Research on Autonomous Vehicle Path Planning Algorithm Based on Improved RRT* Algorithm and Artificial Potential Field Method
Abstract
:1. Introduction
2. Traditional Algorithm
2.1. RRT* Algorithm
2.2. Traditional Artificial Potential Field Method
3. Improved RRT* Algorithm
3.1. Introducing the Concept of Artificial Potential Fields
3.1.1. Introducing the Gravitational Component
3.1.2. Introduction of Repulsive Force Component
3.2. Probabilistic Sampling Optimization
3.3. Adaptive Step Size Strategy
3.4. Global Path Post-Processing
3.4.1. Node Pruning Strategy
3.4.2. Node Optimization
4. Improved Artificial Potential Field Method
4.1. Obstacle Avoidance Constraint
4.2. Road Repulsion Potential Field
4.3. Increase Distance Factor
4.4. Virtual Target Point
4.5. Elliptical Groove Treatment
5. Fusion Algorithm
5.1. Analysis of the Limitation of the Algorithm
5.2. Algorithm Fusion Strategy
5.3. Path Smoothing Strategy
6. Simulation Analysis
6.1. Simulation Analysis of Improved RRT* Algorithm
6.1.1. Experiment 1
6.1.2. Experiment 2
6.2. Simulation Analysis of Fusion Algorithm
7. Conclusions
- (1)
- Targeting the deficiencies of the RRT* algorithm, such as strong randomness, slow convergence speed, poor path feasibility, and poor ability to deal with corners, the RRT* algorithm is improved, and the concepts of artificial potential field and probabilistic sampling optimization are introduced to make RRT* node sampling more purposeful, probabilistic sampling applicability stronger, and sampling efficiency better. Considering the constraint imposed by the fixed step size, the adaptive step size is designed according to the road curvature to solve the problem that oscillation may occur near the target point, improve the adaptability to each road scene, and achieve rapid convergence towards the target point accurately. The path planned by the improved RRT* is post-processed to minimize the number of redundant nodes along the path and optimize the global path quality.
- (2)
- In view of the problems that the artificial potential field method is prone to local optimization, the target is unreachable, and it is not suitable for the global scene, an enhanced artificial potential field method is introduced, which adds obstacle avoidance constraints to obstacles and formulates a road boundary repulsion potential field to delineate the risk boundaries within the road space. The distance factor is added to the repulsion function to solve the problem of target unreachability. In the face of U-shaped obstacles, virtual gravity points are introduced to solve the local minimum problem and improve the performance of obstacle avoidance. For the case where the obstacle is located in the bend, the safety ellipse of the obstacle is treated with an elliptical slot to reduce unnecessary steering on the planned path.
- (3)
- Aiming at the emerging unknown obstacles, complex obstacles, and other road scenes, a fusion algorithm of improved RRT* and an improved artificial potential field method is proposed. The enhanced RRT* algorithm is employed for generating the global path, and the nodes of the global path are extracted to serve as temporary target points for the artificial potential field method, which guides the vehicle to drive, reduces the occurrence of the local minimum, uses the artificial potential field method to avoid the local path when encountered with unknown obstacles, and carries on the path smoothing processing to the planned path to satisfy the vehicle’s driving. The simulation results in different scenarios demonstrate that the fusion algorithm can successfully plan a smoother and more feasible path and verify its effectiveness and robustness.
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Achiri, A.T.; Mbue, I.N.; Merlin, A.; Gerard, A. Automobile Crash Investigation Based on Vehicle System Related Causes: Systematic Literature Review. World J. Eng. Technol. 2022, 10, 139–157. [Google Scholar] [CrossRef]
- Gaba, S.; Pawar, S.; Chinta, P.P.; Sweta, S. A computational model of deep learning in self-driving car. AIP Conf. Proc. 2023, 2755, 020019. [Google Scholar] [CrossRef]
- Lin, S.-L.; Li, X.-Q.; Wu, J.-Y.; Lin, B.-C. Research on overtaking path planning of autonomous vehicles. In Proceedings of the 2021 IEEE International Future Energy Electronics Conference (IFEEC), Taipei, Taiwan, 16–19 November 2021; pp. 1–4. [Google Scholar] [CrossRef]
- Reda, M.; Onsy, A.; Haikal, A.Y.; Ghanbari, A. Path planning algorithms in the autonomous driving system: A comprehensive review. Robot. Auton. Syst. 2024, 174, 104630. [Google Scholar] [CrossRef]
- Li, X. Path planning of intelligent mobile robot based on Dijkstra algorithm. J. Phys. Conf. Ser. 2021, 2083, 042034. [Google Scholar] [CrossRef]
- He, Z.; Liu, C.; Chu, X.; Negenborn, R.R.; Wu, Q. Dynamic anti-collision A-star algorithm for multi-ship encounter situations. Appl. Ocean. Res. 2022, 118, 102995. [Google Scholar] [CrossRef]
- Li, Q.; Xu, Y.; Bu, S.; Yang, J. Smart Vehicle Path Planning Based on Modified PRM Algorithm. Sensors 2022, 22, 6581. [Google Scholar] [CrossRef] [PubMed]
- Huang, G.; Ma, Q. Research on Path Planning Algorithm of Autonomous Vehicles Based on Improved RRT Algorithm. Int. J. Intell. Transp. Syst. Res. 2021, 20, 170–180. [Google Scholar] [CrossRef]
- Karaman, S.; Frazzoli, E. Sampling-based algorithms for optimal motion planning. Int. J. Robot. Res. 2011, 30, 846–894. [Google Scholar] [CrossRef]
- Cong, J.; Hu, J.; Wang, Y.; He, Z.; Han, L.; Su, M. FF-RRT*: A sampling-improved path planning algorithm for mobile robots against concave cavity obstacle. Complex Intell. Syst. 2023, 9, 7249–7267. [Google Scholar] [CrossRef]
- Lin, Y.; Zhang, L. An improved Quick Informed-RRT* algorithm based on hybrid bidirectional search and adaptive adjustment strategies. Intell. Serv. Robot. 2024. [Google Scholar] [CrossRef]
- Gu, X.; Han, M.; Zhang, W.; Xue, G.; Zhang, G.; Han, Y. Intelligent vehicle path planning based on improved artificial potential field algorithm. In Proceedings of the 2019 International Conference on High Performance Big Data and Intelligent Systems (HPBD&IS), Shenzhen, China, 9–11 May 2019; pp. 104–109. [Google Scholar] [CrossRef]
- Li, Y.; Yang, W.; Zhang, X.; Kang, X.; Li, M. Research on Automatic Driving Trajectory Planning and Tracking Control Based on Improvement of the Artificial Potential Field Method. Sustainability 2022, 14, 12131. [Google Scholar] [CrossRef]
- Xu, X.; Hu, Y.; Zhai, J.M.; Li, L.Z.; Guo, P.S. A novel non-collision trajectory planning algorithm based on velocity potential field for robotic manipulator. Int. J. Adv. Robot. Syst. 2018, 15, 1729881418787075. [Google Scholar] [CrossRef]
- Zhai, S.; Pei, Y. The Dynamic Path Planning of Autonomous Vehicles on Icy and Snowy Roads Based on an Improved Artificial Potential Field. Sustainability 2023, 15, 15377. [Google Scholar] [CrossRef]
