让机器人实时根据反馈调整动作，不重训模型也能纠错。
ORPA: Online Residual Policy Adaptation for Robot Manipulation Control with Human Feedback
- 用轻量模块在运行时直接修正关节空间动作
- 在ALOHA平台测试中成功率提升，抗扰动能力更强
- 适合需要快速响应的精密操作场景
通过模仿学习训练的机器人操控策略（如基于Transformer的ACT）在理想条件下表现良好，但对微小执行误差和分布偏移敏感。传统纠错需收集数据并重新训练整个策略，计算成本高且无法实时部署。本文提出在线残差策略自适应（ORPA）框架，可在不修改原始策略参数的前提下，通过即时反馈驱动修正机器人动作。ORPA在预训练控制策略上增加一个轻量级、反馈条件化的模块，直接在关节空间预测残差修正量，实现实时行为调整。我们在ALOHA平台上评估了多个高精度操控任务，结果表明，相比基线控制策略和基于规则的逆运动学修正，ORPA显著提升了成功概率，并增强了对微小扰动的恢复能力。
原文摘要 · Abstract (English)
Robotic manipulation policies trained via imitation learning, such as Action Chunking with Transformers (ACT), can achieve strong performance under ideal conditions but often remain sensitive to small execution errors and distribution shifts. Correcting these failures typically requires dataset aggregation and full-policy retraining, which is computationally expensive and unsuitable for real-time deployment. In this work, we propose Online Residual Policy Adaptation (ORPA), a framework that enables immediate, feedback-driven correction of robot actions without modifying the underlying policy parameters. ORPA augments a pretrained control policy with a lightweight, feedback-conditioned module that predicts residual adjustments directly in joint space, allowing the system to adapt its behavior at runtime. We evaluate ORPA on a set of precision-sensitive manipulation tasks using the ALOHA platform, demonstrating improvements in success rate and recovery from small perturbations compared to baseline control policies and rule-based inverse kinematics corrections.
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。