3-D Vision Techniques for Autonomous Vehicles

PurposeThe purpose of this paper is to put forward a rolling assistant robot with two rolling modes, and the multi-mode rolling motion strategy with path planning algorithm, which is suitable to this multi-mode mobile robot, is proposed based on chessboard-shaped grid division (CGD).Design/methodology/approachBased on the kinematic analysis and motion properties of the mobile parallel robot, the motion strategy based on CGD path planning algorithm of a mobile robot with two rolling modes moving to a target position is divided into two parts, which are local self-motion planning and global path planning. In the first part, the mobile parallel robot can move by switching and combining the two rolling modes; and in the second part, the specific algorithm of the global path planning is proposed according to the CGD of the moving ground.FindingsThe assistant robot, which is a novel 4-RSR mobile parallel robot (where R denotes a revolute joint and S denotes a spherical joint) integrating operation and rolling locomotion (Watt linkage rolling mode and 6R linkage rolling mode), can work as a moving spotlight or worktable. A series of simulation and prototype experiment results are presented to verify the CGD path planning strategy of the robot, and the performance of the path planning experiments in simulations and practices shows the validation of the path planning analysis.Originality/valueThe work presented in this paper is a further exploration to apply parallel mechanisms with two rolling modes to the field of assistant rolling robots by proposing the CGD path planning strategy. It is also a new attempt to use the specific path planning algorithm in the field of mobile robots for operating tasks.

This paper deals with a new approach based on Q-learning for solving the problem of mobile robot path planning in complex unknown static environments. As a computational approach to learning through interaction with the environment, reinforcement learning algorithms have been widely used for intelligent robot control, especially in the field of autonomous mobile robots. However, the learning process is slow and cumbersome. For practical applications, rapid rates of convergence are required. Aiming at the problem of slow convergence and long learning time for Q-learning based mobile robot path planning, a state-chain sequential feedback Q-learning algorithm is proposed for quickly searching for the optimal path of mobile robots in complex unknown static environments. The state chain is built during the searching process. After one action is chosen and the reward is received, the Q-values of the state-action pairs on the previously built state chain are sequentially updated with one-step Q-learning. With the increasing number of Q-values updated after one action, the number of actual steps for convergence decreases and thus, the learning time decreases, where a step is a state transition. Extensive simulations validate the efficiency of the newly proposed approach for mobile robot path planning in complex environments. The results show that the new approach has a high convergence speed and that the robot can find the collision-free optimal path in complex unknown static environments with much shorter time, compared with the one-step Q-learning algorithm and the Q(λ)-learning algorithm.

ABSTRACTOccupancy grid mapping in the field of mobile robotics is an integrative and promising solution for the various prerequisite such as path planning, autonomous navigation, localization, SLAM (Simultaneously Localization And Mapping) etc. The reliability of the occupancy grid mapping depends upon diverse parameters such as sensor accuracy, size of a grid cell, intrinsic and extrinsic parameters, sensor registration, sensor modelling, scanning angle, ambient conditions, etc. This research reveals the uncertainty in the generation of the laser occupancy grid map with the implementation of conventional laser geometry technique when the detected obstacle/target is on the perimeter of the grid cell. During autonomous navigation, the obstacle and the mobile robot are in a dynamic state that consequence in the wrong perception of the environment by identifying the wrong grid cell as occupied in the occupancy grid map when the obstacle is on the perimeter of the grid cell. The examined error is reduced by a newly designed Perimeter-based SLAM (P-SLAM) technique based on the vector algebra, laser geometry, Inverse Sensor Model and coordinate system. The obtained results with the implementation of P-SLAM are validated w.r.t conventional approaches with qualitative and quantitative analysis by performing real-world experiments.

Path planning based on deep reinforcement learning has been a hot topic in the field of mobile robots in recent years, but there are still many shortcomings in its application. Such as the lack of agents' generalization ability, the loss of targets in the process of exploration and the inefficiency of data exploration. In this paper, we propose an improved path planning algorithm to solve the above three problems. We take the Depth Deterministic Policy Gradient (DDPG) algorithm as the basic algorithm, and increase generalization ability of agents by adding adaptive gaussian noise, then, in order to solve the problem of losing target in exploration process, we redesign the reward functions based on the curiosity mechanism. We also add the memory units for agents to make the exploration process more efficient. Finally, we verify that the improved algorithm has good adaptability in different obstacle avoidance environments through simulation experiments.