- Huang, S. Path planning based on mixed algorithm of RRT and artificial potential field method. In Proceedings of the 2021 4th International Conference on Intelligent Robotics and Control Engineering (IRCE), Lanzhou, China, 18–20 September 2021; pp. 149–155. [Google Scholar] [CrossRef]
- Zhang, W.; Wang, N.; Wu, W. A hybrid path planning algorithm considering AUV dynamic constraints based on improved A* algorithm and APF algorithm. Ocean. Eng. 2023, 285, 115333. [Google Scholar] [CrossRef]
- Wu, H.; Zhang, Y.; Huang, L.; Zhang, J.; Luan, Z.; Zhao, W.; Chen, F. Research on vehicle obstacle avoidance path planning based on APF-PSO. Proc. Inst. Mech. Eng. Part D J. Automob. Eng. 2022, 237, 1391–1405. [Google Scholar] [CrossRef]
- Dasiah, N.B.J.a.p.a. Modified RRT* for Path Planning in Autonomous Driving. arXiv 2024, arXiv:arXiv:2402.12129. [Google Scholar] [CrossRef]
- Nguyen, K.; Dang, V.T.; Pham, D.D.; Dao, P.N. Formation control scheme with reinforcement learning strategy for a group of multiple surface vehicles. Int. J. Robust Nonlinear Control. 2023, 34, 2252–2279. [Google Scholar] [CrossRef]
- Shi, Y.; Dong, X.; Hua, Y.; Yu, J.; Ren, Z. Distributed output formation tracking control of heterogeneous multi-agent systems using reinforcement learning. ISA Trans. 2023, 138, 318–328. [Google Scholar] [CrossRef] [PubMed]
- Wei, K.; Ren, B. A Method on Dynamic Path Planning for Robotic Manipulator Autonomous Obstacle Avoidance Based on an Improved RRT Algorithm. Sensors 2018, 18, 571. [Google Scholar] [CrossRef]
- Xin, P.; Wang, X.; Liu, X.; Wang, Y.; Zhai, Z.; Ma, X. Improved Bidirectional RRT* Algorithm for Robot Path Planning. Sensors 2023, 23, 1041. [Google Scholar] [CrossRef]
- Dong, M.; Chen, T.; Yang, J. Simulation Research on path Planning of Unmanned vehicle based on improved RRT algorithm. Comput. Simul. 2019, 36, 96–100. [Google Scholar]
- Zhuge, C.; Wang, Q.; Liu, J.; Yao, L. An Improved Q-RRT* Algorithm Based on Virtual Light. Comput. Syst. Sci. Eng. 2021, 39, 107–119. [Google Scholar] [CrossRef]
- Li, W.; Jin, J. Optimal path Convergence method based on artificial potential Field method and heuristic sampling. Comput. Appl. 2021, 41, 2912. [Google Scholar] [CrossRef]
- Liu, X.; Cao, L. Research on path Planning of manipulator based on improved RRT* algorithm. J. Sichuan Univ. Sci. Eng. (Nat. Sci. Ed.) 2024, 37, 61–70. [Google Scholar] [CrossRef]
- Zhang, Y.; Gao, F.; Zhao, F. Research on Path Planning and Tracking Control of Autonomous Vehicles Based on Improved RRT* and PSO-LQR. Processes 2023, 11, 1841. [Google Scholar] [CrossRef]
- Wang, J.; Li, B.; Meng, M.Q.H. Kinematic Constrained Bi-directional RRT with Efficient Branch Pruning for robot path planning. Expert Syst. Appl. 2021, 170, 114541. [Google Scholar] [CrossRef]
- Guo, Y.; Liu, H.; Fan, X.; Lyu, W.; Chen, H. Research Progress of Path Planning Methods for Autonomous Underwater Vehicle. Math. Probl. Eng. 2021, 2021, 8847863. [Google Scholar] [CrossRef]
- Liu, H. Research on Path Planning of RRT Algorithm Based on APF. Master’s Thesis, Jiangsu University, Zhenjiang, China, 2022. [Google Scholar] [CrossRef]
- Wang, W.; Li, G.; Liu, S.; Yang, Q. Trajectory Planning of a Semi-Trailer Train Based on Constrained Iterative LQR. Appl. Sci. 2023, 13, 10614. [Google Scholar] [CrossRef]
- Hongyu, H.; Chi, Z.; Yuhuan, S.; Bin, Z.; Fei, G.J.I.-P. An improved artificial potential field model considering vehicle velocity for autonomous driving. IFAC-PapersOnLine 2018, 51, 863–867. [Google Scholar] [CrossRef]
