← 研踪 PaperTrailarXiv:2611.20324 · v1
High-Speed Forward and Reverse Tractor-Trailer Driving with Learned Vehicle Dynamics
首次提交 2026-11-16 07:34
版本更新 2026-11-16 07:34
雷达观测 2026-11-17 17:12
摘要
Tractor-trailer systems are difficult to control, especially unstable during reverse motion, and their dynamics depend on difficult-to-measure factors, including road friction and suspension coefficients. We introduce a learned dynamics model for tractor-trailer control and compare it with a reduced-order dynamics model with Fiala tire forces as an analytic baseline. Specifically, we compare a model predictive path integral (MPPI) controller that uses the learned dynamics model to an MPPI controller that uses the analytic model, as well as to three additional baseline controllers. In the main closed-loop tracking experiments across four simulated environments, MPPI with learned dynamics achieves mean speeds closer to the target magnitudes and lower root-mean-square (RMS) hitch angles than MPPI with the analytic model at every tested setpoint, with higher completion rates in seven of eight reverse configurations.
作者备注:The first three authors contributed equally to this work. Project page: https://ds12a.github.io/drift-with-trailer/
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-16 07:34 · 最新观测版本
High-Speed Forward and Reverse Tractor-Trailer Driving with Learned Vehicle Dynamics
Tractor-trailer systems are difficult to control, especially unstable during reverse motion, and their dynamics depend on difficult-to-measure factors, including road friction and suspension coefficients. We introduce a learned dynamics model for tractor-trailer control and compare it with a reduced-order dynamics model with Fiala tire forces as an analytic baseline. Specifically, we compare a model predictive path integral (MPPI) controller that uses the learned dynamics model to an MPPI controller that uses the analytic model, as well as to three additional baseline controllers. In the main closed-loop tracking experiments across four simulated environments, MPPI with learned dynamics achieves mean speeds closer to the target magnitudes and lower root-mean-square (RMS) hitch angles than MPPI with the analytic model at every tested setpoint, with higher completion rates in seven of eight reverse configurations.
查看此版本解读 →查看此版本原文 ↗