Task For Mobile Robots Research Articles

Inspection Robot Navigation Based on Improved TD3 Algorithm.

The swift advancements in robotics have rendered navigation an essential task for mobile robots. While map-based navigation methods depend on global environmental maps for decision-making, their efficacy in unfamiliar or dynamic settings falls short. Current deep reinforcement learning navigation strategies can navigate successfully without pre-existing map data, yet they grapple with issues like inefficient training, slow convergence, and infrequent rewards. To tackle these challenges, this study introduces an improved two-delay depth deterministic policy gradient algorithm (LP-TD3) for local planning navigation. Initially, the integration of the long-short-term memory (LSTM) module with the Prioritized Experience Re-play (PER) mechanism into the existing TD3 framework was performed to optimize training and improve the efficiency of experience data utilization. Furthermore, the incorporation of an Intrinsic Curiosity Module (ICM) merges intrinsic with extrinsic rewards to tackle sparse reward problems and enhance exploratory behavior. Experimental evaluations using ROS and Gazebo simulators demonstrate that the proposed method outperforms the original on various performance metrics.

A finite-time path-tracking control algorithm for nonholonomic mobile robots with unknown dynamics and subject to wheel slippage/skid disturbances

Path planning and tracking control are two performance-critical tasks for wheeled mobile robots, particularly when nonholonomic constraints are imposed on robots in dynamically uncertain conditions. Accomplishing certain performance and safety considerations related to path-tracking, such as global stability, transient performance, and smooth finite-time convergence, becomes more difficult for nonholonomic robots. This paper is concerned with proposing a new adaptive robust finite-time tracking control approach for a large class of differential drive autonomous nonholonomic wheeled mobile robots (NWMRs) that are subject to structured uncertainties and extraneous disturbances with fully unknown dynamics. For this purpose, nonlinear kinodynamics of a type of rear-wheel drive NWMRs are developed by incorporating the skid/slippage constituents of the wheel motion. Then, a path-tracking controller is proposed using a continuous finite-time adaptive integral sliding mode control coupled with an integral backstepping approach (FTAISM-IBC). For the adaptive controller design, the entire nonlinear dynamics of the robot, including nonlinear vector functions and control gain functions, together with extraneous disturbances, are estimated by leveraging the universal approximation capabilities of radial basis neural networks (RBFNNs). The finite-time stability proof is presented by utilizing the Lyapunov stability theorem. Furthermore, the adaptive gains are derived to ensure the finite-time stability of the system subject to unknown functions, parametric variations, and unknown but bounded disturbances. Finally, the effectiveness of the proposed controller is evaluated through simulations in terms of several key performance indicators against several reported studies.

A Survey of Machine Learning Approaches for Mobile Robot Control

Machine learning (ML) is a branch of artificial intelligence that has been developing at a dynamic pace in recent years. ML is also linked with Big Data, which are huge datasets that need special tools and approaches to process them. ML algorithms make use of data to learn how to perform specific tasks or make appropriate decisions. This paper presents a comprehensive survey of recent ML approaches that have been applied to the task of mobile robot control, and they are divided into the following: supervised learning, unsupervised learning, and reinforcement learning. The distinction of ML methods applied to wheeled mobile robots and to walking robots is also presented in the paper. The strengths and weaknesses of the compared methods are formulated, and future prospects are proposed. The results of the carried out literature review enable one to state the ML methods that have been applied to different tasks, such as the following: position estimation, environment mapping, SLAM, terrain classification, obstacle avoidance, path following, learning to walk, and multirobot coordination. The survey allowed us to associate the most commonly used ML algorithms with mobile robotic tasks. There still exist many open questions and challenges such as the following: complex ML algorithms and limited computational resources on board a mobile robot; decision making and motion control in real time; the adaptability of the algorithms to changing environments; the acquisition of large volumes of valuable data; and the assurance of safety and reliability of a robot’s operation. The development of ML algorithms for nature-inspired walking robots also seems to be a challenging research issue as there exists a very limited amount of such solutions in the recent literature.

Out-of-distribution- and location-aware PointNets for real-time 3D road user detection without a GPU

Abstract3D road user detection is an essential task for autonomous vehicles and mobile robots, and it plays a key role, for instance, in obstacle avoidance and route planning tasks. Existing solutions for detection require expensive GPU units to run in real-time. This paper presents a light algorithm that runs in real-time without a GPU. The algorithm combines a classical point cloud proposal generator approach with a modern deep learning technique to achieve a small computational requirement and comparable accuracy to the state-of-the-art. Typical downsides of this approach, such as many out-of-distribution proposals and loss of location information, are examined, and solutions are proposed. We have evaluated the performance of the method with the KITTI dataset and with our own annotated dataset collected with a compact mobile robot platform equipped with a low-resolution LiDAR (16-channel). Our approach reaches a real-time inference on a standard CPU, unlike other solutions in the literature. Furthermore, we achieve superior speed on a GPU, which indicates that our method has a high degree of parallelism. Our method enables low-cost mobile robots to detect road users in real-time.

