外观
论文arXiv 2610.1046521 天前
LLA-MPPI：利用 GPU 加速并行仿真实现腿式机器人快速自适应全身控制
LLA-MPPI通过选择GPU批量接触仿真器实现腿式机器人全身自适应控制，并在仿真任务和Unitree Go2上验证。
宇树 Go2原文链接：LLA-MPPI: Rapidly Adaptive Whole-body Control of Legged Robots with GPU-Accelerated Parallel Simulations（arXiv 2610.10465 · 发布日期：2026-10-07）
LLA-MPPI: Rapidly Adaptive Whole-body Control of Legged Robots with GPU-Accelerated Parallel Simulations
LLA-MPPI通过选择GPU批量接触仿真器实现腿式机器人全身自适应控制，并在仿真任务和Unitree Go2上验证。
核心要点
- 固定标称模型的实时全身控制在部署动力学变化时容易退化。
- 方法用窗口预测误差在GPU批量接触仿真器库中选择最能解释近期运动的模型。
- 选中模型供全身MPPI规划控制，无需离线训练，且所选假设具有物理可解释性。
- 四个仿真任务成功率为97.5%，硬件展示了负载变化、单腿失效和推箱增重场景；代码、视频和项目详情已公开。
验证范围与局限：验证范围为四个仿真任务和一台Unitree Go2上的硬件演示。
英文摘要 (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
作者：Sebin Jung, Maitham F. AL-Sunni, Juan Alvarez-Padilla, Zachary R. Manchester, Changliu Liu, John M. Dolan
来源
本页事实对应的公开页面，以原文为准。