Volume 3 · Issue 7 (2026)
DOI number:
10.66521/2938-9933-2026071903
An Improved Artificial Potential Field Method for Local Obstacle-Avoidance Path Planning of Intelligent Vehicles
Chaojie Lei, Wen Li*, Hongbing Chen, Yidan Gao, Hanlu Shi
Business School, East China University of Political Science and Law, Shanghai 201620, China
Corresponding Author: Wen Li (1609151361@qq.com)
Abstract: Aiming at the inherent defects of the traditional Artificial Potential Field (APF) method in local obstacle avoidance path planning for intelligent vehicles, including the Goal Non-Reachable with Obstacles Nearby (GNRON) problem, local minima traps, and path oscillation near obstacles, this paper proposes an improved APF method. The improvements include three aspects: introducing a relative distance factor to reconstruct the repulsive potential field function so that the repulsive force naturally vanishes at the goal position; designing a virtual sub-goal guidance strategy that generates a temporary sub-goal in the gradient-perpendicular direction when the vehicle is detected to be trapped in a local minimum; and constructing an adaptive step-size mechanism that dynamically adjusts the motion step according to obstacle proximity. Comparative experiments are conducted in six typical simulation scenarios with 50 independent trials each. Results show that the improved algorithm achieves 100% goal reachability across all scenarios, while the traditional APF completely fails in three challenging scenarios (GNRON, U-trap, symmetric obstacles) and only succeeds in three simpler ones. In the complex comprehensive scenario, path length is reduced by 5.5% and path smoothness is improved by 32.9%. The adaptive step-size strategy reduces path length by 23.5% and improves smoothness by 28.6% compared to fixed step sizes. Parameter sensitivity analysis demonstrates that 96.7% of parameter combinations yield successful path planning, indicating strong robustness.
Keywords: Artificial Potential Field; Path Planning; Local Obstacle Avoidance; Local Minima; Adaptive Step Size; Intelligent Vehicle
References
[1]
Khatib O. Real-time obstacle avoidance for manipulators and mobile robots[J]. International Journal of Robotics Research, 1986, 5(1): 90-98.
[2]
Fox D, Burgard W, Thrun S. The dynamic window approach to collision avoidance[J]. IEEE Robotics & Automation Magazine, 1997, 4(1): 23-33.
[3]
Zhou Z, Chen J. Semantic-aware path planning with A* and APF integration for complex environments[J]. Robotics and Autonomous Systems, 2023, 160: 104325.
[4]
Ge S S, Cui Y J. Dynamic motion planning for mobile robots using potential field method[J]. Autonomous Robots, 2002, 13(3): 207-222.
[5]
Ge S S, Cui Y J. New potential functions for mobile robot path planning[J]. IEEE Transactions on Robotics and Automation, 2000, 16(5): 615-620.
[6]
Park M G, Jeon J H, Lee M C. Obstacle avoidance for mobile robots using artificial potential field approach with simulated annealing[C]// IEEE International Symposium on Industrial Electronics. Pusan: IEEE, 2001: 1530-1535.
[7]
Luo G, Yu L, Pourcel L. A reliable path planning algorithm based on adjustable radius virtual circle model[J]. Journal of Intelligent & Robotic Systems, 2021, 103(2): 1-16.
[8]
Koren Y, Borenstein J. Potential field methods and their inherent limitations for mobile robot navigation[C]// IEEE International Conference on Robotics and Automation. Sacramento: IEEE, 1991: 1398-1404.
[9]
Liu Zhijie, Zhang Minglu, Zhang Xiaojun. Path planning of mobile robots based on an improved artificial potential field method[J]. robot, 2018, 40(1): 24-30.
[10]
Li G, Yamashita A, Asama H, et al. An efficient improved artificial potential field based regression search method for robot path planning[C]// IEEE International Conference on Mechatronics and Automation. Chengdu: IEEE, 2012: 1227-1232.
[11]
Sun J, Liu G, Tian G, et al. Smart obstacle avoidance using a danger index for a dynamic environment[J]. Applied Sciences, 2019, 9(8): 1589.
[12]
Rostami S M H, Sangaiah A K, Wang J, et al. Obstacle avoidance of mobile robots using modified artificial potential field algorithm[J]. EURASIP Journal on Wireless Communications and Networking, 2019, 2019(1): 1-19.
[13]
Cai Zixing, He Hangen, Chen Hong. Current status and future development of mobile robot technology research[J]. robot, 2002, 24(5): 475-480.
[14]
Montiel O, Orozco-Rosas U, Sepulveda R. Path planning for mobile robots using bacterial potential field for avoiding static and dynamic obstacles[J]. Expert Systems with Applications, 2015, 42(12): 5177-5191.
[15]
Mac T T, Copot C, Tran D T, et al. Heuristic approaches in robot path planning: a survey[J]. Robotics and Autonomous Systems, 2016, 86: 13-28.
[16]
LaValle S M. Rapidly-exploring random trees: a new tool for path planning[R]. Computer Science Department, Iowa State University, 1998.
[17]
Karaman S, Frazzoli E. Sampling-based algorithms for optimal motion planning[J]. International Journal of Robotics Research, 2011, 30(7): 846-894.
[18]
Zhang Tao, Li Qingdu. Mobile robot path planning based on an improved RRT algorithm[J]. Computer Engineering and Applications, 2019, 55(12): 234-239.
[19]
Weerakoon T, Ishii K, Nassiraei A A F. An artificial potential field based mobile robot navigation method to prevent from deadlock[J]. Journal of Artificial Intelligence and Soft Computing Research, 2015, 5(3): 189-203.
[20]
Zhao Dongbin, Liu Derong, Yi Jianqiang. A review of path planning methods based on deep reinforcement learning[J]. Control and Decision, 2021, 36(7): 1521-1536.
Download PDF