CAR-FMP: Improved Force-Based Motion Planning for Autonomous Vehicles in Urban Environments

Document Type : Original Article

Authors

1 B.Sc. Student, Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, Iran

2 Assistant Professor, Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, Iran

3 M.Sc. Student, Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, Iran

Abstract

Urban autonomous vehicle navigation remains one of the fundamental challenges in intelligent transportation systems, as it requires real-time decision-making in dynamic traffic conditions, continuous interaction with other vehicles, and appropriate responses to unpredictable obstacles. In this study, an enhanced version of the Force-based Motion Planning (FMP) algorithm, entitled CAR-FMP, is proposed for autonomous urban driving. In the proposed approach, an additional auxiliary force is introduced to enable safe overtaking maneuvers, maintain appropriate distances from surrounding vehicles, and dynamically adjust speed while turning, thereby improving the overall smoothness and stability of the vehicle’s motion. To evaluate performance, the algorithm was tested in the CARLA simulation environment under two standard benchmark scenarios, CoRL2017 and NoCrash. Experimental results indicate that the proposed CAR-FMP method achieves, on average, a 6% higher success rate in the CoRL2017 scenario and a 12% increase in the NoCrash scenario with dense traffic, compared with typical learning-based approaches. Overall, the CAR-FMP framework, relying on distributed control and independent of pre-defined paths, provides an effective and scalable solution for safe and efficient navigation of autonomous vehicles in complex urban environments.

Keywords

Main Subjects

References

[1]     L. Samimi-Dehkordi, " Network Attacks Detection in Autonomous Vehicles using Deep Nerul Network", Applied and basic Machine intelligence research, 2, 22025, pp. 83-93 10.22034/abmir.2025.22510.1083
[2]     S. Teng, X. Hu, P. Deng, B. Li, Y. Li, Y. Ai, D. Yang, L. Li, Z. Xuanyuan and F. Zhu, "Motion planning for autonomous driving: The state of the art and future perspectives," IEEE Transactions on Intelligent Vehicles, vol. 8, no. IEEE, pp. 3692--3711, 2023.
[3]     D. Dauner, M. Hallgarten, A. Geiger and K. Chitta, "Parting with misconceptions about learning-based vehicle motion planning," in Conference on Robot Learning, PMLR, 2023, pp. 1268--1281.
[4]     E. Ohn-Bar, A. Prakash, A. Behl, K. Chitta and A. Geiger, "Learning situational driving," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11296--11305.
[5]     J. Cheng, Y. Chen and Q. Chen, "Pluto: Pushing the limit of imitation learning-based planning for autonomous driving," arXiv preprint arXiv:2404.14327, 2024.
[6]     X. Liang, T. Wang, L. Yang and E. Xing, "Cirl: Controllable imitative reinforcement learning for vision-based self-driving," in Proceedings of the European conference on computer vision (ECCV), 2018, pp. 584--599.
[7]     D. Chen, B. Zhou, V. Koltun and P. Krähenbühl, "Learning by cheating," in Conference on robot learning, PMLR, 2020, pp. 66--75.
[8]     Codevilla, Felipe, et al. "End-to-end driving via conditional imitation learning." 2018 IEEE international conference on robotics and automation (ICRA). IEEE, 2018.
[9]     Y. Chen, C. Ji, Y. Cai, T. Yan and B. Su, "Deep reinforcement learning in autonomous car path planning and control: A survey," arXiv preprint arXiv:2404.00340, 2024.
[10]  L. Wang, S. Yang, K. Yuan, Y. Huang and H. Chen, "A combined reinforcement learning and model predictive control for car-following maneuver of autonomous vehicles," Chinese Journal of Mechanical Engineering, vol. 36, no. Springer, p. 80, 2023.
[11]  T. P. Lillicrap, J. J. Hunt, A. Pritzel, N. Heess, T. Erez, Y. Tassa, D. Silver and D. Wierstra, "Continuous control with deep reinforcement learning," arXiv preprint arXiv:1509.02971, 2015.
[12]  K. Lee, D. Isele, E. A. Theodorou and S. Bae, "Spatiotemporal costmap inference for MPC via deep inverse reinforcement learning," IEEE Robotics and Automation Letters, vol. 7, no. IEEE, pp. 3194--3201, 2022.
[13]  Toromanoff, M., Wirbel, E., & Moutarde, F. (2020). End-to-end model-free reinforcement learning for urban driving using implicit affordances. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 7153-7162)
[14]  A. Dosovitskiy, G. Ros, F. Codevilla, A. Lopez and V. Koltun, "CARLA: An open urban driving simulator," in Conference on robot learning, PMLR, 2017, pp. 1--16.
[15]  LaValle, S. M., & Kuffner, J. J. (2001). Randomized kinodynamic planning. The International Journal of Robotics Research, 20(5), 378–400.
[16]  Rawlings, J. B., & Mayne, D. Q. (2009). Model predictive control: Theory and design. Nob Hill Publishing.
[17]  S. H. Semnani, R. de, H. Anton and H. H. Liu, "Force-based algorithm for motion planning of large agent," IEEE Transactions on Cybernetics, vol. 52, no. IEEE, pp. 654--665, 2020.
[18]  G. Lin, A. Milan, C. Shen, and I. Reid. RefineNet: Multi-path refinement networks for high-resolutionsemantic segmentation. In Computer Vision and Pattern Recognition (CVPR), 2017
[19]  A. Krizhevsky, I. Sutskever, and G. E. Hinton. ImageNet classification with deep convolutional neural networks. In Neural Information Processing Systems (NIPS), 2012.
[20]  Kavraki, L. E., Švestka, P., Latombe, J. C., & Overmars, M. H. (1996). Probabilistic roadmaps for path planning in high-dimensional configuration spaces. IEEE Transactions on Robotics and Automation, 12(4), 566–580.
[21]  P. E. Hart, N. J. Nilsson, and B. Raphael, “A formal basis for the heuristic determination of minimum cost paths,” IEEE Transactions on Systems Science and Cybernetics, vol. 4, no. 2, pp. 100–107, Jul. 1968, doi: 10.1109/TSSC.1968.300136.
Applied and basic Machine intelligence research
Volume 4, Issue 1
May 2026
Pages 15-27

Files

Share

How to cite

Statistics