) while also exhibiting a significantly enhanced operating speed compared to Dyna-SLAM. [ABSTRACT FROM AUTHOR]

Advances in visual odometry (VO) systems have benefited from the widespread use of affordable RGB-D cameras, improving indoor localization and mapping accuracy. However, older sensors like the Kinect v1 face challenges due to depth inaccuracies and incomplete data. This study compares indoor VO systems that use RGB-D images, exploring methods to enhance depth information. We examine conventional image inpainting techniques and a deep learning approach, utilizing newer depth data from devices like the Kinect v2. Our research highlights the importance of refining data from lower-quality sensors, which is crucial for cost-effective VO applications. By integrating deep learning models with richer context from RGB images and more comprehensive depth references, we demonstrate improved trajectory estimation compared to standard methods. This work advances budget-friendly RGB-D VO systems for indoor mobile robots, emphasizing deep learning's role in leveraging connections between image appearance and depth data. [ABSTRACT FROM AUTHOR]

Autonomous navigation is the prerequisite and foundation for mobile robots to accomplish complex tasks. Traditional autonomous navigation systems rely on the accuracy of maps and cannot adapt to highly complex industrial and service scenarios. End-to-end navigation methods for mobile robots that do not rely on a priori map information and are able to make autonomous decisions through deep reinforcement learning, and environment interaction learning have become a new research hotspot. Most existing classifications cannot comprehensively summarize the challenges and opportunities of end-to-end navigation problems. Based on the characteristics of end-to-end navigation systems, the challenges of the navigation problem are attributed to the key issues of poor perception ability of navigation agents, ineffective learning and poor generalization ability of navigation strategies. The research status and development trends of end-to-end navigation systems are described. Representative research results in recent years addressing these key issues are detailed respectively, and their advantages and shortcomings are summarized. Finally, the future development trends of end-to-end navigation for mobile robots are prospectively envisioned in aspects such as visual language navigation, multi-agents collaborative navigation, end-to-end navigation for fusion super-resolution reconstructed images and interpretable end-to-end navigation, providing certain insights for the research and application of end-to-end navigation for mobile robots. [ABSTRACT FROM AUTHOR]

In this paper an improved multiple adaptive neuro-fuzzy inference system (MANFIS) to solve the wheeled mobile robots path planning in unstructured environments is proposed. The fuzzy C-means (FCM) clustering method is used in ANFIS to decrease the input data size, which leads to predict the efficiency of the proposed robot path planning model. The FCM clustering method allow classifying the robot sensors extracted input data into clusters; each cluster has similar properties that assists to develop the correlation between data and as a result simplify the proposed model. The design MANFIS architecture takes both the advantages of artificial neural network which has self-learning ability and fuzzy system to describe the uncertain phenomena of the data. Finally, by combining cluster data and MANFIS an optimum velocity for left and right wheel of the robot is determined, which safely navigate the robot in an optimized route. The simulation and experimental results show that the proposed path planning method is effective and can be implemented for any complex environments. The results obtained by the simulation and in physical experiments are equated with each other and noticed a good promise between both the results as the difference in results is less than 9%. The simulation results consistently demonstrate the superiority of the proposed FCM-ANFIS, manifesting performance improvements of up to 4.4% for path length reduction and up to 8.9% for mobile robot time duration reduction when compared to heuristic methods. This paper identifies and describes a new development on path planning technique that will help the robots to navigate in any kind of uncertain navigation environments. [ABSTRACT FROM AUTHOR]

This paper presents a low-cost system for simultaneous localization and mapping (SLAM) for unknown indoor environments. The system is based on a low-cost mobile-robot platform. The low-cost mobile robot is designed and fabricated in our control laboratory. The Rao-Blackwellized particle filter algorithm is used for SLAM computations, Xbox 360 Kinect module is utilized for stereo-camera imaging, and a Linux-based microcomputer (Raspberry Pi3) was used as the main onboard processing unit. An Arduino board is used to control the DC motors for mobile robot wheels. Raspberry Pi unit was wirelessly connected to a ground station machine that processes the information sent by the robot to build the environment map and estimate its pose. ROS (Robot Operating System) is used for map visualization, data-handling, and communication between different software nodes. The system has been tested virtually on a simulator and in real indoor environments and has successfully identified objects greater than 30 cm × 30 cm × 30 cm and added it to the map. It also shows promising capability to work autonomous missions independently without aid from any external sensors and with a fraction of the cost of similar systems based on Lidars. [ABSTRACT FROM AUTHOR]

Introduction: Many countries are facing a shortage of healthcare workers. Furthermore, healthcare workers are experiencing many stressors, resulting in psychological issues, impaired health, and increased intentions to leave the workplace. In recent years, different technologies have been implemented to lighten workload on healthcare workers, such as electronic patient files. Robotic solutions are still rather uncommon. To help with acceptance and actual use of robots their functionalities should correspond to the users' needs. Method: In the pilot study Care4All-Initial, we developed and field-tested applications for a mobile service robot in a psychosocial, multimodal group therapy for people with dementia. To guide the process and assess possible facilitators and barriers, we conducted a reoccurring focus group including people with dementia, therapists, professional caregivers as well as researchers from different disciplines with a user-centered design approach. The focus group suggested and reviewed applications and discussed ethical implications. We recorded the focus group discussions in writing and used content analysis. Results: The focus group discussed 15 different topics regarding ethical concerns that we used as a framework for the research project: Ethical facilitators were respect for the autonomy of the people with dementia and their proxies regarding participating and data sharing. Furthermore, the robot had to be useful for the therapists and attendees. Ethical barriers were the deception and possible harm of the people with dementia or therapists. The focus group suggested 32 different applications. We implemented 13 applications that centered on the robot interacting with the people with dementia and lightening the workload off the therapists. The implemented applications were facilitated through utilizing existing hard- and software and building on applications. Barriers to implementation were due to hardware, software, or applications not fitting the scope of the project. Discussion: To prevent barriers of robot employment in a group therapy for people with dementia, the robot's applications have to be developed sufficiently for a flawless and safe use, the use of the robot should not cause irritation or agitation, but rather be meaningful and useful to its users. To facilitate the development sufficient time, money, expertise and planning is essential. [ABSTRACT FROM AUTHOR]

Three-dimensional (3D) perception is vital to drive mobile robotics' progress toward intelligence. However, state-of-the-art 3D perception solutions require complicated postprocessing or point-by-point scanning, suffering computational burden, latency of tens of milliseconds, and additional power consumption. Here, we propose a parallel all-optical computational chipset 3D perception architecture (Aop3D) with nanowatt power and light speed. The 3D perception is executed during the light propagation over the passive chipset, and the captured light intensity distribution provides a direct reflection of the depth map, eliminating the need for extensive postprocessing. The prototype system of Aop3D is tested in various scenarios and deployed to a mobile robot, demonstrating unprecedented performance in distance detection and obstacle avoidance. Moreover, Aop3D works at a frame rate of 600 hertz and a power consumption of 33.3 nanowatts per meta-pixel experimentally. Our work is promising toward next-generation direct 3D perception techniques with light speed and high energy efficiency. [ABSTRACT FROM AUTHOR]

HEX Pixhawk 2.1 CUBE ORANGE+ in combination with Mission Planner software package is used for effective motion control of unmanned aerial and swimming vehicles. The article aims to develop efficient methods of flight trajectory generation for USVs to improve the accuracy and safety of autonomous missions. This research aims to develop and validate methods of trajectory construction for unmanned vehicles and analyze the motion of mobile robots taking into account the impact of currents. Different flight parameters such as altitude, velocity, and heading are considered, as well as methods for controlling the USVs according to the given targets. Special attention is given to safety and the configuration of sensors and devices required for autonomous flight. The author's results include the development of trajectory planning algorithms, evaluation of the effect of currents on the robot's motion, and development of software to acquire and process seafloor data. Graphs and computational results demonstrating the effect of current velocity on robot trajectory are presented for visualization and analysis. Software development methods for acquiring and processing seabed depth data using HEX Pixhawk 2.1 CUBE ORANGE+ hardware and an echolocation device are also described. The obtained results have both theoretical and practical significance. In the theoretical aspect, the proposed methods allow us to control USVs more efficiently and analyze their behavior in different conditions. In practical terms, it opens new perspectives for seabed exploration and autonomous missions with high accuracy and safety. [ABSTRACT FROM AUTHOR]

