arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

International Conference on Intelligent Robots and Systems · 会议 · Robotics

2026-07-01 至 2026-07-01 共收录 4
2604.04138 2026-07-01 cs.RO cs.AI 版本更新

Learning Dexterous Grasping from Sparse Taxonomy Guidance

从稀疏分类学指导中学习灵巧抓取

Juhan Park, Taerim Yoon, Seungmin Kim, Joong-Gil Kim, Wontae Ye, Jeongeun Park, Yoonbyung Chai, Geonwoo Cho, Geunwoo Cho, Dohyeong Kim, Kyungjae Lee, Yong-Jae Kim, Sungjoon Choi

机构 * Korea University(高丽大学) Korea University of Technology and Education(韩国技术教育大学) Naver AI Lab(Naver AI 实验室) Seoul National University(首尔大学) WIRobotics RLWRLD

AI总结 GRIT框架通过稀疏分类学指导学习灵巧抓取,提升对新物体的泛化能力,实现87.9%的成功率,并通过高阶分类学选择实现抓取策略的可控性。

Comments IROS 2026 accepted

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.13844 2026-07-01 cs.RO 版本更新

LDHP: Library-Driven Hierarchical Planning for Non-prehensile Dexterous Manipulation

LDHP:基于库的非抓取灵巧操作分层规划

Tierui He, Jiahui Zuo, Fumin Zhang, Chao Zhao

AI总结 提出库驱动分层规划器LDHP,通过顶层接触状态规划器与底层抓取规划器协同,实现非抓取操作的可执行性,在零自由度提升和槽插入任务中验证了鲁棒性。

Comments 8 pages,accepted by IROS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.07939 2026-07-01 cs.RO physics.flu-dyn 版本更新

Unified Structural-Hydrodynamic Modeling of Underwater Underactuated Mechanisms and Soft Robots

水下欠驱动机构与软体机器人的统一结构-水动力学建模

Chenrui Zhang, Yiyuan Zhang, Yunfei Ye, Junkai Chen, Haozhe Wang, Cecilia Laschi

机构 * Department of Mechanical Engineering and Advanced Robotics Centre, National University of Singapore(新加坡国立大学机械工程系与先进机器人中心) Singapore-MIT Alliance for Research and Technology (SMART) Centre(新加坡-麻省理工学院研究与技术联盟中心)

AI总结 提出一种轨迹驱动的全局优化框架,基于CMA-ES同时识别弹性、阻尼和分布式水动力学参数,实现水下欠驱动机构和软体机器人的高保真建模,仅需单段视频。

Comments The first two listed authors contributed equally. Yiyuan Zhang is the corresponding author. This paper has been accepted to the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.15614 2026-07-01 cs.RO 版本更新

AION: Aerial Indoor Object-Goal Navigation Using Dual-Policy Reinforcement Learning

AION: 基于双策略强化学习的空中室内目标导航

Zichen Yan, Yuchen Hou, Shenao Wang, Yichao Gao, Rui Huang, Lin Zhao

机构 * Department of Electrical and Computer Engineering, National University of Singapore(新加坡国立大学电子与计算机工程系)

AI总结 提出AION,一种端到端双策略强化学习框架,解耦探索与目标到达行为,用于视觉空中目标导航,无需外部定位或全局地图,在AI2-THOR和IsaacSim中验证了优越性能。

Comments Accepted to IROS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