Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Autonomous Drifting with 3 Minutes of Data via Learned Tire Models (2306.06330v2)

Published 10 Jun 2023 in eess.SY, cs.LG, and cs.SY

Abstract: Near the limits of adhesion, the forces generated by a tire are nonlinear and intricately coupled. Efficient and accurate modelling in this region could improve safety, especially in emergency situations where high forces are required. To this end, we propose a novel family of tire force models based on neural ordinary differential equations and a neural-ExpTanh parameterization. These models are designed to satisfy physically insightful assumptions while also having sufficient fidelity to capture higher-order effects directly from vehicle state measurements. They are used as drop-in replacements for an analytical brush tire model in an existing nonlinear model predictive control framework. Experiments with a customized Toyota Supra show that scarce amounts of driving data -- less than three minutes -- is sufficient to achieve high-performance autonomous drifting on various trajectories with speeds up to 45mph. Comparisons with the benchmark model show a $4 \times$ improvement in tracking performance, smoother control inputs, and faster and more consistent computation time.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (28)
  1. H. B. Pacejka, Tire and Vehicle Dynamics. Butterworth-Heinemann, third edition ed., 2012.
  2. J. Svendenius and M. Gäfvert, “Construction of novel semi-empirical tire models for combined braking and cornering,” Technical Reports; TFRT, vol. 7606, 2003.
  3. J. Svendenius, Tire modeling and friction estimation. PhD thesis, Lund University, 2007.
  4. M. Acosta and S. Kanarachos, “Tire lateral force estimation and grip potential identification using neural networks, extended kalman filter, and recursive least squares,” Neural Computing and Applications, vol. 30, pp. 3445–3465, 2017.
  5. P. Guarneri, G. Rocca, and M. Gobbi, “A neural-network-based model for the dynamic simulation of the tire/suspension system while traversing road irregularities,” IEEE Transactions on Neural Networks, vol. 19, pp. 1549–1563, 2008.
  6. N. Xu, H. Askari, Y. Huang, J. Zhou, and A. Khajepour, “Tire force estimation in intelligent tires using machine learning,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, pp. 3565–3574, 2022.
  7. J. Matuško, I. Petrović, and N. Peric, “Neural network based tire/road friction force estimation,” Eng. Appl. Artif. Intell., vol. 21, pp. 442–456, 2008.
  8. B. Paden, M. Cáp, S. Z. Yong, D. S. Yershov, and E. Frazzoli, “A survey of motion planning and control techniques for self-driving urban vehicles,” IEEE Transactions on Intelligent Vehicles, vol. 1, pp. 33–55, 2016.
  9. C. You and P. Tsiotras, “Vehicle modeling and parameter estimation using adaptive limited memory joint-state ukf,” 2017 American Control Conference (ACC), pp. 322–327, 2017.
  10. Springer Science & Business Media, 2011.
  11. P. Falcone, F. Borrelli, J. Asgari, H. E. Tseng, and D. Hrovat, “Predictive active steering control for autonomous vehicle systems,” IEEE Transactions on Control Systems Technology, vol. 15, pp. 566–580, 2007.
  12. J. Kong, M. Pfeiffer, G. Schildbach, and F. Borrelli, “Kinematic and dynamic vehicle models for autonomous driving control design,” 2015 IEEE Intelligent Vehicles Symposium (IV), pp. 1094–1099, 2015.
  13. P. Polack, F. Altché, B. d’Andréa Novel, and A. de La Fortelle, “The kinematic bicycle model: A consistent model for planning feasible trajectories for autonomous vehicles?,” 2017 IEEE Intelligent Vehicles Symposium (IV), pp. 812–818, 2017.
  14. E. Fiala, “Seitenkraften am rollenden luftreifen,” VdI, vol. 96, pp. 973–979, 1954.
  15. J. Y. Goh, T. Goel, and J. C. Gerdes, “Toward automated vehicle control beyond the stability limits: Drifting along a general path,” Journal of Dynamic Systems Measurement and Control-transactions of The Asme, vol. 142, 2019.
  16. A. Balachandran, T. L. Chen, J. Y. Goh, S. McGill, G. Rosman, S. Stent, and J. J. Leonard, “Human-centric intelligent driving: Collaborating with the driver to improve safety,” in Automated Road Transportation Symposium, pp. 85–109, Springer, 2023.
  17. R. Hindiyeh and J. C. Gerdes, “A controller framework for autonomous drifting: Design, stability, and experimental validation,” Journal of Dynamic Systems Measurement and Control-transactions of The Asme, vol. 136, p. 051015, 2011.
  18. J. K. Subosits and J. C. Gerdes, “Impacts of model fidelity on trajectory optimization for autonomous vehicles in extreme maneuvers,” IEEE Transactions on Intelligent Vehicles, vol. 6, pp. 546–558, 2021.
  19. J. Y. Goh and J. C. Gerdes, “Simultaneous stabilization and tracking of basic automobile drifting trajectories,” 2016 IEEE Intelligent Vehicles Symposium (IV), pp. 597–602, 2016.
  20. J. Y. M. Goh, Automated vehicle control beyond the stability limits. Stanford University, 2019.
  21. S. Srinivasan, I. Sa, A. Zyner, V. Reijgwart, M. de la Iglesia Valls, and R. Y. Siegwart, “End-to-end velocity estimation for autonomous racing,” IEEE Robotics and Automation Letters, vol. 5, pp. 6869–6875, 2020.
  22. N. A. Spielberg, M. Brown, N. R. Kapania, J. C. Kegelman, and J. C. Gerdes, “Neural network vehicle models for high-performance automated driving,” Science Robotics, vol. 4, 2019.
  23. G. Williams, P. Drews, B. Goldfain, J. M. Rehg, and E. A. Theodorou, “Information-theoretic model predictive control: Theory and applications to autonomous driving,” IEEE Transactions on Robotics, vol. 34, pp. 1603–1622, 2017.
  24. T. Q. Chen, Y. Rubanova, J. Bettencourt, and D. K. Duvenaud, “Neural ordinary differential equations,” in NeurIPS, 2018.
  25. F. Djeumou, C. Neary, É. Goubault, S. Putot, and U. Topcu, “Neural networks with physics-informed architectures and constraints for dynamical systems modeling,” in L4DC, 2022.
  26. F. Djeumou, C. Neary, É. Goubault, S. Putot, and U. Topcu, “Taylor-lagrange neural ordinary differential equations: Toward fast training and evaluation of neural odes,” in IJCAI, 2022.
  27. J. Y. Goh, M. Thompson, J. Dallas, and A. Balachandran, “Nonlinear model predictive control for highly transient autonomous drifting.” 15th International Symposium on Advanced Vehicle Control, 2022.
  28. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.
Citations (16)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now