Objective: This study aimed to develop a control architecture for reactive autonomous navigation of a mobile robot by integrating Deep Learning techniques and fuzzy behaviors based on traffic signal recognition. Materials: The research utilized transfer learning with the Inception V3 network as a base for training a neural network to identify traffic signals. The experiments were conducted using a Donkey-Car, an Ackermann-steering-type opensource mobile robot, with inherent computational limitations. Results: The implementation of the transfer learning technique yielded a satisfactory result, achieving a high accuracy of 96.2% in identifying traffic signals. However, challenges were encountered due to delays in frames per second (FPS) during testing tracks, attributed to the Raspberry Pi's limited computational capacity. Conclusions: By combining Deep Learning and fuzzy behaviors, the study demonstrated the effectiveness of the control architecture in enhancing the robot's autonomous navigation capabilities. The integration of pre-trained models and fuzzy logic provided adaptability and responsiveness to dynamic traffic scenarios. Future research could focus on optimizing system parameters and exploring applications in more complex environments to further advance autonomous robotics and artificial intelligence technologies. [ABSTRACT FROM AUTHOR]

The trajectory tracking accuracy of high-clearance mobile robots could be affected by phenomena such as wheel slippage caused by changes in the working surface material and motion state. To reveal the impact of slippage factor and improve the tracking precision of wheeled mobile robots, this study proposed a sliding mode of trajectory tracking control with soft switching. Considering the slippage working environment of mobile robots, a three-degrees-of-freedom kinematic model of mobile robots containing slip rate was established. Based on the kinematic model of the system, a trajectory tracking controller utilizing soft switching sliding mode control was developed, followed by a comprehensive stability analysis. The MATLAB platform was utilized to verify the circular trajectory tracking performance of the mobile robot under both slipping and nonslipping conditions. Results demonstrate that: (1) Under ideal conditions (disregarding wheel slippage), the sliding mode tracker based on model design quickly achieves high-precision tracking of the robot's trajectory, with the tracking error controlled at 0.002 m within 0.6 s in a circular trajectory, capable of adjusting and tracking the desired circular trajectory in a short time and maintaining consistent posture. (2) When considering the effect of slippage, the uncompensated sliding mode control produces a larger periodic tracking error (the amplitude of the circular trajectory reaches 0.065 m) and a larger direction angle error at the trough of the lateral position, causing a sudden change in the direction angle. Nevertheless, the proposed sliding compensation in this study can improve its accuracy by about twice, with the tracking error controlled around 0.03 m in circular trajectories, effectively improving the system's tracking accuracy. This study expands the working environment of mobile robots and provides a basis for their high-performance operation in complex environments. [ABSTRACT FROM AUTHOR]

The modeling structures of rollers, mecanum wheels, and mecanum wheeled mobile robots presented in the literature use single contact force assumption. This assumption may give good results in a simulation environment; however, it is not strong enough to reflect reality. To make an improvement, a new aspect of mecanum wheel model is proposed in this study. The model takes the variable roller contact forces into account and investigates their effects on the performance of motion of a mecanum wheeled mobile robot. It uses all points on each roller's curved shape so that the slippage phenomena is also taken into consideration which makes it possible to get less position estimation errors in real-time operations. The modeling structure introduced aims to reflect reality both in simulation and real applications. A simulation environment is developed for this study. To make verification, an experimental setup including a four-mecanum-wheeled mobile robot, its mechanical and electrical hardware and software infrastructures, and a ground-truth system is designed and constructed. A Robot Operating System (ROS) based control system is created and integrated into the experimental system. Different types of reference trajectories including straight-line, square-shaped, Z-shaped, and wave(S)-shaped are used to test the performance of the model proposed in both simulation and experimental studies. The tests are also conducted using the model that involves single contact force assumption to make comparisons. The details of the variable contact forces model proposed, simulation environment developed, experimental setup built, simulation and experimental studies, their results, and comparisons are given in this paper. [ABSTRACT FROM AUTHOR]

