Search

Target tracking is a key component of control systems with applications in various domains. Several examples of commercial applications may be given, which benefit from this technology: the development of car collision avoidance systems which must detect and track potential obstacles and hazards, or the development of UAVs that can track and record the evolution of athletes. For the purpose of our research, this technology was developed and tested as part of a less complex application. The current work describes a simple yet practical implementation of vision-based control for a mobile robot system. In the experiment, we used a mobile robot as target and a similar robot as follower. To achieve the tracking task, the used strategy involves the detection of a specific visual object mounted on the target, by extracting its features which are then used in issuing control commands within a remotely-closed loop. A Deep Learning approach is used for object detection, incorporating a detector model into the strategy while preserving an explicit controller in the overall scheme. The carried experiment has proven that this new approach provides the expected results, which make it a suitable tool for development of larger scale applications of control systems. [ABSTRACT FROM AUTHOR]

In this article, the fault-attack control problem is investigated for wheeled mobile robot (WMR) systems subjected to actuator faults, disturbances, communication attacks, and limited communication resources. An event-observer based compensation controller is presented. With the help of the observer estimation values and the attack sleep/active instant trigger information, the tracking control performance is realized for the robot system with the assistance of the neural network approximation technology. Concretely, first, the robot system dynamic model with actuator faults, disturbances, and attacks is established. Then, an event-based proportional–integral observer (PIO) is established. In the observer framework, a state estimator, an actuator fault efficiency estimator, and a disturbance estimator are embedded. Based on the observer outputs, a second-order adaptive sliding mode fault-compensation reliable controller is presented. In this controller framework, the fault compensation, disturbance attenuation, and the attack sleep/active time instant information are contained to guarantee the reliability and performance recoverability of the robot system. Furthermore, a dynamic even condition and an adaptive trigger scheme are constructed in the sensor and actuator channel to achieve the communication-efficient purpose. Finally, two cases of the robot system are performed to verify the system recoverability of the presented approach. • A class of wheeled mobile robot systems with actuator faults, disturbances, and communication attacks is established. • An event-based proportional–integral observer framework is designed for the robot system to estimate the states, actuator faults and lumped disturbances. • A novel observer-event-based adaptive fault-attack-tolerant control architecture is presented to simultaneously preserve and recover control performance for the robot system while saving the communication resources. [ABSTRACT FROM AUTHOR]

This paper presents several non-singleton general type-2 fuzzy logic controllers (NGT2FLCs) for an under-actuated mobile two-wheeled self-balancing robot to improve the anti-interference capability of the system. Four kinds of fuzzifiers, including singleton fuzzifier, type-1 non-singleton fuzzifier, interval type-2 non-singleton fuzzifier and general type-2 non-singleton fuzzifier, are considered to construct different general type-2 fuzzy logic controllers (GT2FLCs). In order to show the superiority of the GT2FLCs, three kinds of interval type-2 fuzzy logic controllers (IT2FLCs), including singleton IT2FLCs, type-1 non-singleton IT2FLCs (N1IT2FLCs) and interval type-2 non-singleton IT2FLCs (N2IT2FLCs), are also presented. A comparative study between singleton fuzzy controllers and non-singleton fuzzy controllers, and IT2FLCs and GT2FLCs is also shown. All simulation results show that the performance of non-singleton fuzzy logic controllers is better than that of singleton fuzzy logic controllers. The NGT2FLCs get the best performance in the presence of uncertainties and external disturbances. [ABSTRACT FROM AUTHOR]

The paper presents the implementation of the high-level decentralized control system for a group of mobile robots (MR), which provides a common information space in a group, and performs decomposition of the main task (task from operator) and generates subgroups on the basis of agents' functional purpose. [ABSTRACT FROM AUTHOR]

Abstract This paper presents a new path planning algorithm based on Probability and Fuzzy Logic (PFL) as a duality technique to enhance the performance of Fuzzy Logic alone. Fuzzy Logic interacts with the grading of obstacles existed in the path and probability lies over the decision to move the mobile robot. The fuzzy grading correspondence with the probabilistic decision is the primary function of moving the mobile robot towards the goal and the secondary is path planning which lies over the probability distribution function. The distance–speed combination rule is developed for effective navigation. The single and multiple mobile robot systems have been tested successfully in a dense environment in presence of obstacles (static and dynamic) and moving goal. The obtained results are optimal when compared to other navigational approaches in sense of navigational path length and time in the static and dynamic environment. Highlights • It studies the geometric constraints present in the environment and classifies the decision for generation of the obstacle-free path. • The probability is defined over fuzzy by selecting the path gradient with certainty. Optimized path decision, path transformation, and distributed decision are major advantages of the PFL controller over fuzzy Logic alone. • It is robust for navigation of single and multi-robot system in a complex-crowded environment in the presence of obstacles (static and dynamic) and moving goal situations. • It provides the capability of handling uncertain and imprecise information using distance–speed rules, performs real-time operation efficiently, gives easy combination and coordination of various behavior, ability to develop perception-action based strategies and easy implementation. • It gives better results when compared to other AI Controller in terms of path length and navigational time. [ABSTRACT FROM AUTHOR]

