arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

Robotics: Science and Systems · 会议 · Robotics

2026-06-04 至 2026-06-04 共收录 7
2602.12215 2026-06-04 cs.RO

LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion

LDA-1B:通过通用具身数据摄取扩展潜动力学动作模型

Jiangran Lyu, Kai Liu, Xuheng Zhang, Haoran Liao, Yusen Feng, Wenxuan Zhu, Tingrui Shen, Jiayi Chen, Jiazhao Zhang, Yifei Dong, Wenbo Cui, Senmao Qi, Shuo Wang, Yixin Zheng, Mi Yan, Xuesong Shi, Haoran Li, Dongbin Zhao, Ming-Yu Liu, Zhizheng Zhang, Li Yi, Yizhou Wang, He Wang

机构 * Peking University(北京大学) Galbot CASIA(中国科学院自动化研究所) BAAI(北京人工智能研究院) Tsinghua University(清华大学) Sun Yat-sen University(中山大学) NVIDIA

AI总结 提出LDA-1B机器人基础模型,通过统一格式的具身交互数据集EI-30k和结构化DINO潜空间中的动力学学习,联合建模动力学、策略和视觉预测,在接触丰富、灵巧和长时任务上分别提升高达21%、48%和23%。

Comments Accepted at RSS 2026, Project Page:https://pku-epic.github.io/LDA

详情

展开后加载摘要…

URL PDF HTML 收藏
1709.04906 2026-06-04 eess.SY cs.MA cs.RO cs.SY

On the interaction between Autonomous Mobility-on-Demand systems and the power network: models and coordination algorithms

关于自主出行-on-demand系统与电力网络相互作用:模型和协调算法

Federico Rossi, Ramon Iglesias, Mahnoosh Alizadeh, Marco Pavone

AI总结 本文研究了自主出行-on-demand系统与电力网络的相互作用,提出了一种模型来捕捉两者之间的耦合关系,并通过联合优化算法协调两个系统。

Comments Extended version of the paper presented at Robotics: Science and Systems XIV and accepted by TCNS. In Version 4, the body of the paper is largely rewritten for clarity and consistency, and new numerical simulations are presented. All source code is available (MIT) at https://dx.doi.org/10.5281/zenodo.3241651

详情

展开后加载摘要…

URL PDF HTML 收藏
1708.04790 2026-06-04 cs.RO cs.SY eess.SY

Evaluation of Human-Robot Collaboration Models for Fluent Operations in Industrial Tasks

工业任务中流畅操作的人机协作模型评估

Lior Sayfeld, Ygal Peretz, Roy Someshwar, Yael Edan

AI总结 本文评估了人机协作模型在工业任务中的性能,比较了基于定时和传感器的模型与自适应模型,发现自适应模型在总装配时间和空闲时间上有显著提升。

Comments Robotics: Science and Systems, Human-Robot Hand-Over Workshop 2015

详情

展开后加载摘要…

URL PDF HTML 收藏
1707.03092 2026-06-04 eess.SY cs.LG cs.RO cs.SY

A Separation-Based Design to Data-Driven Control for Large-Scale Partially Observed Systems

基于分离的设计到数据驱动控制用于大规模部分观测系统

Dan Yu, Mohammadhussein Rafieisakhaei, Suman Chakravorty

AI总结 本文研究了由偏微分方程(PDE)描述的状态动力学导致的 partially observed 随机最优控制问题,通过黑盒模拟模型求解开环确定性轨迹优化问题,并基于输入输出实验数据设计线性二次高斯控制器。

Comments 3 pages, 6 figures, In Robotics: Science and Systems (RSS) 2017 Workshop of "POMDPs in Robotics: State of The Art, Challenges, and Opportunities"

详情

展开后加载摘要…

URL PDF HTML 收藏
1705.09415 2026-06-04 cs.RO cs.SY eess.SY

Near-Optimal Belief Space Planning via T-LQG

通过T-LQG实现接近最优的信念空间规划

Mohammadhussein Rafieisakhaei, Suman Chakravorty, P. R. Kumar

AI总结 本文提出T-LQG方法,用于非线性机器人系统在观测和运动不确定性下的规划问题,提供近优反馈控制策略,解决POMDP问题。

Comments 3 pages, 3 figures, In Robotics: Science and Systems (RSS) 2017 Workshop of "POMDPs in Robotics: State of The Art, Challenges, and Opportunities"

详情

展开后加载摘要…

URL PDF HTML 收藏
1702.02453 2026-06-04 cs.LG cs.RO cs.SY eess.SY

Preparing for the Unknown: Learning a Universal Policy with Online System Identification

为未知做准备:学习通用策略与在线系统识别

Wenhao Yu, Jie Tan, C. Karen Liu, Greg Turk

AI总结 本文提出了一种学习通用策略的方法,通过在线系统识别和大量训练示例,使策略在未知动态模型下具备鲁棒性,适用于多种动态模型和环境变化。

Comments Accepted as a conference paper at RSS 2017

详情

展开后加载摘要…

URL PDF HTML 收藏
1404.7073 2026-06-04 eess.SY cs.LG cs.LO cs.RO cs.SY

Probably Approximately Correct MDP Learning and Control With Temporal Logic Constraints

在时序逻辑约束下进行近似正确马尔可夫决策过程的学习与控制

Jie Fu, Ufuk Topcu

AI总结 本文提出在未知随机环境中,基于PAC-MDP方法学习满足时序逻辑规范的近优控制策略,通过多项式时间与空间复杂度实现高概率的近优策略生成。

Comments 9 pages, 5 figures, Accepted by 2014 Robotics: Science and Systems (RSS)

详情

展开后加载摘要…

URL PDF HTML 收藏