We present a lazy incremental search algorithm, Lifelong-GLS (L-GLS), along with its bounded suboptimal version, Bounded L-GLS (B-LGLS) that combine the search efficiency of incremental search algorithms with the evaluation efficiency of lazy search algorithms for fast replanning in problem domains where edge evaluations are more expensive than vertex expansions. The proposed algorithms generalize Lifelong Planning A* (LPA*) and its bounded suboptimal version, Truncated LPA* (TLPA*), within the Generalized Lazy Search (GLS) framework, so as to restrict expensive edge evaluations only to the current shortest subpath when the cost-to-come inconsistencies are propagated during repair. We also present dynamic versions of the L-GLS and B-LGLS algorithms, called Generalized D* (GD*) and Bounded Generalized D* (B-GD*), respectively, for efficient replanning with non-stationary queries, designed specifically for navigation of mobile robots. We prove that the proposed algorithms are complete and correct in finding a solution that is guaranteed not to exceed the optimal solution cost by a user-chosen factor. Our numerical and experimental results support the claim that the proposed integration of the incremental and lazy search frameworks can help find solutions faster compared to the regular incremental or regular lazy search algorithms when the underlying graph representation changes often. [ABSTRACT FROM AUTHOR]

The growing significance of mobile robots in a full spectrum of areas of life creates new challenges and opportunities in robotics. One critical aspect to consider is energy utilization, as accurate prediction plays a vital role in a robot's reliability and safety. Furthermore, precise prediction offers economic advantages, particularly for robotic fleets, where energy management systems can optimize maintenance costs and operational efficiency. The following review describes the state of the art of energy usage prediction for different types of mobile robots, highlights current trends, and analyses algorithms' complexity (in implementation and execution), accuracy, and universality. [ABSTRACT FROM AUTHOR]

Snake robots, also known as apodal robots, are among the most common and versatile modular robots. Primarily due to their ability to move in different patterns, they can evolve in scenarios with several constraints, some of them hardly accessible to other robot configurations. This paper deals with a specific environment constraint where the robot needs to climb a prismatic obstacle, similar to a step. The objective is to carry out simulations of this function, before implementing it in the physical model. To this end, we propose two different algorithms, parameterized by the obstacle dimensions determined by image processing, and both are evaluated in simulated experiments. The results show that both algorithms are viable for testing in real robots, although more complex scenarios still need to be further studied. [ABSTRACT FROM AUTHOR]

Mobile robots play an important role in the industrial Internet of Things (IIoT); they need effective mutual communication between the cloud and themselves when they move in a factory. By using the sensor nodes existing in the IIoT environment as relays, mobile robots and the cloud can communicate through multiple hops. However, the mobility and delay sensitivity of mobile robots bring new challenges. In this paper, we propose a dynamic cooperative transmission algorithm with mutual information accumulation to cope with these two challenges. By using rateless coding, nodes can reduce the delay caused by retransmission under poor channel conditions. With the help of mutual information accumulation, nodes can accumulate information faster and reduce delay. We propose a two-step dynamic algorithm, which can obtain the current routing path with low time complexity. The simulation results show that our algorithm is better than the existing heuristic algorithm in terms of delay. [ABSTRACT FROM AUTHOR]