Exploring the Use of Particle and Kalman Filters for Obstacle Detection in Mobile Robots

The present study aims to explore the adaptation of estimation methodologies, specifically Particle filters and Kalman filters, for the purpose of determining the position and velocity vector of obstacles within the operational workspace of mobile robots. These algorithms are commonly employed in the motion planning tasks of mobile robots for the estimation of their own position. The proposed methodology utilizes LiDAR sensor data to estimate the position vectors and calculate the velocity vectors of obstacles. Additionally, an uncertainty parameter can be determined using the introduced perception method. The performance of the newly adapted algorithms is evaluated through comparison of the absolute error in position and velocity vector estimations.

Vision- and Lidar-Based Autonomous Docking and Recharging of a Mobile Robot for Machine Tending in Autonomous Manufacturing Environments

Autonomous docking and recharging are among the critical tasks for autonomous mobile robots that work continuously in manufacturing environments. This requires robots to demonstrate the following abilities: (i) detecting the charging station, typically in an unstructured environment and (ii) autonomously docking to the charging station. However, the existing research, such as that on infrared range (IR) sensor-based, vision-based, and laser-based methods, identifies many difficulties and challenges, including lighting conditions, severe weather, and the need for time-consuming computation. With the development of deep learning techniques, real-time object detection methods have been widely applied in the manufacturing field for the recognition and localization of target objects. Nevertheless, those methods require a large amount of proper and high-quality data to achieve a good performance. In this study, a Hikvision camera was used to collect data from a charging station in a manufacturing environment; then, a dataset for the wireless charger was built. In addition, the authors of this paper propose an autonomous docking and recharging method based on the deep learning model and the Lidar sensor for a mobile robot operating in a manufacturing environment. In the proposed method, a YOLOv7-based object detection method was developed, trained, and evaluated to enable the robot to quickly and accurately recognize the charging station. Mobile robots can achieve autonomous docking to the charging station using the proposed Lidar-based approach. Compared to other methods, the proposed method has the potential to improve recognition accuracy and efficiency and reduce the computation costs for the mobile robot system in various manufacturing environments. The developed method was tested in real-world scenarios and achieved an average accuracy of 95% in recognizing the target charging station. This vision-based charger detection method, if fused with the proposed Lidar-based docking method, can improve the overall accuracy of the docking alignment process.

Path Planning in Dynamic Environments Based on Q-Learning

With the rapid progress of science and technology, the scope of applications for mobile robots is growing. Path planning in dynamic environment is always a challenging task for mobile robot, which shows significant impacts in the medical field and the military field. Q-learning, a model-free reinforcement learning algorithm, can recognize its surroundings and demonstrate a system making decisions for itself about how this algorithm learns to make accurate decisions about achieving optimal target. Therefore, a path planning algorithm was proposed for robots in dynamic environments based on Q-learning. This algorithm can successfully generate several viable paths in environments with both static obstacles, dynamic obstacles and target point. First, three environments with different levels of complexity were created. Afterwards, to generate several optimal paths, the path planning algorithm was conducted in multiple times in different environments. Finally, the experimental results were collected and visualized to illustrate information. The effectiveness of the proposed algorithm is validated by experiment results in solving problems of path planning in dynamic environments with required point.

SHREC 2023: Point cloud change detection for city scenes

Localization and navigation are the two most important tasks for mobile robots, which require an up-to-date and accurate map. However, to detect map changes from crowdsourced data is a challenging task, especially from billions of points collected by 3D acquisition devices. Collecting 3D data often requires expensive data acquisition equipment and there are limited data sources to evaluate point cloud change detection. To address these issues, in this Shape Retrieval Challenge (SHREC) track, we provide a city-scene dataset with real and synthesized data to detect 3D point cloud change. The dataset consists of 866 pairs of object changes from 78 city-scene 3D point clouds collected by LiDAR and 845 pairs of object changes from 100 city-scene 3D point clouds generated by a high-fidelity simulator.We compare three methods on this benchmark. Evaluation results show that data-driven methods are the current trend in 3D point cloud change detection. Besides, the siamese network architecture is helpful to detect changes in our dataset. We hope this benchmark and comparative evaluation results will further enrich and boost the research of point cloud change detection and its applications.