Scene perception of mobile robot is that the robot realizes the perception and understanding of the surrounding environment through a series of sensors configured by itself, and the perception technology based on vision has always been a hot and difficult point in research. Therefore, in terms of visual environment perception algorithms, there have been numerous valuable research achievements in recent years. In particular, the object detection and segmentation algorithm based on convolutional neural network has shown good performance in simple scene, but there are still some limitations when these algorithms are directly applied to actual scenes. In this paper, we study the practical application of vision-based environmental perception of mobile robots in complex scenes, presents a unified algorithm architecture of object detection and road segmentation, and build a vision-based mobile robot's environment perception system. Firstly, the image acquisition of the surrounding environment is completed by the computer camera mounted on the robot, and then the obstacle detection and the segmentation of the drivable area are achieved by using the target detection and segmentation algorithm. In order to meet the real-time requirements, the detection and segmentation algorithms share the same feature extraction network, and are jointly trained as one framework. Finally, according to the detection and segmentation results, the robot can automatically avoid obstacles and move in the drivable area.

The development of robot technology is currently growing rapidly. Mobile robot is one robot with many applications in everyday life. One of the important things in the field of mobile robots is the problem of trajectories or trajectories, in this case how robots can track approved paths. In this study, the mobile robot control system has been tested to track tracks. The path used in this study is the third-order Bezier Order, with control points and end points of the predetermined pathway. Based on the results of simulation tests on the development of mobile robot trajectories, based on the results of simulation tests on mobile robots, it is found that the performance of the track tracking control system is very dependent on the placement of the Bezier curve control points or in other words the actual path formed by the robot is greatly influenced by the shape of the Bezier trajectory that was designed.

Stair climbing is one of the most important capabilities of mobile robots. Therefore, stair-climbing mobile robots have become a field of study and diverse stair-climbing mobile robots have been developed. Although tri-wheel-based stair-climbing robotic platforms were developed to overcome the challenges posed by stair climbing, they have shown limitations such as impact during locomotion and damage owing to friction with the nosing of the stairs. In this study, several tail mechanisms were proposed and designed to solve the limitations of tri-wheel-based stair-climbing robots. A comparative analysis of the tail mechanisms was performed through dynamic simulations based on various performance indices. It was observed that the tail mechanism improved the stability and stair-climbing performance of the tri-wheel-based stair-climbing robots. The experimental verification confirmed the reliability of the comparative analysis results based on the simulation. These findings can be used to design mobile stair-climbing robots.

Mobile robotics is a multidisciplinary field involving both computer science and engineering. Addressing the design of automated systems, it lies at the intersection of artificial intelligence, computational vision, and robotics. This textbook for advanced undergraduates and graduate students emphasizes algorithms for a range of strategies for locomotion, sensing, and reasoning. It concentrates on wheeled and legged mobile robots but discusses a variety of other propulsion systems. The new edition includes advances in robotics and intelligent machines over the last ten years, including significant coverage of SLAM (simultaneous localization and mapping) and multi-robot systems. It includes additional mathematical background and an extensive list of sample problems. Various mathematical techniques that were assumed in the first edition are now briefly introduced in appendices at the end of the text to make the book more self-contained. Researchers as well as students in the field of mobile robotics will appreciate this comprehensive treatment of state-of-the-art methods and key technologies.

For many years, researchers in the field of mobile robotics have been investigating the use of genetic and evolutionary computation (GEC) to aid the development of mobile robot controllers. Alongside the fundamental choices of the GEC mechanism and its operators, which apply to both simulated and physical evolutionary robotics, other issues have emerged which are specific to the application of GEC to physical mobile robotics. This article presents a survey of recent methods in GEC-developed mobile robot controllers, focusing on those methods that include a physical robot at some point in the learning loop. It simultaneously relates each of these methods to a framework of two orthogonal issues: the use of a simulated and/or a physical robot, and the use of finite, training phase evolution prior to a task and/or lifelong adaptation by evolution during a task. A list of evaluation criteria are presented and each of the surveyed methods are compared to them. Analyses of the framework and evaluation criteria suggest several possibilities; however, there appear to be particular advantages in combining simulated, training phase evolution (TPE) with lifelong adaptation by evolution (LAE) on a physical robot.

