arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

期刊&会议

International Conference on Robotics and Automation · 会议 · Robotics

2026-04-02 至 2026-04-02 共收录 5
2604.00744 2026-04-02 cs.RO

How to Train your Tactile Model: Tactile Perception with Multi-fingered Robot Hands

如何训练你的触觉模型:多指机械手的触觉感知

Christopher J. Ford, Kaichen Shi, Laura Butcher, Nathan F. Lepora, Efi Psomopoulou

机构 * Bristol Robotics Laboratory, University of Bristol(布里斯托大学布里斯托机器人实验室)

AI总结 本文提出TacViT模型,基于视觉Transformer实现触觉感知,能有效泛化新传感器数据,减少数据收集和重训练需求,提升多指机械手的触觉感知能力。

Comments Accepted for publication at the International Conference on Robotics and Automation (ICRA) 2026, Vienna

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.00738 2026-04-02 cs.RO

SoftHand Model-W: A 3D-Printed, Anthropomorphic, Underactuated Robot Hand with Integrated Wrist and Carpal Tunnel

SoftHand Model-W: 一种3D打印的拟人化欠驱动机器人手,集成腕关节和腕管机制

Dhillon B. Merritt, Christopher J. Ford, Haoran Li, Malia Smith, Zhixing Chen, Efi Psomopoulou, Nathan F. Lepora

机构 * Bristol Robotics Laboratory, University of Bristol(布里斯托大学布里斯托机器人实验室)

AI总结 SoftHand Model-W通过集成腕关节和腕管机制,实现了五指主动屈伸及掌部主动屈伸和桡侧/尺侧偏移,展示了近端自由度在现实机器人应用中实现多样化、类人操作的关键作用。

Comments Accepted for publication at the International Conference of Robotics and Automation (ICRA) 2026, Vienna

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.00496 2026-04-02 eess.SY cs.SY

The QuadSoft: Design, Construction, and Experimental Validation of a Soft and Actuated Quadrotor

QuadSoft:一种软体和驱动四旋翼的设计、构造与实验验证

Rodolfo Verdin, Hugo Moreno, Mark W. Spong, Gerardo Flores

AI总结 本文提出QuadSoft,一种具有连续曲率腱驱动软体机械臂的全驱动四旋翼,通过半刚性中央框架与柔性臂的结合,实现飞行中可控结构重构。实验验证了其在户外稳定飞行、悬停、方向操控和降落的能力,展示了软体机械臂在保持高度的同时可产生水平位移。

Comments Accepted for publication in the IEEE International Conference on Robotics and Automation (ICRA 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.24212 2026-04-02 cs.RO cs.CV

RANGER: A Monocular Zero-Shot Semantic Navigation Framework through Visual Contextual Adaptation

RANGER:通过视觉上下文适应的单目零样本语义导航框架

Ming-Ming Yu, Yi Chen, Börje F. Karlsson, Wenjun Wu

机构 * Beihang University(北京航空航天大学) Beijing Academy of Artificial Intelligence(北京人工智能研究院) Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所) Hangzhou International Innovation Institute, Beihang University(北京航空航天大学杭州国际创新研究院)

AI总结 RANGER通过视觉上下文学习实现零样本语义导航,无需依赖深度和姿态信息,利用3D基础模型和视觉语言模型提升任务效率与环境适应性。

Comments Accepted at ICRA 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.16483 2026-04-02 cs.CV

Octree Diffusion for Semantic Scene Generation and Completion

八叉树扩散用于语义场景生成与补全

Xujia Zhang, Brendan Crowe, Christoffer Heckman

机构 * University of Colorado Boulder(科罗拉多大学博尔德分校) Autonomous Robotics and Perception Group(自主机器人与感知实验室)

AI总结 本文提出Octree Latent Semantic Diffusion框架,通过八叉树隐式表示实现跨域的3D语义场景补全、扩展和生成,结合结构扩散与语义扩散生成语义标签,无需重训练即可完成单扫描的补全与零样本泛化。

Comments Accepted to ICRA 2026. Revised version with updated paragraphs

Journal ref Proceedings of the 2026 IEEE International Conference on Robotics and Automation (ICRA)

详情

展开后加载摘要…

URL PDF HTML 收藏