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

2026-04-01 至 2026-04-01 共收录 6
2603.30042 2026-04-01 cs.RO cs.HC

HapCompass: A Rotational Haptic Device for Contact-Rich Robotic Teleoperation

HapCompass:一种用于接触密集机器人远程操作的旋转触觉装置

Xiangshan Tan, Jingtian Ji, Tianchong Jiang, Pedro Lopes, Matthew R. Walter

机构 * Toyota Technological Institute at Chicago (TTIC)(丰田芝加哥技术研究所) University of Chicago(芝加哥大学)

AI总结 HapCompass通过机械旋转单个线性共振执行器提供2D方向提示,提升了远程操作任务的成功率、完成时间和最大接触力,同时改进了模仿学习的数据质量。

Comments Accepted to IEEE International Conference on Robotics and Automation (ICRA), 2026. 8 pages, 5 figures. Project page: https://ripl.github.io/HapCompass/

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.29708 2026-04-01 cs.RO cs.SY eess.SY math.DS

SafeDMPs: Integrating Formal Safety with DMPs for Adaptive HRI

SafeDMPs: 将形式安全性与DMPs结合以实现适应性人机交互

Soumyodipta Nath, Pranav Tiwari, Ravi Prakash

机构 * Indian Institute of Science(印度科学研究所)

AI总结 本文提出SafeDMPs框架,结合DMPs的高效动态鲁棒性与基于STTs的非优化控制律,实现安全、鲁棒且适应性强的人机交互。

Comments 8 pages, 8 figures and 1 table

Journal ref 2026 IEEE International Conference on Robotics and Automation

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.29419 2026-04-01 cs.RO cs.AI cs.CV

RAAP: Retrieval-Augmented Affordance Prediction with Cross-Image Action Alignment

RAAP:基于跨图像动作对齐的检索增强的可达性预测

Qiyuan Zhuang, He-Yang Xu, Yijun Wang, Xin-Yang Zhao, Yang-Yang Li, Xiu-Shen Wei

机构 * School of Computer Science and Engineering, and Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Southeast University(东南大学计算机科学与工程学院、新一代人工智能技术与交叉应用重点实验室) Southeast University-Monash University Joint Graduate School, Southeast University(东南大学-蒙纳士大学联合研究生院) School of Computer Science and Engineering, Nanjing University of Science and Technology(南京理工大学计算机科学与工程学院)

AI总结 RAAP通过结合检索与对齐学习,统一了可达性检索与动作方向预测,利用密集对应转移接触点并预测动作方向,实现了跨未见物体和类别的稳健泛化。

Comments Accepted to ICRA 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.14565 2026-04-01 cs.RO cs.AI

Masked IRL: LLM-Guided Reward Disambiguation from Demonstrations and Language

掩码逆强化学习:从演示和语言引导的奖励消歧

Minyoung Hwang, Alexandra Forsey-Smerek, Nathaniel Dennler, Andreea Bobu

机构 * MIT CSAIL(麻省理工学院计算机科学与人工智能实验室)

AI总结 本文提出掩码逆强化学习框架,利用大语言模型结合演示和语言信息,提升机器人奖励学习的样本效率和泛化能力。

Comments Accepted to ICRA 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.01250 2026-04-01 cs.CV

Source-Only Cross-Weather LiDAR via Geometry-Aware Point Drop

仅源域跨天气LiDAR点云几何感知

YoungJae Cheong, Jhonghyun An

机构 * School of Computing, Gachon University(嘉泉大学计算机学院)

AI总结 本文提出几何感知适配器,通过局部窗口KNN搜索和水平圆填充,提升LiDAR语义分割在恶劣天气下的鲁棒性,实现+3.4mIoU的提升。

Comments Accepted by ICRA 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2203.02381 2026-04-01 cs.RO

Where to Look Next: Learning Viewpoint Recommendations for Informative Trajectory Planning

下一步在哪里寻找:为信息轨迹规划学习视角推荐

Max Lodel, Bruno Brito, Álvaro Serra-Gómez, Laura Ferranti, Robert Babuška, Javier Alonso-Mora

机构 * Delft University of Technology(代尔夫特理工大学) Czech Technical University in Prague(捷克理工大学)

AI总结 本文提出一种基于深度强化学习的信息感知策略,用于指导递推时间 horizon轨迹优化规划器,以在动态可行且无碰撞的轨迹中最大化信息增益并减少环境不确定性。

Comments accepted to ICRA2022

Journal ref 2022 International Conference on Robotics and Automation (ICRA)

详情

展开后加载摘要…

URL PDF HTML 收藏