Local Path Planning of Autonomous Vehicle Based on an Improved Heuristic Bi-RRT Algorithm in Dynamic Obstacle Avoidance Environment

Abstract

The existing variants of the rapidly exploring random tree (RRT) cannot be effectively applied in local path planning of the autonomous vehicle and solve the coherence problem of paths between the front and back frames. Thus, an improved heuristic Bi-RRT algorithm is proposed, which is suitable for obstacle avoidance of the vehicle in an unknown dynamic environment. The vehicle constraint considering the driver’s driving habit and the obstacle-free direct connection mode of two random trees are introduced. Multi-sampling biased towards the target state reduces invalid searches, and parent node selection with the comprehensive measurement index accelerates the algorithm’s execution while making the initial path gentle. The adaptive greedy step size, introducing the target direction, expands the node more effectively. Moreover, path reorganization minimizes redundant path points and makes the path’s curvature continuous, and path coherence makes paths between the frames connect smoothly. Simulation analysis clarifies the efficient performance of the proposed algorithm, which can generate the smoothest path within the shortest time compared with the other four algorithms. Furthermore, the experiments on dynamic environments further show that the proposed algorithm can generate a differentiable coherence path, ensuring the ride comfort and stability of the vehicle.

Research on path planning of autonomous vehicle based on RRT algorithm of Q-learning and obstacle distribution

“…Therefore, we propose a tree expansion method with a dynamic step size. The dynamic step method proposed in the current literature (Wang et al, 2022a;Zhang et al, 2022a;Yang et al, 2021) only dynamically changes the step size in the expansion of the tree depending on whether the current node collides with an obstacle or not. If no collision occurs, the step size is expanded, and if a collision occurs, the new node is re-found and expanded with a small step size.…”

Research into Autonomous Vehicles Following and Obstacle Avoidance Based on Deep Reinforcement Learning Method under Map Constraints

“…The simulation indicated that the vehicle could successfully track the path efficiently and reach the destination safely. An improved heuristic Bi-RRT algorithm, specialized for an unknown dynamic environment, was put forward by [ 9 ] for obstacle avoidance. Thence, the related experiments have verified the good performance of such an algorithm in differentiable coherence path generation, ensuring both ride comfort and stability of the vehicle.…”

Advanced Sensing and Safety Control for Connected and Automated Vehicles

“…This Special Issue on Sensors aims to report on some of the recent research efforts on this increasingly important topic. The 11 accepted papers in this Issue cover vehicle position estimation [ 1 ], 3D Object Detection [ 2 ], pedestrian state sense [ 3 ], trajectory prediction [ 4 ], criticality assessment [ 5 ], active fault-tolerant control for actuator failure [ 6 ], decision-making in the scenario of highway driving out of the ramp [ 7 ] and uncertain interactive traffic scenarios [ 8 ], RRT-based path planning algorithm [ 9 ], C/GMRES motion planning algorithm [ 10 ], and lane-keeping controller design [ 11 ]. In this introduction, a brief description of the content of each contribution forming the Special Issue is provided.…”

“…Ref. [ 9 ] proposes using an improved heuristic Bi-RRT algorithm to obtain a smooth and asymptotically optimal path, with continuous curvature possessing high efficiency and accuracy in an uncertain dynamic environment. The consideration of the driver’s driving habit and the obstacle-free direct connection mode of two trees, as well as the introduction of the greedy step size and the design of the path reorganization, can expand the node more effectively, make the path smooth, and ensure the ride comfort of the vehicle.…”

“…In summary, there is a huge potential for the application of CAV in areas of traffic perception, decision-making, and driving safety improvement. This Special Issue contributes to this by proposing solutions to the general problems of state estimation [ 1 ], objective detection [ 2 , 3 ], trajectory prediction [ 4 ], driving safety improvement [ 5 , 6 ], decision-making [ 7 , 8 ], path planning [ 9 , 10 ] and vehicle motion control [ 11 ], which largely represent the theoretical challenges and practical interest of this research topic. Finally, we wish to thank the authors, reviewers, and journal staff for their commitment and effort, without which we could not have completed this Special Issue on time.…”