Abstract The development of a virtual scenario is desirable in many hostile environments such as in mining or sewer pipelines to inspect its current condition and to identify possible failures. Obtaining a virtual image through the reconstruction of the mineshaft or the inner pipe is a valuable tool for assessment and fault detection. The approach presented in this paper uses a fuzzy controlled robot so that the video information can reliably be taken. The robot fuzzy control guarantees its motion in a straight line while taking the images from the pipe. The control algorithm therefore prevents the robot from overturning while moving inside the pipe. Results from our 3D reconstruction approach using the autonomous mobile robot is presented. The proposed method overcomes the limitations of different detectors by using a novel combination of DoG and Harris Laplace. Once the frame selection is made, then the regions with affine transformations are used to find image features as correspondences using image descriptors such as SIFT (Scale-Invariant Feature Transform). The correspondences are required to obtain the orientation and position of the camera and to obtain the scene structure leading to the creation of the 3D virtual environment. The 3D reconstruction method outperformed similar commercial software which highlights its potential. Highlights • Novel 3D reconstruction approach using an autonomous sewer robot. • The novel algorithm is used to select appropriate correspondences. • Affine transformations are used to find features as dense local correspondences. • Image descriptors are used to obtain the orientation and position of the camera. • Image descriptors are used to obtain the scene structure for 3D reconstruction. [ABSTRACT FROM AUTHOR]

This article presents a hybrid control system for a group of mobile robots. The components of this system are the supervisory controller(s), employing a discrete, event-driven model of concurrent robot processes, and robot motion controllers, employing a continuous time model with event-switched modes. The missions of the robots are specified by a sequence of to-be visited points, and the developed methodology ensures in a formal way their correct accomplishment. [ABSTRACT FROM AUTHOR]

In this paper, a new approach is presented for getting a solution of the mobile robot path planning problem based on Adaptive Particle Swarm Optimization (APSO). The proposed APSO algorithm is smarter than conventional PSO and widely used for solving the real time problems. In this work an objective function is framed considering the distance between robot to goal and obstacle respectively. The objective function is optimized with of APSO for solving the path planning process of robot. The different simulated experiments are performed to test the ability of the proposed algorithm. The performance of the robot path planning using APSO is compared to the performance of the conventional PSO in terms path length and time in static environments. It is focused that using new approach the robot can successfully avoid obstacle and reach the target with shorter time than conventional PSO. [ABSTRACT FROM AUTHOR]

The physical system design is more complex day after day due to the advancement in technology. In this paper, bond graph modelling of a multi domain physical system like skid steered mobile is presented. The proposed method is used to describe the dynamics of the system in various physical domains. By applying the bond and junction properties, mathematical model is extracted. In the second part of the paper, an unified technique is proposed to control the robot along the predefined complex trajectory. To track the desired trajectory, a flatness-based controller is proposed for the mobile robot. The developed dynamic model and the controller is modelled using BG V20 toolbox in MATLAB. Open loop as well as closed loop simulation are carried out to check the efficacy of the proposed model. Experimental trials performed in simulation environment revealed that the developed dynamic model and the controller for the robot can efficiently track the desired trajectory. [ABSTRACT FROM AUTHOR]

This paper presents the design of fuzzy control system for an omnidirectional robot. The control structure of omnidirectional robot was described. The kinematics and dynamics of the mobile robot are presented. The design of control system is implemented for position and orientation angle in order to control the linear and angular speed of the omnidirectional robot. The designs of fuzzy controllers are performed and then these are used for the control of the holonomic 4-wheel-driven soccer robots. The designed fuzzy control algorithm has been extensively tested in simulation and provided satisfactory results in run time. The controller presented in this paper provides an optimal solution to minimize the differences between the reference trajectory and the current output. The obtained results demonstrate the effectiveness of proposed algorithms in robot soccer control. [ABSTRACT FROM AUTHOR]

