The path-planning algorithm aims to find the optimal path between the starting and goal points without collision. One of the most popular algorithms is the optimized Rapidly exploring Random Tree (RRT*). The strength of RRT* algorithm is the collision-free path. It is the main reason why RRT-based algorithms are used in path planning for mobile robots. The RRT* algorithm generally creates the node for randomly making a tree branch to reach the goal point. The weakness of the RRT* algorithm is in the random process when the randomized nodes fall into the obstacle regions. The proposed algorithm generates a new random environment by removing the obstacle regions from the global environment. The objective is to minimize the number of unusable nodes from the randomizing process. The results show better performance in computational time and overall path-planning length. Bacterial mutation and local search algorithms are combined at post-processing to get a better path length and reduce the number of nodes. The proposed algorithm is tested in simulation.

https://www.mdpi.com/2079-9292/11/9/1459/pdf?version=1651563286

Improved Rapidly Exploring Random Tree with Bacterial Mutation and Node Deletion for Offline Path Planning of Mobile Robot

Aiming at the problems of low success rate and slow learning speed of the DDPG algorithm in path planning of a mobile robot in a dynamic environment, an improved DDPG algorithm is designed. In this article, the RAdam algorithm is used to replace the neural network optimizer in DDPG, combined with the curiosity algorithm to improve the success rate and convergence speed. Based on the improved algorithm, priority experience replay is added, and transfer learning is introduced to improve the training effect. Through the ROS robot operating system and Gazebo simulation software, a dynamic simulation environment is established, and the improved DDPG algorithm and DDPG algorithm are compared. For the dynamic path planning task of the mobile robot, the simulation results show that the convergence speed of the improved DDPG algorithm is increased by 21%, and the success rate is increased to 90% compared with the original DDPG algorithm. It has a good effect on dynamic path planning for mobile robots with continuous action space.

/pdf/research-on-dynamic-path-planning-of-mobile-robot-based-on-29epw0l491.pdf

Research on Dynamic Path Planning of Mobile Robot Based on Improved DDPG Algorithm

In this paper, an improved artificial potential field (APF) method combined with Bug2 is proposed for dynamic obstacle avoidance of mobile robots, which eliminates the trajectory oscillations and avoids failure when encountering a complex obstacle. First, the problems of avoidance failure and trajectory oscillations of the relative position and velocity-based APF were analyzed. Then, a Bug2-based APF method is proposed by using the M-line of Bug2 to optimize the avoidance trajectory. The proposed method makes the angle of the virtual repulsion force tangent to the obstacle, which results in avoidance that the trajectory surrounds the obstacle along with the M-line. Finally, the effectiveness and practicability of the proposed method are demonstrated by performing many simulations and experiments. The results show that the proposed method can realize safe and autonomous dynamic obstacle avoidance and significantly improve the robot’s success rate and obstacle avoidance efficiency. 

An Improved Artificial Potential Field Method for Autonomous Dynamic Obstacle Avoidance of Complex Obstacles

In order to meet the requirements of vehicle automatic obstacle avoidance, a lane change trajectory planning method is proposed to meet the requirements of safety, comfort, and lane change efficiency. Firstly, the potential collision points that may exist are analyzed using information about surrounding vehicle movement and the road. Then, the safe lane change range for vehicles is obtained. Secondly, the control points of the fifth order Bézier curve are constrained to generate a series of path clusters in the optimal range. At the same time, the driver’s style and reaction time are taken into account in the risk assessment stage of the route using the improved artificial potential field method. Finally, the optimal path is selected by comprehensively considering lane-changing efficiency and comfort. In order to further verify the accuracy of the algorithm, real-vehicle experiments have been carried out on the autonomous vehicle platform. Under different driving styles, the vehicle can avoid obstacles perfectly while ensuring the smoothness of the path. Simulation and real-vehicle experiment results show that the proposed algorithm can provide an excellent solution for autonomous vehicles for lane changing and obstacle avoidance. 

/pdf/a-path-planning-method-for-autonomous-vehicles-based-on-risk-226pi5po.pdf

A Path Planning Method for Autonomous Vehicles Based on Risk Assessment

Robotic systems are becoming inevitable part of our lives. The demand for robotic system, which can perform multiple tasks with less complexity and energy consumption, is very high in the market. Multi robot system is the most recommended system for such requirements. In the case of multi-robot system reaching their intended destination and performing the assigned task determines its usefulness and relevance. In any mobile robot system path planning is a crucial step which should be designed carefully. Over the years, many path-planning algorithms have been realized yet there is scope of improvement in this area. Usually robotic path planning will happen either in static or dynamic environment. This work focuses on multi robotic path planning in a known environment (static in nature). The system consist of two robot, which will traverse through a planned path depending on the obstacles. The selection of the robot will be based on a score which is generated by considering multiple parameters. The cooperative behavior of these robots enables them to perform the task assigned to the other robot while the other robot is facing a malfunction or failure. The path planning process is realized using reinforcement learning for namely the Temporal Difference (TD) algorithm. The work also emphasizes on catering the existing TD algorithm to work for multi robotic system thereby increasing the efficiency of the system. The simulation of multi robotic system is carried out with the helpof Python 3.8.5 and SpyderIDE. 

Multi Robotic Path Planning in a Static Environment

Aiming at the problem of local deadlock and path redundancy when mobile robots are running in a complex and unknown environment, specific application design and simulation comparisons of several existing local path planning methods are carried out, and the planning process The problems that have arisen propose solutions. The principle and usage scenarios of three local path planning algorithms, artificial potential field method, Rapid-exploration Random Tree and bidirectional Rapid-exploration Random Tree are analyzed emphatically. Simulation tests are carried out on the MATLAB platform to verify the feasibility of the designed method Sex and effectiveness. This paper optimizes the RRT algorithm to get the B-RRT algorithm, so that the calculation time of path planning is greatly shortened.

Tianyang Hu

Papers

Research on the Path Planning Algorithm of Mobile Robot