Optimizing Steering Feedback Torque With Reinforcement Learning Guided by Human Reward Model
IEEE Transactions on Transportation Electrification · 2024-12 · 10 (4) · 10468-10480
DOI: 10.1109/tte.2024.3381266 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Transportation Electrification, 2024-12. Verfasst von Rui Zhao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: “Lingyan” Research and Development Program of Zhejiang Province, “Jianbing” Research and Development Program of Zhejiang Province, Key Research and Development Program of Jiaxing.
Abstract (Originalsprache)
Steering feel holds a main role in driving, making steering feedback torque (SFT) generation an important research of steer-by-wire (SBW) system. Authentic steering feel provides sensations comparable to conventional steering systems, while the SFT model aligns with driver preferences, reducing cognitive load and fatigue, thereby improving vehicle safety. Current research on driver-preferred SFT is limited to real-world trials, a method often time-intensive and suboptimal. This article presents an innovative approach for obtaining optimal SFT with reinforcement learning (RL) guided by the human reward model. The human reward model, trained on human feedback data, is introduced to guide the SFT model’s optimization. Given complexity of assessing human evaluations, the reward model is validated with virtual data. Building upon previous data-driven SFT modeling, a fine-tuning method leveraging the RL method is presented, using human reward model’s outputs. This approach retains the nonlinear predictive capabilities of the pretrained model while aligning with human evaluations. Results confirm the human reward model’s ability to replicate human SFT standards. Models adapted using this network retain the nonlinear predictive capabilities of the initial network, even under high-frequency inputs. Overall, this work pioneers the integration of human feedback into SFT optimization, providing novel insights for the advancement of SBW systems.
Förderung
- “Lingyan” Research and Development Program of Zhejiang Province
- “Jianbing” Research and Development Program of Zhejiang Province
- Key Research and Development Program of Jiaxing
Zitieren
APA
Zhao, R., Deng, W., Huang, K., Nan, J., Wang, Y., & Ding, J. (2024). Optimizing Steering Feedback Torque With Reinforcement Learning Guided by Human Reward Model. IEEE Transactions on Transportation Electrification, 10(4), 10468-10480. https://doi.org/10.1109/tte.2024.3381266
Vancouver
Zhao R, Deng W, Huang K, Nan J, Wang Y, Ding J. Optimizing Steering Feedback Torque With Reinforcement Learning Guided by Human Reward Model. IEEE Transactions on Transportation Electrification. 2024;10(4):10468-10480. doi:10.1109/tte.2024.3381266
BibTeX
@article{Zhao2024,
author = {Zhao, Rui and Deng, Weiwen and Huang, Kaibo and Nan, Jiangfeng and Wang, Ying and Ding, Juan},
title = {Optimizing Steering Feedback Torque With Reinforcement Learning Guided by Human Reward Model},
journal = {IEEE Transactions on Transportation Electrification},
year = {2024},
volume = {10},
number = {4},
pages = {10468--10480},
doi = {10.1109/tte.2024.3381266}
}
EUVIMED