In the view of the problem of designing and optimization of interval type-2 fuzzy logic controller (IT2 FLC) for Delta robot trajectory control, a systematic design method is put forward in this paper. A type-1 fuzzy logic controller (T1 FLC) is designed and optimized. Then, three kinds of method to blur the T1 fuzzy membership functions are proposed to generate IT2 fuzzy sets from the optimized T1 fuzzy sets. A systematic analysis is carried out to study the relationship between blur methods, blur degree and output control surface of IT2 FLC. Output signal enhance coefficient is proposed to make sure the IT2 FLC to provide enough output signal. The optimized IT2 FLC is validated through a set of simulations and by comparing against its type-1 counterpart in the presence of external and internal uncertainties. The simulation results show the optimized IT2 FLC can provide better trajectory tracking performance. [ABSTRACT FROM AUTHOR]

Industrial robots conceived for high-precision assembly processes are demanded to match the best trade-off between precision and speed. This research presents a new approach for defining the motion profiles of robots, based on a smooth trajectory generation model. Execution time is minimized by a novel multi-variable optimization approach, taking into account the performance of each joint and the requirements of extremely precise assembly tasks. The proposed method, tested on a modular robot for the optoelectronics industry, provides jerk-bounded trajectories up to 39% faster compared to the best performing motion planning approaches, while offering the possibility to adapt these trajectories for degraded operating conditions. [ABSTRACT FROM AUTHOR]

The paper explain analysis of inertial navigation system and accelerometric, gyroscopic sensors and describe possibilities of their application for inertial navigation of mobile robot. Such controlling system allows to monitor exact position of robot. These information can be applied for robot controlling, its autonomous control or its tracking. Inertial navigation is completely autonomous and independent from surroundings, i.e. the system is resistant from external influences as magnetic disturbances, electronically disturbance, signal deformation, etc. For mobile robots to be successful, they have to move safely in environments populated and dynamic. While recent research has led to a variety of localization methods that can track robots well in static environments, we still lack methods that can robustly localize mobile robots in dynamic environments. [ABSTRACT FROM AUTHOR]

The automatic design of controllers for mobile robots usually requires two stages. In the first stage, sensorial data are preprocessed or transformed into high level and meaningful values of variables which are usually defined from expert knowledge. In the second stage, a machine learning technique is applied to obtain a controller that maps these high level variables to the control commands that are actually sent to the robot. This paper describes an algorithm that is able to embed the preprocessing stage into the learning stage in order to get controllers directly starting from sensorial raw data with no expert knowledge involved. Due to the high dimensionality of the sensorial data, this approach uses Quantified Fuzzy Rules (QFRs), that are able to transform low-level input variables into high-level input variables, reducing the dimensionality through summarization. The proposed learning algorithm, called Iterative Quantified Fuzzy Rule Learning (IQFRL), is based on genetic programming. IQFRL is able to learn rules with different structures, and can manage linguistic variables with multiple granularities. The algorithm has been tested with the implementation of the wall-following behavior both in several realistic simulated environments with different complexity and on a Pioneer 3-AT robot in two real environments. Results have been compared with several well-known learning algorithms combined with different data preprocessing techniques, showing that IQFRL exhibits a better and statistically significant performance. Moreover, three real world applications for which IQFRL plays a central role are also presented: path and object tracking with static and moving obstacles avoidance. [ABSTRACT FROM AUTHOR]

This paper aims to investigate the formation control of multi-robot systems, where the kinematic model of a differentially driven wheeled mobile robot is considered. Based on the graph-theoretic concepts and locally distributed information, an adaptive neural fuzzy formation controller is designed with the capability of on-line learning. The learning rules of controller parameters can be derived from the analyzing of Lyapunov stability. In addition to simulations, the proposed techniques are applied to an experimental multi-robot platform for performance validations. From simulation and experimental results, the proposed adaptive neural fuzzy protocol can provide better formation responses compared to conventional consensus algorithms. [ABSTRACT FROM AUTHOR]

The utilization of only existing radiant sources in autonomous and mobile robotics is a relatively new field. These radiant sources, referred to as ambient radiation were "the noise and errors" in the production of various range finding and obstacle locating sensors. The research looks to developing methods to utilize this "noise" for autonomous robot mobility and addresses the inherent problems associated with dynamically changing environment analysis. A fuzzy logic topology is adapted in the processing of amplified data from an array of sensors in photovoltaic mode. The "fuzzified" data may be used for the purposes of obstacle avoidance or for higher level applications such as item location, fire detection and environmental mapping. [ABSTRACT FROM AUTHOR]