This paper proposes a solution to the problem of mobile robot navigation and trajectory interpolation in dynamic environments with large scenes. The solution combines a semantic laser SLAM system that utilizes deep learning and a trajectory interpolation algorithm. The paper first introduces some open-source laser SLAM algorithms and then elaborates in detail on the general framework of the SLAM system used in this paper. Second, the concept of voxels is introduced into the occupation probability map to enhance the ability of local voxel maps to represent dynamic objects. Then, in this paper, we propose a PointNet++ point cloud semantic segmentation network combined with deep learning algorithms to extract deep features of dynamic point clouds in large scenes and output semantic information of points on static objects. A descriptor of the global environment is generated based on its semantic information. Closed-loop completion of global map optimization is performed to reduce cumulative error. Finally, T-trajectory interpolation is utilized to ensure the motion performance of the robot and improve the smooth stability of the robot trajectory. The experimental results indicate that the combination of the semantic laser SLAM system with deep learning and the trajectory interpolation algorithm proposed in this paper yields better graph-building and loop-closure effects in large scenes at SIASUN large scene campus. The use of T-trajectory interpolation ensures vibration-free and stable transitions between target points. [ABSTRACT FROM AUTHOR]

Visual Place Recognition (VPR) aims to determine whether a robot or visual navigation system locates in a previously visited place using visual information. It is an essential technology and challenging problem in computer vision and robotic communities. Recently, numerous works have demonstrated that the performance of Convolutional Neural Network (CNN)-based VPR is superior to that of traditional methods. However, with a huge number of parameters, large memory storage is necessary for these CNN models. It is a great challenge for mobile robot platforms equipped with limited resources. Fortunately, Binary Neural Networks (BNNs) can reduce memory consumption by converting weights and activation values from 32-bit into 1-bit. But current BNNs always suffer from gradients vanishing and a marked drop in accuracy. Therefore, this work proposed a BinVPR model to handle this issue. The solution is twofold. Firstly, a feature restoration strategy was explored to add features into the latter convolutional layers to further solve the gradient-vanishing problem during the training process. Moreover, we identified two principles to address gradient vanishing: restoring basic features and restoring basic features from higher to lower layers. Secondly, considering the marked drop in accuracy results from gradient mismatch during backpropagation, this work optimized the combination of binarized activation and binarized weight functions in the Larq framework, and the best combination was obtained. The performance of BinVPR was validated on public datasets. The experimental results show that it outperforms state-of-the-art BNN-based approaches and full-precision networks of AlexNet and ResNet in terms of both recognition accuracy and model size. It is worth mentioning that BinVPR achieves the same accuracy with only 1% and 4.6% model sizes of AlexNet and ResNet. [ABSTRACT FROM AUTHOR]

It is worthwhile to calculate the execution cost of a manipulator for selecting a planning algorithm to generate trajectories, especially for an agricultural robot. Although there are various off-the-shelf trajectory planning methods, such as pursuing the shortest stroke or the smallest time cost, they often do not consider factors synthetically. This paper uses the state-of-the-art Python version of the Robotics Toolbox for manipulator trajectory planning instead of the traditional D–H method. We propose a cost function with mass, iteration, and residual to assess the effort of a manipulator. We realized three inverse kinematics methods (NR, GN, and LM with variants) and verified our cost function's feasibility and effectiveness. Furthermore, we compared it with state-of-the-art methods such as Double A* and MoveIt. Results show that our method is valid and stable. Moreover, we applied LM (Chan λ = 0.1) in mobile operation on our agricultural robot platform. [ABSTRACT FROM AUTHOR]

Robot-assisted rehabilitation is a rapidly advancing field whereby robotic devices are used for the treatment of disabilities. Mechanism design and actuation of these devices play important roles in the treatment and the non-ergonomic designs may even increase the cardiorespiratory load and cause discomfort leading to further gait disorders. This article identifies crucial design and actuation aspects of gait rehabilitation robots and presents the first intrinsically compliant gait robot design with three actuated and five passive degrees of freedom, alleviating the prevalent issues. The gait robot joints remain aligned with the human anatomical joints during the swing and the stance phases due to the use of special bushes and dampers. The intrinsically compliant actuators on the new gait robot make it safe to work with human subjects. Increased degrees of freedom allow for natural walking dynamics instead of canceling or constraining them. The robot firmware, including the kinematic modeling, is designed using multiple adaptive neuro-fuzzy inference system to save on the computational time of the robot controller. The new robot design is finally validated for its intended use in gait rehabilitation, by employing a fuzzy logic controller and evaluating the position, velocity, and acceleration profiles of its joints. [ABSTRACT FROM AUTHOR]

