Intelligent vehicle local path planning and trajectory tracking combining artificial potential field and dynamic window approach

Abstract

In response to the issues of slightly large curvatures of the planned paths and poor obstacle avoidance effect in dynamic obstacle environments associated with the artificial potential field (APF), a study on local obstacle avoidance algorithms for static and dynamic obstacles is conducted, taking the example of a two-lane road in the same direction. The improved algorithm introduces the elliptical obstacle potential field boundary model to improve the path smoothness, and the road-center attractive force is designed to ensure that the vehicle returns to the target lane quickly after the obstacle avoidance is completed. The feasible path is searched by the dynamic window approach (DWA) meeting the vehicle speed constraint, and the evaluation function of DWA is reconstructed based on the concept of the APF attraction and repulsion, and the optimal path is selected as the actual path of the vehicle to avoid obstacles. The reliability of the algorithm is validated through simulation using MATLAB, with results indicating a significant reduction in the curvature of the path planned by the improved algorithm, leading to enhancements in both the safety and smoothness of the path. The trajectory tracking controller is established, and the effectiveness of the planning algorithm is verified in the CarSim-Simulink co-simulation platform. The results show that the improved algorithm enables the vehicle to successfully complete the obstacle avoidance task in a complex and changeable environment, and the actual obstacle avoidance path is basically the same as the planning path in the obstacle avoidance process. The front wheel steering angle and lateral acceleration are both relatively small, with good trackability, comfort and safety.

Keywords

intelligent vehicles local path planning artificial potential field dynamic window approach trajectory tracking

Get full access to this article

View all access options for this article.

References

National Bureau of Statistics of the People’s Republic of China. China statistical yearbook. China Statistics Press, 2022.

Yang

Zhuang

Sun

, et al. Multifactor analysis of road traffic accidents. Chongq Jiaotong Univ (Nat Sci) 2018; 37(4): 87–95. https://doi.org/10.3969/j.issn.1674-0696.2018.04.14

Peng

Xie

Huang

. Research on local path planning algorithms for autonomous vehicles. Automot Eng 2020; 42(1): 1–10. https://link.oversea.cnki.net/doi/10.19562/j.chinasae.qcgc.2020.01.001

Chang

Wang

Xing

, et al. Robot path planning based on cluster-driven crossover genetic algorithm. Comp Eng Appl. Epub ahead of print 2026; 1–14. http://cea.ceaj.org/CN/10.3778/j.issn.1002-8331.2512-0063

Lamini

Benhlima

Elbekri

. Genetic algorithm based approach for autonomous mobile robot path planning. Procedia Compute Sci 2018; 127: 180–189. https://doi.org/10.1016/j.procs.2018.01.113

Jolly

Kumar

Vijayakumar

. A Bezier curve based path planning in a multi-agent robot soccer system without violating the acceleration limits. Robot Auton Syst 2009; 57(1): 23–33. https://doi.org/10.1016/j.robot.2008.03.009

Fox

Burgard

Thrun

. The dynamic window approach to collision avoidance. IEEE Robot Autom Mag 2002; 4(1): 23–33. https://doi.org/10.1109/100.580977

Song

Hao

. Path planning for unmanned surface vehicle based on predictive artificial potential field. Int J Adv Robot Syst 2020; 17(2): 1–17. https://doi.org/10.1177/1729881420918461

Zhang

, et al. Human-vehicle steering collision avoidance path planning based on pedestrian location prediction. Automot Eng 2021; 43(6): 877–884. https://link.oversea.cnki.net/doi/10.19562/j.chinasae.qcgc.2021.06.011

10.

Khatib

. Real-time obstacle avoidance for manipulators and mobile robots. Int J Robot Res 1986; 5(1): 90–98. https://doi.org/10.1177/027836498600500106

11.

Tang

, et al. Vehicles path planning and tracking based on an improved artificial potential field method. J Southwest Univ (Nat Sci Ed) 2018; 40(6): 174–182. https://link.oversea.cnki.net/doi/10.13718/j.cnki.xdzk.2018.06.025

12.

Raja

Dutta

Venkatesh

. New potential field method for rough terrain path planning using genetic algorithm for a 6-wheel rover. Robot Auton Syst 2015; 72: 295–306. https://doi.org/10.1016/j.robot.2015.06.002

13.

Abdul Hamid

Zamzuri

Yamada

, et al. Modular design of artificial potential field and nonlinear model predictive control for a vehicle collision avoidance system with move blocking strategy. Proc IMechE Part D: J Automobile Engineering 2018; 232(10): 1353–1373. https://doi.org/10.1177/0954407017729057

14.

Zheng

. Overtaking trajectory planning strategy for intelligent vehicles based on improved artificial potential field method. Agric Equip Veh Eng 2021; 59(9): 64–68. https://doi.org/10.3969/j.issn.1673-3142.2021.09.014

15.

Guo

. Local path planning for unmanned ground vehicles based on improved artificial potential field method in Frenet coordinate system. Acta Armamentarii 2024; 45(7): 2097–2109. https://doi.org/10.12382/bgxb.2023.0305

16.

Wang

. Research on mobile robot obstacle avoidance trajectories using improved artificial potential field method. Computer Eng Appl 2022; 58(6): 296–304. https://doi.org/10.3778/j.issn.1002-8331.2108-0122

17.

Wang

Yin

Zheng

, et al. Path planning for mobile robots based on improved A* algorithm and dynamic window approach. Robot 2020; 42(3): 346–353. https://link.oversea.cnki.net/doi/10.13973/j.cnki.robot.190305

18.

Chen

Huang

Shen

. Non-oscillatory path planning based on virtual obstacle method. Acta Armamentarii 2019; 40(3): 651–658. https://doi.org/10.3969/j.issn.1000-1093.2019.03.025

19.

Qiu

Wang

Zhao

, et al. Dynamic path planning for unmanned vehicles using improved artificial potential field method. Mach Des Manuf 2023; (3): 291–296. https://link.oversea.cnki.net/doi/10.19356/j.cnki.1001-3997.2023.03.011

20.

Zhao

Dong

, et al. Research on intelligent vehicle trajectory planning algorithm based on improved artificial potential field. Chongqing Jiaotong Univ (Nat Sci) 2022; 41(11): 153–160. https://doi.org/10.3969/j.issn.1674-0696.2022.11.21

21.

Zhang

Wei

. Mobile robot path planning based on improved artificial potential field method. J Syst Simul 2025; 37(11): 2918–2926. https://link.oversea.cnki.net/doi/10.16182/j.issn1004731x.joss.24-0665

22.

Liang

Zhao

, et al. AGV path planning algorithm based on fusion of dynamic window approach and artificial potential field method. Sci Technol Eng 2025; 25(14): 5924–5933. https://doi.org/10.12404/j.issn.1671-1815.2405367

23.

Bai

Pang

, et al. Path planning of autonomous mobile robot in comprehensive unknown environment using deep reinforcement learning. IEEE Internet Things J 2024; 11(12): 22153–22166. https://doi.org/10.1109/JIOT.2024.3379361

24.

Pang

Zuo

Liu

, et al. Design and experimental validation of lane centering control and dynamic obstacle avoidance for uncrewed autonomous car. IEEE/ASME Trans Mechatron. Epub ahead of print 2026: 1–13. https://doi.org/10.1109/TMECH.2025.3650596

25.

Zhou

, et al. Path tracking method for soil sampling platform based on MPC-Stanley. Trans Chin Soc Agric Eng 2026; 42(3): 79–87. https://doi.org/10.11975/j.issn.1002-6819.202509221