外观
论文arXiv 2610.1406421 天前
我的样本有帮助吗？面向接触丰富操作中真实世界采样式MPC的计算预算分配
原文链接：Do My Samples Help? Compute Budget Allocation for Real-World Sampling-Based MPC in Contact-Rich Manipulation（arXiv 2610.14064 · 发布日期：2026-10-07）
Do My Samples Help? Compute Budget Allocation for Real-World Sampling-Based MPC in Contact-Rich Manipulation
研究接触丰富操作中SMPC固定计算预算分配，提出BAMPC，并在仿真与真机三项任务验证。
核心要点
- GPU物理仿真让SMPC可实时评估大量非可微接触rollout，但计算预算有限且权衡不清。
- BAMPC基于MuJoCo Warp，将动力学不确定性、状态不确定性和时间对齐作为独立预算维度。
- 框架在仿真和真实机器人上使用相同控制栈，以支持受控的sim-to-real比较。
- 三项任务显示最佳预算取决于主导sim-to-real误差，动力学随机化并非总是最有效。
验证范围与局限：验证范围为仿真和一台真实机器人上的三项接触丰富操作任务。
英文摘要 (Abstract)
Sampling-based model predictive control (SMPC) is increasingly practical for contact-rich manipulation because GPU-based physics simulators enable real-time evaluation of large numbers of non-differentiable contact rollouts. However, this computation budget is finite and can be spent in competing ways, including denser control exploration, representing dynamics or state uncertainty, replanning more frequently, or aligning the simulation better with the physical state. Yet, the resulting trade-offs are not well understood in real-world sim-to-real control. In this work, we address this question through a systematic study of how to allocate a fixed computation budget for SMPC in contact-rich manipulation. To enable controlled comparisons, we develop a GPU-based framework named Budget-Allocating Model Predictive Control (BAMPC), which runs on MuJoCo Warp and exposes dynamics uncertainty, state uncertainty, and temporal alignment as independent dimensions of the computation budget while using the same control stack in simulation and on a real robot. Across three contact-rich manipulation tasks, we find that the best budget allocation depends on the dominant sim-to-real error, with dynamics randomization not universally the most effective one.
作者：Magnus Dierking, João Carvalho, Vince Kurtz, Jan Peters, Nils Dengler, Georgia Chalvatzaki
来源
本页事实对应的公开页面，以原文为准。