This research work envisages addressing fuzzy adjustment of parameters into a hybrid optimization algorithm for solving mathematical benchmark function problems. The problem of benchmark mathematical functions consists of finding the minimal values. In this study, we considered function optimization. We are presenting an enhanced Fuzzy Hybrid Algorithm, which is called Enhanced Fuzzy Hybrid Fireworks and Grey Wolf Metaheuristic Algorithm, and denoted as EF-FWA-GWO. The fuzzy adjustment of parameters is achieved using Fuzzy Inference Systems. For this work, we implemented two variants of the Fuzzy Systems. The first variant utilizes Triangular membership functions, and the second variant employs Gaussian membership functions. Both variants are of a Mamdani Fuzzy Inference Type. The proposed method was applied to 22 mathematical benchmark functions, divided into two parts: the first part consists of 13 functions that can be classified as unimodal and multimodal, and the second part consists of the 9 fixed-dimension multimodal benchmark functions. The proposed method presents better performance with 60 and 90 dimensions, averaging 51% and 58% improvement in the benchmark functions, respectively. And then, a statistical comparison between the conventional hybrid algorithm and the Fuzzy Enhanced Hybrid Algorithm is presented to complement the conclusions of this research. Finally, we also applied the Fuzzy Hybrid Algorithm in a control problem to test its performance in designing a Fuzzy controller for a mobile robot. [ABSTRACT FROM AUTHOR]

Thanks to compact structural integration and high locomotion performance, introducing vibration and asymmetric interaction with the ground is known as an important driving strategy in medium-sized (roughly cm ~ dm scale) mobile robots. For vibrations of different relative intensities, the vibro-bot may be in a continuous sliding state during movement (sliding locomotion), or may be in intermittent jumping and sliding states (hopping locomotion). Herein we conduct a mechanical analysis to reveal the locomotion mechanism of the vibro-bot. Specifically, the nonlinear governing equation of the vibro-bot is derived first. By approximately solving the governing equation, the trigger conditions of the sliding and locomotion modes are predicted, the detailed motion process is outlined, and the optimal design strategies to improve sports performance are clarified. This work not only promotes the design of mobile motion robots, but also has enlightening implications for understanding the locomotion behavior of animals with similar motion characteristics. [ABSTRACT FROM AUTHOR]

Objectives Localization is an important module of the light detection and ranging (LiDAR) simultaneous localization and mapping (SLAM) system, which provides basic information for perception, control, and planning, further assisting robots to accomplish higher-level tasks. However, LiDAR localization methods still face some problems: The localization accuracy and efficiency cannot meet the requirements of the robot products. In some textureless or large open environments, the lack of features easily leads to dangerous robot kidnappings. Consequently, aiming at the localization problems of mobile robots in large indoor environments, a global localization method based on cylindrical features is proposed.Methods First, an offline parameterized map is designed, which consists of some map cylinders and a raster map. Because the point cloud map contains a large number of 3D points and complete cylinders, random sample consensus (RANSAC) and geometric models are combined to directly segment the cylindrical points. The raster map is employed to describe the distributions of stable artificial structures. Then, some lightweight binary files are used to offline record the geometric model of cylinders and the feature distribution of the map. Next, based on three unique geometric characteristics of the cylinder (outlier, symmetry, and saliency), a real-time LiDAR point cloud cylinder segmentation method is proposed. Finally, two pose computation strategies are designed. The first is an optimization model based on heuristic search, which searches for the best matching cylinder between the map and real-time point cloud, and calculates the translation and rotation, respectively. The second is an optimization model based on multi-cylinder constraints, which employs both the topological relation (point-to-point and point-to-line constraints) and geometry attributes to find approximately congruent cylinders, then computes optimal pose.Results To verify the feasibility of the proposed method, we use a 16-line LiDAR to collect the experimental data in three real-world indoor environments, i.e., lobby, corridor, and hybrid scenarios. The global localization experiment is compared to a similar wall-based localization method, and the loop closure detection is compared to M2DP, ESF, Scan Context, and the wall-based localization. The experimental results show that the proposed method outperforms the baseline methods. The place recognition and localization performance of the proposed method reach the mainstream method level, with a localization success rate of 90% and an error of 0.073 m. Some data can reach millimeter localization accuracy, and the fastest speed is within 100 ms.Conclusions The proposed method can effectively realize the global localization and place recognition of the robots in typical open indoor environments. It meets the accuracy and efficiency requirements of autonomous driving for global localization in practical applications. It can be applied to solve the problems of position initialization, re-localization, and loop closure detection. [ABSTRACT FROM AUTHOR]

