Journal of Auto-vehicle Safety Association (자동차안전학회지)

Korean Auto-vehicle Safety Association (한국자동차안전학회)
권호 표지
DOI QR코드

DOI QR Code

Motion Planning of Autonomous Racing Vehicles for Mimicking Human Driver Characteristics

운전자 주행 특성 모사를 위한 트랙 한계 자율 주행 차량의 거동 계획 알고리즘

  • 김창희 (서울대학교 기계공학부) ;
  • 이경수 (서울대학교 기계공학부)
  • Received : 2022.09.05
  • Accepted : 2024.01.17
  • Published : 2024.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a motion planning algorithm of autonomous racing vehicles for mimicking the characteristics of a human driver. Time optimal maneuver of a race car has been actively studied as a major research area over the past decades. Although the time optimization problem yields a single time series solution of minimum time maneuver inputs for the vehicle, human drivers achieve similar lap times while taking various racing lines and velocity profiles. In order to model the characteristics of a specific driver and reproduce the motion, a stochastic motion planning framework based on kernelized motion primitive is introduced. The proposed framework imitates the behavior of the generated reference motion, which is based on a small number of human demonstration laps along the racetrack using Gaussian mixture model and Gaussian mixture regression. The mean and covariance of the racing line and velocity profile mimicking the driver are obtained by accumulating the outputs tested at equidistantly sampled input points. The results confirmed that the obtained lateral and longitudinal motion simulates the driver's driving characteristics, which are feasible for actual vehicle test environments.

Keywords

Acknowledgement

본 논문은 산업통상자원부 자율주행기술개발혁신사업(20018101, TCar 기반 자율주행 인지예측지능제어 차량부품시스템 통합평가 기술개발)의 지원을 받아 수행하였습니다.

References

  1. Tseng, H. E., Ashrafi, B., Madau, D., Brown, T. and Recker, D., 1999, "The development of vehicle stability control at Ford," IEEE/ASME transactions on mechatronics, Vol. 4, No. 3, pp. 223~234. https://doi.org/10.1109/3516.789681
  2. Betz, J., et al., 2022, "Autonomous Vehicles on the Edge: A Survey on Autonomous Vehicle Racing," arXiv preprint, arXiv:2202.07008.
  3. Kapania, N. R., Subosits, J. and Gerdes, J. C., 2016, "A sequential two-step algorithm for fast generation of vehicle racing trajectories," Journal of Dynamic Systems, Measurement, and Control, Vol. 138, No. 9, pp. 1~10. https://doi.org/10.1115/1.4033311
  4. Heilmeier, A., et al., 2020, "Minimum curvature trajectory planning and control for an autonomous race car," Vehicle System Dynamics, Vol. 58, No. 10, pp. 1497~1527. https://doi.org/10.1080/00423114.2019.1631455
  5. Braghin, F., Cheli, F., Melzi, S. and Sabbioni, E., 2008, "Race driver model," Computers & Structures, Vol. 86, No. 13~14, pp. 1503~1516. https://doi.org/10.1016/j.compstruc.2007.04.028
  6. Christ, F., Wischnewski, A., Heilmeier, A. and Lohmann, B., 2021, "Time-optimal trajectory planning for a race car considering variable tyre-road friction coefficients," Vehicle System Dynamics, Vol. 59, No. 4, pp. 588~612. https://doi.org/10.1080/00423114.2019.1704804
  7. Kegelman, J. C., Harbott, L. K. and Gerdes, J. C., 2017, "Insights into vehicle trajectories at the handling limits: analysing open data from race car drivers," Vehicle System Dynamics, Vol. 55, No. 2, pp. 191~207. https://doi.org/10.1080/00423114.2016.1249893
  8. Bentley, R., 1998, "Speed secrets: Professional race driving techniques," MotorBooks International.
  9. Calinon, S., Guenter, F. and Billard, A., 2007, "On learning, representing, and generalizing a task in a humanoid robot," IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), Vol. 37, No. 2, pp. 286~298. https://doi.org/10.1109/TSMCB.2006.886952
  10. Calinon, S., 2016, "A tutorial on task-parameterized movement learning and retrieval," Intelligent service robotics, Vol. 9, No. 1, pp. 1~29. https://doi.org/10.1007/s11370-015-0187-9
  11. Huang, Y., Rozo, L., Silverio, J. and Darwin G., 2019, "Kernelized movement primitives," The International Journal of Robotics Research, Vol. 38, No. 7, pp. 833~852. https://doi.org/10.1177/0278364919846363