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

2026-06-23 至 2026-06-23 共收录 16
2606.23312 2026-06-23 cs.RO 新提交

From Pixels to Concepts: Growing Rich 3D Semantic Scene Graph Forests utilizing Foundation Models

从像素到概念:利用基础模型构建丰富的3D语义场景图森林

David Oberacker, Meike Deitersen, Niklas Spielbauer, Tristan Schnell, Georg Heppner, Arne Roennau

机构 * FZI Research Center for Information Technology(FZI信息技术研究中心) Machine Intelligence and Robotics Lab (MaiRo), Karlsruhe Institute for Technology (KIT)(卡尔斯鲁厄理工学院机器智能与机器人实验室)

AI总结 提出利用基础模型构建具有开放语义关系的3D场景图森林,通过VLM和LLM推理抽象概念节点与关系,提升机器人场景理解与任务执行能力。

Comments To be published in the Proceedings of the IEEE/RSJ International Conference on Intelligent Robots & Systems (IEEE IROS 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.22838 2026-06-23 cs.RO 新提交

FPAS: Frontier-Based Path Planning with Adaptive Sampling for Large-Scale Unknown Environments

FPAS:基于前沿的自适应采样路径规划用于大规模未知环境

Jinwoo Choi, Yeonkyu Lee, Jung-Taak Kim, Jisung Bae, Seung-Woo Seo

机构 * Seoul National University(首尔大学)

AI总结 提出FPAS框架,通过前沿概念引导目标导向任务,并基于前沿开放度自适应采样,在保持高目标到达性能的同时显著提升计算效率。

Comments IROS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.22471 2026-06-23 cs.RO 新提交

Scalable Multi-Task Data Generation via Reinforcement Learning for Language-Conditioned Bimanual Dexterous Manipulation

基于强化学习的可扩展多任务数据生成用于语言条件双手灵巧操作

Zechu Li, Yufeng Jin, Puze Liu, Jan Peters, Georgia Chalvatzaki

机构 * TU Darmstadt(达姆施塔特工业大学) Honda Research Institute Europe GmbH(本田欧洲研究院有限公司) DFKI(德国人工智能研究中心)

AI总结 提出基于强化学习的系统化数据生成流程,结合通用奖励设计、域随机化和语言条件任务标注,合成高质量双手灵巧操作数据集,训练语言条件多任务策略,提升跨任务泛化能力。

Journal ref IROS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.22116 2026-06-23 cs.RO 新提交

DeformX: A Versatile Co-Simulation Framework for Deformable Linear Objects

DeformX: 一种用于可变形线性物体的多功能协同仿真框架

Yi Yang, Xiang Fei, Lehong Wang, Chenhao Li, Zilin Dai, Henry Kou, Lu Li, Howie Choset

机构 * The Robotics Institute, Carnegie Mellon University(卡内基梅隆大学机器人研究所) Department of Mechanical Engineering, Carnegie Mellon University(卡内基梅隆大学机械工程系) School of Ocean and Civil Engineering, Shanghai Jiao Tong University(上海交通大学海洋与土木工程学院) Zhiyuan College, Shanghai Jiao Tong University(上海交通大学致远学院) John A. Paulson School of Engineering and Applied Sciences, Harvard University(哈佛大学约翰·A·保尔森工程与应用科学学院)

AI总结 提出DeformX框架,集成Cosserat杆物理引擎与NVIDIA Isaac Sim,实现可变形线性物体的物理精确与视觉真实仿真,支持机器人学习,在真实线缆分割和绳索摆动任务中验证了仿真到现实的迁移能力。

Comments 11 pages, 11 figures, 5 tables, IROS 2026. Website: https://deformx.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.21935 2026-06-23 cs.RO 新提交

CoRDE: Concept-Prior Routed Diffusion Experts for Structural Generalization in Robot Manipulation

CoRDE:面向机器人操作结构泛化的概念先验路由扩散专家

Haidong Huang, Xixin Zhao, Yaohua Zhou, Jiayu Song, Jiayi Zhang, Jun Ma, Haiyue Zhu, Xiaocong Li

机构 * College of Information Science and Technology, Eastern Institute of Technology, Ningbo(宁波东方理工大学(暂名)信息科学与技术学院) Zhejiang Key Laboratory of Industrial Intelligence and Digital Twin, Eastern Institute of Technology, Ningbo(浙江省工业智能与数字孪生重点实验室,宁波东方理工大学(暂名)) Department of Electrical and Computer Engineering, National University of Singapore(新加坡国立大学电气与计算机工程系) