English(EN) Learning New Tasks via Reusable Skills: Skill-Compositional Experts for Embodied Continual Learning

机器人通过技能组合专家在保留旧任务的同时学习新任务

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-16 04:00

研究人员开发了一个名为SCE（技能组合专家）的新框架，以解决机器人具身持续学习中的灾难性遗忘问题。该框架将任务演示分解为可重用的技能，使机器人能够在保留旧任务的同时学习新的操作任务。在LIBERO基准和现实世界任务上的实验表明，SCE显著提高了性能和保留率。 AI

排序理由该集群包含一篇详细介绍具身持续学习新框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Shuaike Zhang, Shaokun Wang, Haoyu Tang, Jianlong Wu, Liqiang Nie · 2026-06-16 04:00

Learning New Tasks via Reusable Skills: Skill-Compositional Experts for Embodied Continual Learning

arXiv:2606.15685v1 Announce Type: cross Abstract: 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 suffe…