通过智能强化学习在机器人操作中学习鲁棒执行

中文摘要 AI 辅助

机器人操作因不确定性、长期执行和复合误差面临根本挑战，易导致执行不稳定和任务失败。近期视觉语言动作（VLA）模型虽有强泛化能力，但缺乏评估执行稳定性及恢复偏离标称行为的机制。本文提出两个互补指标评估运行时执行质量，以及一个智能强化学习框架，通过高级决策恢复有效执行。该框架基于执行历史推理并选择执行模式调节执行过程，执行退化时触发恢复机制使任务继续。在LIBERO基准测试中评估，标准设置下成功率提高达13.7%，干扰设置下提高达39.2%，显著增强了执行鲁棒性。

英文摘要

Robotic manipulation poses fundamental challenges due to uncertainty, long-horizon execution, and compounding errors, which can easily destabilize execution and lead to task failure. Although recent vision-language-action (VLA) models exhibit strong generalization, they typically lack explicit mechanisms to assess execution stability and to recover when execution deviates from its nominal behavior. In this paper, we propose: (1) two complementary metrics to assess execution quality at runtime, and (2) an agentic reinforcement learning framework that learns to restore effective execution through high-level decision-making rather than directly learning low-level actions. In this framework, an agentic policy reasons over recent execution history and selects among a small set of execution modes to regulate the execution process. Under execution degradation, it triggers appropriate recovery mechanisms to restore the robot to previously visited nominal states, enabling the task to continue. We evaluate the proposed method on the LIBERO benchmark, achieving up to a 13.7% improvement in success rate under standard settings and up to a 39.2% improvement under disturbance settings, demonstrating substantially enhanced execution robustness.

发表机构

• School of Inteligence Science and Engineering, the Harbin Institute of Technology Shenzhen（哈尔滨工业大学（深圳）智能科学与工程学院）
• Faculty of Robot Science and Engineering, Northeastern University（东北大学机器人科学与工程学院）

机构由 AI 辅助整理，请以论文原文为准。