Path Planning for Static Obstacle Avoidance of Autonomous Vehicles based on Imitation Learning and Optimization Technique

Youngmin Yoon; Jaewan Lee

doi:10.22680/kasa2025.17.4.007

All Issue

2025 Vol.17, Issue 4 Next Page

Path Planning for Static Obstacle Avoidance of Autonomous Vehicles based on Imitation Learning and Optimization Technique 모방 학습 및 최적화 기법에 기반한 자율주행 차량의 고정 장애물 회피 경로 계획 연구

31 December 2025. pp. 7-13

PDF XML

Abstract

Imitation learning has been one of the mainstream methods for achieving autonomous driving in recent years. Despite its simple structure and expert-like performance in dealing with diverse driving situations, it may lead to unsafe driving solutions due to the absence of a constraint-checking process. To resolve this problem, this paper presents a method for path planning of autonomous vehicles based on imitation learning and optimization techniques. In this paper, imitation learning is used to derive the expert-like driving path. For this, a neural network is trained in a supervised manner to derive the driving path output given environmental information and a reference path. An optimization technique is applied to post-process the imitation-based driving path result using a cost function and constraints. This contributes to enhanced safety compared to a path planner based solely on imitation learning. The proposed algorithm has been validated via simulation studies. The test results show that the proposed combination of imitation learning and optimization techniques enables the autonomous vehicle to derive a feasible driving path following the expert driving pattern. The addition of the optimization technique is shown to reduce collision rate compared to the neural network-based path planning.

Keywords

Path planning(경로 계획)

Autonomous vehicle(자율주행 자동차)

Imitation learning(모방학습)

Optimization(최적화)

References

M. Werling, S. Kammel, J. Ziegler, and L. Gröll, 2012, “Optimal trajectories for time-critical street scenarios using discretized terminal manifolds,” The International Journal of Robotics Research, Vol. 31, No. 3, pp. 346~359.

10.1177/0278364911423042

Y. Liu, B. Zhou, X. Wang, L. Li, S. Cheng, Z. Chen, G. Li, and L. Zhang, 2021, “Dynamic lane-changing trajectory planning for autonomous vehicles based on discrete global trajectory,” IEEE Transactions on Intelligent Transportation Systems, Vol. 23, No. 7, pp. 8513~8527.

10.1109/TITS.2021.3083541

J. Ziegler, P. Bender, T. Dang, and C. Stiller, 2014, “Trajectory planning for bertha—a local, continuous method,” in 2014 IEEE intelligent vehicles symposium proceedings. IEEE, pp. 450~457.

10.1109/IVS.2014.6856581

X. Zhang, A. Liniger, and F. Borrelli, 2020, “Optimization-based collision avoidance,” IEEE Transactions on Control Systems Technology, Vol. 29, No. 3, pp. 972~983.

10.1109/TCST.2019.2949540

M. Kuderer, S. Gulati, and W. Burgard, 2015, “Learning driving styles for autonomous vehicles from demonstration,” in 2015 IEEE international conference on robotics and automation (ICRA). IEEE, pp. 2641~2646.

10.1109/ICRA.2015.7139555

H. Tian, C. Wei, C. Jiang, Z. Li, and J. Hu, 2022, “Personalized lane change planning and control by imitation learning from drivers,” IEEE Transactions on Industrial Electronics, Vol. 70, No. 4, pp. 3995~4006.

10.1109/TIE.2022.3177788

L. Caltagirone, M. Bellone, L. Svensson, and M. Wahde, 2017, “Lidar-based driving path generation using fully convolutional neural networks,” in 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC). IEEE, pp. 1~6

10.1109/ITSC.2017.8317618

J. Ahn, M. Kim, and J. Park, 2022, “Autonomous driving using imitation learning with look ahead point for semi structured environments,” Scientific Reports, Vol. 12, No. 1, p. 21285.

10.1038/s41598-022-23546-636494372PMC9734677

D. P. Kingma and J. Ba, 2014, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980.

R. Oliveira, P. F. Lima, G. C. Pereira, J. Mårtensson, and B. Wahlberg, 2019, “Path planning for autonomous bus driving in highly constrained environments,” in 2019 IEEE intelligent transportation systems conference (ITSC). IEEE, pp. 2743~2749

10.1109/ITSC.2019.8916773

A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga et al., 2019, “Pytorch: An imperative style, high-performance deep learning library,” Advances in neural information processing systems, Vol. 32.

J. A. Andersson, J. Gillis, G. Horn, J. B. Rawlings, and M. Diehl, 2019, “Casadi: a software framework for nonlinear optimization and optimal control,” Mathematical Programming Computation, Vol. 11, pp. 1~36.

10.1007/s12532-018-0139-4

T. Zhang, W. Song, M. Fu, Y. Yang, X. Tian, and M. Wang, 2021, “A unified framework integrating decision making and trajectory planning based on spatio-temporal voxels for highway autonomous driving,” IEEE Transactions on Intelligent Transportation Systems, Vol. 23, No. 8, pp. 10365~10379.

10.1109/TITS.2021.3093548

Information

Publisher :Korean Auto-vehicle Safety Association
Publisher(Ko) :한국자동차모빌리티안전학회
Journal Title :Journal of Auto-vehicle Safety Association
Journal Title(Ko) :자동차안전학회지
Volume : 17
No :4
Pages :7-13
Received Date : 2024-05-30
Revised Date : 2024-08-09
Accepted Date : 2025-08-13
DOI :https://doi.org/10.22680/kasa2025.17.4.007

Journal of Auto-vehicle Safety Association ISSN:2005-9396(Print) 자동차안전학회지

All Issue