- Ruan, S. Research on Path Planning of Mobile Robot Based on Improved RRT* and Artificial Potential Field Method; Hangzhou University of Electronic Science and Technology: Hangzhou, China, 2023. [Google Scholar] [CrossRef]
- Xie, C.; Tao, T.; Li, J. Research on path Planning based on improved artificial potential Field method. J. Jilin Univ. (Inf. Sci. Ed.) 2023, 41, 998–1006. [Google Scholar] [CrossRef]
- Li, Y.; Jin, R.; Xu, X.; Qian, Y.; Wang, H.; Xu, S.; Wang, Z. A Mobile Robot Path Planning Algorithm Based on Improved A* Algorithm and Dynamic Window Approach. IEEE Access 2022, 10, 57736–57747. [Google Scholar] [CrossRef]
- Lai, R.; Wu, Z.; Liu, X.; Zeng, N. Fusion Algorithm of the Improved A* Algorithm and Segmented Bézier Curves for the Path Planning of Mobile Robots. Sustainability 2023, 15, 2483. [Google Scholar] [CrossRef]
- Li, X.; Zheng, H.; Wang, J.; Xia, Y.; Song, H. A Global Path Planning Method for Unmanned Ground Vehicles in Off-Road Scenarios Based on Terrain Data. Soc. Sci. Res. Netw. 2024. [Google Scholar] [CrossRef]
Candidate Point | Trails | Path Distance |
---|---|---|
5 | 0-5-9 | 0-5-9 = 8 |
6 | 0-4-6-9 | 0-4-6-9 = 16 |
8 | 0-5-8-9 | 0-5-8-9 = 9 |
Neighboring Node | Original Consideration | New Pathway | New Price |
---|---|---|---|
4 | 10 | 0-5-9-4 | 0-5-9-4 = 12 |
6 | 10 + 5 = 15 | 0-5-9-6 | 0-5-9-6 = 9 |
8 | 3 + 5 + 1 = 6 | 0-5-9-8 | 0-5-9-8 = 11 |
Algorithm | Average Path Length | Average Number of Nodes | Average Simulation Time (s) | Average Iterations |
---|---|---|---|---|
RRT algorithm | 37.92 | 81 | 29.61 | 6150 |
RRT* algorithm | 34.05 | 42 | 20.09 | 5590 |
Traditional improved RRT algorithm | 33.89 | 47 | 2.24 | 575 |
This paper improves the algorithm. | 32.47 | 12 | 1.21 | 279 |
Algorithm | Average Path Length | Average Number of Nodes | Average Simulation Time (s) | Average Iterations |
---|---|---|---|---|
Dijkstra algorithm | 31.49 | 7 | 1.42 | 313 |
A* algorithm | 31.65 | 6 | 1.37 | 175 |
Ant colony algorithm | 32.93 | 16 | 3.47 | - |
Improved A* algorithm | 31.78 | 4 | 1.15 | 116 |
This paper improves the algorithm. | 32.47 | 12 | 1.21 | 279 |
Algorithm | Average Path Length | Average Number of Nodes |
---|---|---|
This paper improves the algorithm. | 32.47 | 12 |
An improved algorithm after node optimization | 26.52 | 9 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Li, X.; Li, G.; Bian, Z. Research on Autonomous Vehicle Path Planning Algorithm Based on Improved RRT* Algorithm and Artificial Potential Field Method. Sensors 2024, 24, 3899. https://doi.org/10.3390/s24123899
Li X, Li G, Bian Z. Research on Autonomous Vehicle Path Planning Algorithm Based on Improved RRT* Algorithm and Artificial Potential Field Method. Sensors. 2024; 24(12):3899. https://doi.org/10.3390/s24123899
Chicago/Turabian StyleLi, Xiang, Gang Li, and Zijian Bian. 2024. "Research on Autonomous Vehicle Path Planning Algorithm Based on Improved RRT* Algorithm and Artificial Potential Field Method" Sensors 24, no. 12: 3899. https://doi.org/10.3390/s24123899
APA StyleLi, X., Li, G., & Bian, Z. (2024). Research on Autonomous Vehicle Path Planning Algorithm Based on Improved RRT* Algorithm and Artificial Potential Field Method. Sensors, 24(12), 3899. https://doi.org/10.3390/s24123899