ViReSkill：面向终身机器人学习中基于 LLM 规划的、结合视觉锚定重规划与技能记忆的方法
ViReSkill: Vision-Grounded Replanning with Skill Memory for LLM-Based Planning in Lifelong Robot Learning
AI总结：
针对 LLM/VLM 机器人规划缺乏物理场景锚定且输出不稳定的问题，本文提出 ViReSkill，通过视觉条件重规划和可复用技能记忆实现终身学习，并在仿真与实体机器人上验证了更高成功率。
摘要：
通过强化学习（RL）或模仿学习（IL）训练的机器人往往难以快速适应新任务，而近期的大型语言模型（LLM）和视觉-语言模型（VLM）有望利用极少数据提供知识丰富的规划。然而，将 LLM/VLM 用于运动规划面临两个关键障碍：（i）符号化规划很少与场景几何和物体物理属性建立锚定；（ii）对于完全相同的提示，模型输出可能发生变化，从而削弱执行可靠性。我们提出 ViReSkill，这是一个将视觉锚定重规划与用于积累和复用的技能记忆相结合的框架。当发生失败时，重规划器会以当前场景为条件生成新的动作序列，并针对观测到的状态进行定制。成功时，已执行的规划会被存储为可复用技能，并在未来遇到相同情况时重放，无需额外调用 LLM/VLM。这一反馈回路实现了自主持续学习：每一次尝试都会立即扩展技能集，并稳定后续执行。我们在 LIBERO、RLBench 等模拟器以及实体机器人上评估了 ViReSkill。在所有设置中，它在任务成功率上均持续优于传统基线，展示出稳健的仿真到真实泛化能力。
英文摘要：
Robots trained via Reinforcement Learning (RL) or Imitation Learning (IL) often adapt slowly to new tasks, whereas recent Large Language Models (LLMs) and Vision-Language Models (VLMs) promise knowledge-rich planning from minimal data. Deploying LLMs/VLMs for motion planning, however, faces two key obstacles: (i) symbolic plans are rarely grounded in scene geometry and object physics, and (ii) model outputs can vary for identical prompts, undermining execution reliability. We propose ViReSkill, a framework that pairs vision-grounded replanning with a skill memory for accumulation and reuse. When a failure occurs, the replanner generates a new action sequence conditioned on the current scene, tailored to the observed state. On success, the executed plan is stored as a reusable skill and replayed in future encounters without additional calls to LLMs/VLMs. This feedback loop enables autonomous continual learning: each attempt immediately expands the skill set and stabilizes subsequent executions. We evaluate ViReSkill on simulators such as LIBERO and RLBench as well as on a physical robot. Across all settings, it consistently outperforms conventional baselines in task success rate, demonstrating robust sim-to-real generalization.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
