LLA-MPPI:基于 GPU 加速并行仿真的快速自适应腿足机器人全身控制
LLA-MPPI: Rapidly Adaptive Whole-body Control of Legged Robots with GPU-Accelerated Parallel Simulations
Sebin Jung · Maitham F. AL-Sunni · Juan Alvarez-Padilla · Zachary Manchester · Changliu Liu · John M. Dolan
中文摘要
针对腿足机器人的实时全身控制器通常依赖固定的标称模型进行规划,当实际动力学发生变化时性能会下降。现有自适应方法往往要求模型具有接触动力学无法提供的结构,或者需要针对每种预期条件单独进行离线训练。本文提出 LLA-MPPI(回溯与前瞻自适应模型预测路径积分控制)。该方法将全身自适应问题转化为在一组 GPU 批处理接触仿真器之间的选择,各仿真器具有不同的物理或结构参数。窗口化预测误差用于挑选最能解释近期运动的仿真器;全身 MPPI 规划器在该选定模型上优化控制。框架不需要任何离线训练,所选假设具备物理可解释性。在四个仿真任务中,该方法达到 97.5% 的成功率,而最强基线为 74%,拥有真实模型的 oracle 达到 98.5%。在 Unitree Go2 平台上的硬件验证显示:机器人在运行中增加负载可继续行走;在一条腿失能后仍能行走;并能在运行中持续增加所推箱子的质量将其送达目标位置。
关键要点
- 01问题:实时全身控制器依赖固定标称模型,动力学变化时性能退化;现有自适应方法要么依赖接触动力学难以提供的结构,要么需要针对每种条件做离线训练
- 02方法:把全身自适应转化为在一组具有不同物理/结构参数的 GPU 批处理接触仿真器之间进行选择,窗口化预测误差挑选最佳匹配模型,再由全身 MPPI 在其上规划
- 03结果:在四个仿真任务上达到 97.5% 成功率,优于最强基线的 74%,接近 oracle 的 98.5%;无需任何离线训练,所选假设物理可解释
- 04硬件验证:在 Unitree Go2 上验证了运行中增加负载、单腿失能后行走、运行中持续增加箱子质量并推到目标等场景
- 05作者:Sebin Jung、Maitham F. AL-Sunni、Juan Alvarez-Padilla、Zachary Manchester、Changliu Liu、John M. Dolan
解读
尚无解读。
原始英文摘要
arXiv:2610.10465v1 Announce Type: new Abstract: Real-time whole-body controllers for legged robots typically plan through a fixed nominal model and degrade when the deployed dynamics change. Adaptive methods typically require a model structure that contact dynamics do not provide, or they need offline training for each anticipated condition. We present Look-back and Look-ahead Adaptive Model Predictive Path Integral control (LLA-MPPI). The method converts whole-body adaptation into selection over a bank of GPU-batched contact simulators with different physical or structural parameters. Windowed prediction errors select the simulator that best explains recent motion. A whole-body MPPI planner optimizes controls through the selected model. The framework requires no offline training, and its selected hypotheses are physically interpretable. Across four simulated tasks, it achieves 97.5% success while the strongest baseline reaches 74% and an oracle with the true model reaches 98.5%. Hardware validation on a Unitree Go2 shows the robot walking under a payload added mid-run, walking after one leg is disabled, and pushing a box to its goal while increasing its mass on the fly. Code, videos, and project details are available at: https://lla-control.github.io