提出可组合技能框架，让机器人持续学新任务不丢旧技能。
Learning New Tasks via Reusable Skills: Skill-Compositional Experts for Embodied Continual Learning
- 用可组合技能分解演示，构建可复用技能库
- 双分支设计保证技能执行与衔接，减少遗忘
- 在真实机械臂任务中显著提升持续学习表现
具身持续学习（ECL）旨在让机器人在闭环控制下持续学习新操作任务，同时保留已有行为。与传统持续学习相比，ECL面临更严重的灾难性遗忘问题，闭环控制下的特征漂移会逐步传播，导致旧技能退化。核心挑战在于如何在不断演化的任务中结构化地复用技能，现有方法多关注技能学习，却未显式组织以实现连贯任务执行。为此，我们提出技能组合专家框架（SCE）。SCE通过组合式技能接地（CSG）将任务示范分解为可复用技能，构建技能库；基于此，双执行-过渡专家（DETE）通过两分支实现新任务学习：一分支保障技能执行，另一分支支持技能间过渡，确保行为连贯。在LIBERO基准和真实世界操作任务上的实验表明，SCE持续提升记忆保留与整体任务性能。特征漂移分析与消融研究进一步验证了方法的有效性。
原文摘要 · Abstract (English)
Embodied Continual Learning (ECL) aims to enable robots to continually acquire new manipulation tasks while retaining previously learned behaviors under closed-loop control. Compared with conventional continual learning, ECL suffers from more severe catastrophic forgetting. Feature drift accumulated under closed-loop control progressively propagates through sequential decision-making, leading to degradation of previously learned behaviors. A key challenge in ECL lies in structured skill reuse across continually evolving tasks, since existing methods primarily focus on skill learning without explicitly organizing them for coherent task execution. To address this issue, we propose SCE, a Skill-Compositional Experts framework for ECL. SCE builds a skill base via Compositional Skill Grounding (CSG), which decomposes task demonstrations into reusable skills. Based on this, Dual Execution-and-Transition Experts (DETE) enable new task learning through skill composition, where one branch ensures skill execution and the other supports transitions between skills for coherent behavior. Experiments on LIBERO benchmarks and real-world manipulation tasks demonstrate that SCE consistently improves retention and overall task performance. Further feature drift analyses and ablation studies verify the effectiveness of our method. Project website: https://eqcy.github.io/sce/.
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。