Multiple Mobile Robot Task and Motion Planning: A Survey

With recent advances in mobile robotics, autonomous systems, and artificial intelligence, there is a growing expectation that robots are able to solve complex problems. Many of these problems require multiple robots working cooperatively in a multi-robot system. Complex tasks may also include the interconnection of task-level specifications with robot motion-level constraints. Many recent works in the literature use multiple mobile robots to solve these complex tasks by integrating task and motion planning. We survey recent contributions to the field of combined task and motion planning for multiple mobile robots by categorizing works based on their underlying problem representations, and we identify possible directions for future research. We propose a taxonomy for task and motion planning based on system capabilities, applicable to multi-robot and single-robot systems.

A Novel Deep Learning Approach to 5G CSI/Geomagnetism/VIO Fused Indoor Localization.

For positioning tasks of mobile robots in indoor environments, the emerging positioning technique based on visual inertial odometry (VIO) is heavily influenced by light and suffers from cumulative errors, which cannot meet the requirements of long-term navigation and positioning. In contrast, positioning techniques that rely on indoor signal sources such as 5G and geomagnetism can provide drift-free global positioning results, but their overall positioning accuracy is low. In order to obtain higher precision and more reliable positioning, this paper proposes a fused 5G/geomagnetism/VIO indoor localization method. Firstly, the error back propagation neural network (BPNN) model is used to fuse 5G and geomagnetic signals to obtain more reliable global positioning results; secondly, the conversion relationship from VIO local positioning results to the global coordinate system is established through the least squares principle; and finally, a fused 5G/geomagnetism/VIO localization system based on the error state extended Kalman filter (ES-EKF) is constructed. The experimental results show that the 5G/geomagnetism fusion localization method overcomes the problem of low accuracy of single sensor localization and can provide more accurate global localization results. Additionally, after fusing the local and global positioning results, the average positioning error of the mobile robot in the two scenarios is 0.61 m and 0.72 m. Compared with the VINS-mono algorithm, our approach improves the average positioning accuracy in indoor environments by 69.0% and 67.2%, respectively.

Spectrum Surveying: Active Radio Map Estimation With Autonomous UAVs

Radio maps find numerous applications in wireless communications and mobile robotics tasks, including resource allocation, interference coordination, and mission planning. Although numerous existing techniques construct radio maps from spatially distributed measurements, the locations of such measurements are predetermined beforehand. In contrast, this paper proposes spectrum surveying, where a mobile robot such as an unmanned aerial vehicle (UAV) collects measurements at a set of locations that are actively selected to obtain high-quality map estimates in a short surveying time. This is performed in two steps. First, two novel algorithms, a model-based online Bayesian estimator and a data-driven deep learning algorithm, are devised for updating a map estimate and an uncertainty metric that indicates the informativeness of measurements at each possible location. These algorithms offer complementary benefits and feature constant complexity per measurement. Second, the uncertainty metric is used to plan the trajectory of the UAV to gather measurements at the most informative locations. To overcome the combinatorial complexity of this problem, a dynamic programming approach is proposed to obtain lists of waypoints through areas of large uncertainty in linear time. Numerical experiments conducted on a realistic dataset confirm that the proposed scheme constructs accurate radio maps quickly.

Continuous shared control of a mobile robot with brain–computer interface and autonomous navigation for daily assistance

Although the electroencephalography (EEG) based brain–computer interface (BCI) has been successfully developed for rehabilitation and assistance, it is still challenging to achieve continuous control of a brain-actuated mobile robot system. In this study, we propose a continuous shared control strategy combining continuous BCI and autonomous navigation for a mobile robot system. The weight of shared control is designed to dynamically adjust the fusion of continuous BCI control and autonomous navigation. During this process, the system uses the visual-based simultaneous localization and mapping (SLAM) method to construct environmental maps. After obtaining the global optimal path, the system utilizes the brain-based shared control dynamic window approach (BSC-DWA) to evaluate safe and reachable trajectories while considering shared control velocity. Eight subjects participated in two-stage training, and six of these eight subjects participated in online shared control experiments. The training results demonstrated that naïve subjects could achieve continuous control performance with an average percent valid correct rate of approximately 97 % and an average total correct rate of over 80 %. The results of online shared control experiments showed that all of the subjects could complete navigation tasks in an unknown corridor with continuous shared control. Therefore, our experiments verified the feasibility and effectiveness of the proposed system combining continuous BCI, shared control, autonomous navigation, and visual SLAM. The proposed continuous shared control framework shows great promise in BCI-driven tasks, especially navigation tasks for brain-driven assistive mobile robots and wheelchairs in daily applications.

