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

2025-12-15 至 2025-12-15 共收录 3
2508.07606 2025-12-15 cs.RO

In-situ Value-aligned Human-Robot Interactions with Physical Constraints

原位价值对齐的人机交互与物理约束

Hongtao Li, Ziyuan Jiao, Xiaofeng Liu, Hangxin Liu, Zilong Zheng

机构 * College of Artificial Intelligence and Automation, Hohai University(人工智能与自动化学院,河海大学) State Key Laboratory of General Artificial Intelligence, BIGAI(通用人工智能国家重点实验室,BIGAI)

AI总结 本研究提出结合人类偏好与物理约束的框架,通过ICLHF方法实现任务计划生成与约束平衡,提升人机交互的效率与适应性。

Comments 8 pages, 7 figures. Accepted by IROS 2025

Journal ref 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.10284 2025-12-15 cs.RO cs.HC

From "Thumbs Up" to "10 out of 10": Reconsidering Scalar Feedback in Interactive Reinforcement Learning

从' thumbs up '到' 10 分之 10 ':重新考虑交互强化学习中的标量反馈

Hang Yu, Reuben M. Aronson, Katherine H. Allen, Elaine Schaertl Short

机构 * Tufts University School of Engineering, Computer Science(塔夫茨大学工程学院计算机科学系) Tufts University School of Engineering, Mechanical Engineering(塔夫茨大学工程学院机械工程系)

AI总结 本文提出STEADY方法,通过处理标量反馈提升机器人抓取任务中的学习效果,证明标量反馈在适当处理下对强化学习有益。

Journal ref IROS 2023

详情

展开后加载摘要…

URL PDF HTML 收藏
2107.08492 2025-12-15 cs.RO

SENSORIMOTOR GRAPH: Action-Conditioned Graph Neural Network for Learning Robotic Soft Hand Dynamics

传感器运动图:用于学习机器人柔性手动力学的动作条件图神经网络

João Damião Almeida, Paul Schydlo, Atabak Dehban, José Santos-Victor

AI总结 本文提出了一种基于图神经网络的传感器运动图模型,用于学习机器人柔性手的动力学,通过利用系统的组合性和顺序不变性,提升了动力学预测的准确性与鲁棒性。

Comments Accepted at 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021)

Journal ref IEEE Int. Conference on Intelligent Robots and Systems (IROS) 2021

详情

展开后加载摘要…

URL PDF HTML 收藏