论文arXiv 2611.218064 天前
VIL仿真概率横向运动预测模型:融合物理先验与残差学习降低19%位置误差
本文由 AI 根据公开内容整理,可能有误,请以原文为准:A Probabilistic Lateral Motion Prediction Model with Improved Response Fidelity for Vehicle-in-the-Loop Simulation(arXiv 2611.21806)
核心内容
针对车辆环回(VIL)仿真中横向动力学模型递归积分失真的痛点,研究提出一种改进响应保真度的概率横向运动预测模型。该方案旨在解决传统模型在生成水平横向位置及航向指令时累积误差过大的问题。实验数据显示,相比Deep Dynamics自适应方法,新模型将平均横向位置均方根误差(RMSE)从0.596m降至0.483m,提升幅度达19.0%;横向速度RMSE从0.0469m/s优化至0.0441m/s,验证了其在长时序预测中的有效性。
技术架构采用二自由度车辆模型作为物理先验,利用循环神经网络(RNN)学习横向加速度与横摆角速度的相关残差修正项。为维持递归生成时的保真度,引入多步展开训练策略,将修正后的响应反馈至后续状态并直接惩罚累积横向速度误差。同时,通过条件高斯分布表征响应不确定性,并利用增广状态线性化将其传播至位置与航向预测中,实现了物理机理与数据驱动残差学习的深度融合,确保了仿真环境下运动生成的置信度。
关键看点
- 混合建模架构:以二自由度车辆模型为物理先验,叠加RNN学习横向加速度与横摆角速度的相关残差修正,兼顾物理可解释性与数据拟合能力。
- 多步展开训练:在训练阶段将修正响应递归输入后续状态,直接惩罚累积横向速度误差,有效解决了开环训练导致的闭环推理误差发散问题。
- 量化性能提升:横向位置RMSE由0.596m降至0.483m(优化19%),横向速度RMSE由0.0469m/s降至0.0441m/s,显著优于Deep Dynamics基准。
- 不确定性传播机制:采用条件高斯分布表征响应不确定性,并通过增广状态线性化传递至位置与航向预测,为VIL仿真提供可靠的概率边界。
工程与产业观察
该研究为具身智能体的高保真Sim2Real迁移提供了关键动力学基准。其“物理先验+残差学习+多步展开”范式不仅适用于车辆VIL仿真,对足式机器人等复杂非线性系统的Sim2Real校准同样具有工程参考价值,证明了在递归控制任务中显式建模不确定性与累积误差惩罚是提升仿真可信度的核心路径。
英文摘要 (Abstract)
Vehicle-in-the-loop (VIL) simulation requires a lateral dynamics model that accurately reproduces vehicle responses and reliably generates horizontal lateral-position and heading commands through recursive integration. This paper presents a probabilistic lateral motion prediction model with improved response fidelity. A two-degree-of-freedom vehicle model provides the physical prior, while a recurrent neural network learns correlated residual corrections to lateral acceleration and yaw rate. To maintain prediction fidelity during recursive motion generation, multistep rollout training feeds corrected responses into subsequent states and histories and directly penalizes accumulated lateral-velocity error. A conditional Gaussian characterizes response uncertainty, which is propagated to lateral-response, position, and heading predictions through augmented-state linearization. Evaluation results demonstrate improved lateral-response and integrated-motion prediction. Compared with the Deep Dynamics lateral adaptation, the proposed model reduces mean lateral-position root-mean-square error (RMSE) from 0.596 m to 0.483 m, an improvement of 19.0%, while reducing mean lateral-velocity RMSE from 0.0469 m/s to 0.0441 m/s. These results demonstrate the effectiveness of combining physical priors, probabilistic residual learning, and multistep rollout training for response-faithful lateral motion prediction.
作者:Xiangyang Ye, Chaosheng Huang, Jinwen Yang, Zhengxian Chen, Jun Li
外部来源
本页事实对应的公开页面,以原文为准。(点击将离开本站)