Learning Deep Neural Network Controller for Path Following of Unicycle Robots

This letter investigates the scope of deep neural network (DNN) based controller in the path following task for unicycle mobile robots. A DNN-based controller is trained to follow paths with arbitrary curvature in two-dimensional space. The training process does not require initialization or supervision from any other known expert controller. Rather, the training of the DNN controller is guided by another predictive neural network that represents a path following error dynamics which is exponentially stable at the origin. The two DNNs are trained jointly in a simulated environment. The learned DNN controller is then employed as a standalone controller in a real unicycle robot for the tasks of following various linear and curved paths.

A Novel Radar Point Cloud Generation Method for Robot Environment Perception

Millimeter-wave (mmWave) radar has been widely used in autonomous driving due to its good performance under harsh weather conditions. In recent years, with the development of mmWave radar hardware performance, radar point clouds, as an important data format of mmWave radar, have been widely used in high-level perception tasks of mobile robots and autonomous driving. However, at present, compared to LiDAR point clouds, in common application scenes of mobile robots, mmWave radar point clouds have shortcomings such as sparsity and containing many “ghost” targets. Therefore, in this article, we analyze the reasons that cause these problems and propose a new method for point cloud generation as well as a new evaluation metric. After building a new dataset and carrying out experiments in real-world scenes, our method shows better performance on the quality of radar point clouds compared to other methods. In addition, by evaluating the performance of applying the high-quality radar point clouds to object detection tasks as well as localization and mapping tasks, the result shows that radar point clouds generated using our method can significantly improve the environment perception ability of mobile robots.

Sampling visual SLAM with a wide‐angle camera for legged mobile robots

AbstractPrecise localisation and navigation are the two most important tasks for mobile robots. Visual simultaneous localisation and mapping (VSLAM) is useful in localisation systems of mobile robots. The wide‐angle camera has a broad field of vision and more abundant information on images, so it is widely used in mobile robots, including legged robots. However, wide‐angle cameras are more complicated than ordinary cameras in the design of visual localisation systems, and higher requirements and challenges are put forward for VSLAM technologies based on wide‐angle cameras. In order to resolve the problem of distortion in wide‐angle images and improve the accuracy of localisation, a sampling VSLAM based on a wide‐angle camera model for legged mobile robots is proposed. For the predictability of the periodic motion of a legged robot, in the method, the images are sampled periodically, image blocks with clear texture are selected and the image details are enhanced to extract the feature points on the image. Then, the feature points of the blocks are extracted and by using the feature points of the blocks in the images, the feature points on the images are extracted. Finally, the points on the incident light through the normalised plane are selected as the template points; the relationship between the template points and the images is established through the wide‐angle camera model, and the pixel coordinates of the template points in the images and the descriptors are calculated. Moreover, many experiments are conducted on the TUM datasets with a quadruped robot . The experimental results show that the trajectory error and translation error measured by the proposed method are reduced compared with the VINS‐MONO, ORB‐SLAM3 and Periodic SLAM systems.

A path planning approach for mobile robots using short and safe Q-learning

Path planning is a major challenging problem for mobile robots, as the robot is required to reach the target position from the starting position while simultaneously avoiding conflicts with obstacles. This paper refers to a novel method as short and safe Q-learning to alleviate the short and safe path planning task of mobile robots. To solve the slow convergence of Q-learning, the artificial potential field is utilized to avoid random exploration and provides a priori knowledge of the environment for mobile robots. Furthermore, to speed up the convergence of the Q-learning and reduce the computing time, a dynamic reward is proposed to facilitate the mobile robot towards the target point. The experiments are divided into two parts: short and safe path planning. The mobile robot can reach the target with the optimal path length in short path planning, and away from obstacles in safe path planning. Experiments compared with the state-of-the-art algorithm demonstrate the effectiveness and practicality of the proposed approach. Concluded, the path length, computing time and turning angle of SSQL is increased by 2.83%, 23.98% and 7.98% in short path planning, 3.64%, 23.42% and 12.61% in safe path planning compared with classical Q-learning. Furthermore, the SSQL outperforms other optimization algorithms with shorter path length and smaller turning angles.

