自适应重规划减少计算开销，提升机器人控制效率
AdaReP:Adaptive Re-Planning under Model Mismatch for Neural World-Model Predictive Control
- 基于动态误差传播分析，在线调整重规划频率
- 物理实验中减少80%以上计划查询次数，性能相当
- 无需训练，可无缝集成到现有神经世界模型系统
神经世界模型结合模型预测控制（MPC）在每一步环境交互中重规划，以限制累积预测误差，但带来显著计算开销。复用缓存计划可降低开销，但其有效性取决于预测偏差在局部动态中的传播方式。本文通过扰动驱动的动态遗憾框架分析该权衡，发现过时计划惩罚与重规划容忍度、自上次重规划以来的累积误差及局部动态敏感性呈正相关。基于此结构，提出AdaReP——一种无需训练的封装方法，利用当前轨迹偏差和局部敏感性估计，动态调整重规划阈值，不修改已学习的世界模型或规划器。在图像空间规划、隐空间控制及真实机器人操作任务中，AdaReP显著降低规划端计算量，同时保持相近任务表现，包括在50次物理机器人实验中减少超过80%的查询次数。
原文摘要 · Abstract (English)
Neural world models coupled with model predictive control (MPC) replan at every environment step to bound accumulated prediction error, but this incurs substantial computational overhead. Reusing a cached plan reduces this overhead, yet its effectiveness depends on how prediction mismatch propagates through the local dynamics. We analyze this trade-off with a perturbation-based dynamic-regret framework and show that stale-plan penalties scale with the reuse tolerance, the accumulated mismatch since the last replanning step, and the local dynamics sensitivity. Based on this structure, we propose AdaReP, a training-free wrapper that adapts the replanning tolerance online using the current deviation from the cached rollout and a local sensitivity estimate, without modifying the learned world model or planner. Across image-space planning, latent-space control, and real-world robotic manipulation, AdaReP substantially reduces planner-side computation while maintaining comparable task performance, including over 80% fewer queries on a 50-trial physical robot study.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。