The application of intelligent control algorithms in the field of autonomous mobile robotics enables effective control of mobile robots with a minimal possible error. At present, most of commonly used systems to control an autonomous mobile robot are, however, too complicated to design. Our goal was to design a fuzzy controller with an optimal number of inference rules in a way to achieve the best possible level of quality of mobile robot control. The proposed controller was implemented in the mobile robot EN20, where the time of regulation and the absolute and the quadratic control surface were used to evaluate quality parameters. The analysis of the quality of control was performed with the use of a fuzzy controller with 9, 25 and 49 inference rules. We found from the results of modelling that the greatest influence on the quality of control of a mathematical model of the mobile robot had the number of inference rules of the fuzzy controller. Mathematical and graphical dependence of the quality of control on the number of inference rules was calculated from the parameters of the quality of control. The results of the research are equations of the curves of the individual parameters of control of quality, which show that for the control of the autonomous mobile robot EN 20, that the optimal fuzzy controller has 49 inference rules, triangular functions of the pertinence of individual linguistic values and it is defuzzificated by Centroid method.

The field of mobile robot (MR) navigation with obstacle avoidance has largely focused on real, physical obstacles as the sole external causative agent for navigation impediment. This paper has explored the possible option of virtual obstacles (VOs) dominance in robot navigation impediment in certain navigation environments as a MR move from one point in the workspace to a desired target point. The systematically explored literature presented reviews mostly between the years 2000 and 2021; however, some outlier reviews from earlier years were also covered. An exploratory review approach was deployed to itemise and discuss different navigation environments and how VOs can impact the efficacy of both algorithms and sensors on a robotic vehicle. The associated limitations and the specific problem types addressed in the different literature sources were highlighted including whether or not a VO was considered in the path planning simulation or experiment. The discussion and conclusive sections further recommended some solutions as a measure towards addressing sensor performance incapacitation in a robot vehicle navigation problem.

The mobile robot has been one of the hottest fields in recent years, it has been widely applied in the most critical and efficient occasions in the industry, meanwhile, path planning becomes a frontier and interesting research topic for the mobile robot. In this paper, firstly mobile robot is introduced, some universal path planning algorithms of the mobile robot are reviewed, then a fuzzy logic and filter smoothing based on the data from the laser scan sensor is proposed, the path planning and autonomous obstacle avoidance based on this algorithm is emphasized because it can automatically find the best path according to the size and position of gaps between the obstacles in the dynamic environment, finally our designed mobile robot and corresponding Android APP are introduced, the path planning and obstacle avoidance algorithms are tested on this mobile robot, the testing results show this algorithm has the advantage of responding quickly, global optimized and hardware resource saved compared with other algorithms, it is suitable for the mobile robot that is designed on the embedded system and it can meet our designed requirement.

In this paper we address the demand for flexibility and economic efficiency in industrial autonomous guided vehicle (AGV) systems by the use of cloud computing. We propose a cloud-based architecture that moves parts of mapping, localization and path planning tasks to a cloud server. We use a cooperative longterm Simultaneous Localization and Mapping (SLAM) approach which merges environment perception of stationary sensors and mobile robots into a central Holistic Environment Model (HEM). Further, we deploy a hierarchical cooperative path planning approach using Conflict-Based Search (CBS) to find optimal sets of paths which are then provided to the mobile robots. For communication we utilize the Manufacturing Service Bus (MSB) which is a component of the manufacturing cloud platform Virtual Fort Knox (VFK). We demonstrate the feasibility of this approach in a real-life industrial scenario. Additionally, we evaluate the system's communication and the planner for various numbers of agents.

The production and assembly of customized products increases the demand for flexible automation systems. One approach is to remove the safety fences that separate human and industrial robot to combine their skills. This collaboration possesses a certain risk for the human co-worker, leading to numerous safety concepts to protect him. The human needs to be monitored and tracked by a safety system using different sensors. The proposed system consists of a RGBD camera for surveillance of the common working area, an array of optical distance sensors to compensate shadowing effects of the RGBD camera and a laser range finder to detect the co-worker when approaching the work cell. The software for collision detection, path planning, robot control and predicting the behaviour of the co-worker is based on the Robot Operating System (ROS). A first prototype of the work cell shows that with advanced algorithms from the field of mobile robotics a very flexible safety concept can be realized: the robot not simply stops its movement when detecting a collision, but plans and executes an alternative path around the obstacle.

Recently, the field of mobile robotics have witnessed an unprecedented expansion due to their vast applications that range from surveillance and construction to planetary exploration and emergency rescue operations. Their tasks became more and more complex that their autonomy became essential in the majority of the applications which means that devising controllers that suit different scenarios and situations is of importance. In this project, we aim to control the velocity of a modelled 2-wheel differential drive robot by using a PSO optimized PID controller. In addition to speed control, in order for a robot to move to specific waypoints by itself, a path planning algorithm has to be implemented. Pure pursuit, a simple yet efficient path tracking method for nonholonomic ground vehicles is utilized.