Analytical Review of Approaches to the Distribution of Tasks for Mobile Robot teams Based on Soft Computing Technologies

The use of various types of heuristic algorithms based on soft computing technologies for the distribution of tasks in groups of mobile robots performing monosyllabic operations in a single workspace is considered: genetic algorithms, ant algorithms and artificial neural networks. It is shown that this problem is NP-complex and its solution by direct iteration for a large number of tasks is impossible. The initial problem is reduced to typical NP-complete problems: the generalized problem of finding the optimal group of closed routes from one depot and the traveling salesman problem. A description of each of the selected algorithms and a comparison of their characteristics are presented. A step-by-step algorithm of operation is given, taking into account the selected genetic operators and their parameters for a given population volume. The general structure of the developed algorithm is presented, which makes it possible to solve a multi-criteria optimization problem efficiently enough, taking into account time costs and the integral criterion of robot efficiency, taking into account energy costs, functional saturation of each agent of the group, etc. The possibility of solving the initial problem using an ant algorithm and a generalized search for the optimal group of closed routes is shown. For multi-criteria optimization, the possibility of linear convolution of the obtained vector optimality criterion is shown by introducing additional parameters characterizing group control: the overall efficiency of the functioning of all robots, the energy costs for the functioning of the support group and the energy for placing one robot on the work field. To solve the task distribution problem using the Hopfield neural network, its representation is made in the form of a graph obtained during the transition from the generalized task of finding the optimal group of closed routes from one depot to the traveling salesman problem. The quality indicator is the total path traveled by each of the robots in the group.

Evolutionary self-organizing fuzzy system using fuzzy-classification-based social learning particle swarm optimization

A self-organizing algorithm based on an online cluster and fuzzy sets update algorithm (OCFU) and fuzzy-classification-based social learning particle swarm optimization (FC-SLPSO) is proposed to address the problem of rule initialization and fitness function evaluation. The OCFU algorithm is used to determine the structure of the fuzzy system and build a flexible partition of fuzzy sets in each input variable. The FC-SLPSO algorithm establishes a fuzzy K-Nearest Neighbor (KNN) classifier in each iteration. The fitness evaluation is performed only when the membership degree of the offspring particles belonging to potential particles is greater than that of the parent particles, which effectively reduces the number of fitness function evaluations and accelerates the PSO algorithm. The tracking results of three nonlinear systems show that the tracking accuracy of the proposed method is better. The Pioneer P3DX mobile robot model and simulation environment with a two-dimensional lidar are constructed based on the Coppeliasim robot simulation platform. Using the algorithms proposed in this paper, the tracking task of the pioneer p3dx mobile robot along a wall is achieved. The effectiveness of the proposed algorithm is verified by the cosimulation of Coppeliasim and MATLAB in multiple scenarios.

ESD-SLAM: An efficient semantic visual SLAM towards dynamic environments

Traditional visual SLAM algorithms run robustly under the assumption of a static environment, but always fail in dynamic scenes, since moving objects will impair camera pose tracking. Given this, this paper presents an efficient semantic dynamic SLAM (ESD-SLAM), which is suitable for dynamic scenarios. Based on the ORB-SLAM2 framework, the ESD-SLAM we proposed employs lightweight semantic segmentation network FcHarDNet to extract semantic information, and uses the region growing algorithm to optimize the semantic segmentation boundary. Then dynamic objects are removed by combining semantic information with multi-view geometry, and it further improves the localization accuracy. Combining semantic information and depth information, a dense point cloud map of static scene is constructed to serve the planning task of mobile robot. We conduct the experiments on the public TUM RGB-D dataset and in the real-world environment. Experimental results show that the proposed algorithm can improve the performance of the ORB-SLAM2 system in dynamic scenes, and significantly improve the real-time performance compared with other same type dynamic SLAM algorithms.

Information-Aware Lyapunov-Based MPC in a Feedback-Feedforward Control Strategy for Autonomous Robots

This letter proposes a feedback-feedforward control scheme that combines the benefits of an online active sensing control strategy (the feedforward control component) to maximize the information needed for correctly executing the desired task, with a Lyapunov-based control strategy (the feedback control component) that guarantees an asymptotic convergence towards the task itself. To quantify the amount of the collected information along the planned trajectories, the smallest eigenvalue of the Constructability Gramian is adopted as a metric and optimized, for generating the feedforward control component, within a Lyapunov-based Model Predictive Control framework (LMPC). The latter indeed allows to systematically handle the closed-loop stability and robustness properties of a Lyapunov-based nonlinear control law, and, at the same time, to reduce the estimation uncertainty and, thus, increase the task execution performance. To show the effectiveness of our method, we consider three case studies where a unicycle equipped with suitable onboard sensors has to perform three classical tasks in mobile robotics: path following, point-to-point motion, and trajectory tracking.