让机器人持续学习新技能而不忘记旧技能，避免灾难性遗忘。
Lifelong Language-Conditioned Robotic Manipulation Learning
- 通过技能适应机制保留旧知识，共享新旧技能共性。
- 用奇异值分解提取技能语义子空间，记录核心语义信息。
- 适合需要长期学习新任务的机器人应用场景。
传统语言条件下的机器人操作代理在连续学习新技能时，容易导致旧技能的灾难性遗忘，限制了动态场景的实际部署。本文提出SkillsCrafter框架，一种新型机器人操作学习方法，可持续学习多种技能并减少对旧技能的遗忘。具体而言，我们设计了操作技能适应机制，在保留旧技能知识的同时，继承新旧技能间的共享知识，以促进新技能的学习；同时，对多样化的技能指令进行奇异值分解，获得通用技能语义子空间投影矩阵，从而记录技能的本质语义空间。为实现无遗忘且具备泛化能力的操作，我们提出技能专业化聚合方法，计算技能语义子空间中的技能间相似性，实现对先前学习技能知识的聚合，以应对任何新或未知技能。大量实验验证了所提SkillsCrafter的有效性和优越性。
原文摘要 · Abstract (English)
Traditional language-conditioned manipulation agent sequential adaptation to new manipulation skills leads to catastrophic forgetting of old skills, limiting dynamic scene practical deployment. In this paper, we propose SkillsCrafter, a novel robotic manipulation framework designed to continually learn multiple skills while reducing catastrophic forgetting of old skills. Specifically, we propose a Manipulation Skills Adaptation to retain the old skills knowledge while inheriting the shared knowledge between new and old skills to facilitate learning of new skills. Meanwhile, we perform the singular value decomposition on the diverse skill instructions to obtain common skill semantic subspace projection matrices, thereby recording the essential semantic space of skills. To achieve forget-less and generalization manipulation, we propose a Skills Specialization Aggregation to compute inter-skills similarity in skill semantic subspaces, achieving aggregation of the previously learned skill knowledge for any new or unknown skill. Extensive experiments demonstrate the effectiveness and superiority of our proposed SkillsCrafter.
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。