IEEE RA-L

SkillPlug: Unsupervised Skill Mining for Few-Shot Adaptation in Robotic Manipulation

SkillPlug：用于机器人操作中少样本适应的无监督技能挖掘

Zi-han Ding, Ziwei Wang

机构 * School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电气与电子工程学院） 纠错

AI总结 针对机器人操作中学习可转移视觉运动模仿策略的挑战，提出SkillPlug框架，通过技能调节模块挖掘共享可转移技能库，经自监督学习形成任务共享先验，微调轻量级组件实现少样本适应，提升多任务和少样本适应性能。

Comments 8 pages, 8 figures, published to RA-L

Journal ref IEEE Robotics and Automation Letters, vol. 11, no. 8, pp. 9511-9518, Aug. 2026

D-CLIPSE: Distributed Consensus-based Localization with Passive Listening on Shared State Exchange

D-CLIPSE：基于分布式共识的共享状态交换被动监听定位

Kyle Biron-Gricken, James Richard Forbes

AI总结 研究多机器人定位问题，提出基于分布式共识的滤波框架，通过共享预积分里程计和相关共享状态实现定位，在模拟和实验中验证，精度和一致性接近集中式方法，优于当前分散式方法。

Comments 8 pages, 7 figures, 1 table. Submitted to IEEE Robotics and Automation Letters