Objective In order to improve the adaptability of mobile robots to complex map environments, we propose a global path planning method called laser model, which improves the A* algorithm and ray model.Methods This method draws inspiration from the real-time scanning principle of planar light detection and ranging, which emits multiple virtual laser rays from the path node to the target point to perceive the boundary of obstacles, thereby quickly crossing obstacles and reaching the target point. At the same time, combined with the Floyd optimization algorithm, a safe, reliable, and stable global path is obtained in a relatively short time.Results In the concave environment of the experiment, the search time of the laser model is 99% faster than that of the A* algorithm and ray model, and the search process is reduced by 96%. In the experimental infeasible region, the laser model is 99% faster than the A* algorithm and ray model, and the search process is reduced by 97%. Compared with the double ant colony crossover algorithm, the laser model also performs better in concave environments.Conclusions The experimental results show that the proposed method is effective in solving the time consumption problems of concave traps and infeasible areas. [ABSTRACT FROM AUTHOR]

In order to reduce the energy consumption of the welding robot and ensure the cooperative movement of the robot joints, a trajectory planning method with optimal energy consumption based on improved sparrow search algorithm is proposed. Firstly, the trajectory planning model with optimal energy consumption is established based on the joint torque and angular velocity of the robot. To make the velocity, acceleration and jerk of each joint of the robot be bounded and continuous, the joint space trajectory is constructed with seventh degree B-spline curve. The total energy consumption of the robot is calculated by combining kinematic and dynamic parameters. On the basis of improved sparrow search algorithm, the time series corresponding to the optimal energy consumption is solved by using elite reverse learning, non-dominated sorting and Gaussian-Cauchy variation strategy, and then the optimal continuous motion trajectory of energy consumption is planned. The simulation results show that the proposed method can not only achieve continuous smooth control objective, but also effectively reduce energy consumption. [ABSTRACT FROM AUTHOR]

The Global Positioning System (GPS) is the most widely used positioning system for outdoor localization and navigation. However, GPS signals are not always available, especially in indoor or urban canyon environments. As such, alternative positioning systems capable of operating in GPSdenied environments are essential. This paper proposes a novel visual positioning system that combines Red-Green-Blue Depth (RGBD) map construction, semantic graph-based image matching, and dynamic localization and tracking. Our system utilizes a multi-modal sensor consisting of LiDAR and camera to acquire data and build a map library of RGBD images with sparse depth information. To initialize localization, we construct semantic graphs from observed and map images and construct image descriptors for matching to obtain approximate positions. To achieve continuous localization, we combine visual odometry with the ASpanFormer image matching method, and correct pose estimates based on the map library to reduce cumulative errors. We also dynamically update the map library in response to environmental changes. The results show that our system achieves superior accuracy and robustness in challenging scenarios, such as lighting variations, dynamic objects, and similar scene distributions. [ABSTRACT FROM AUTHOR]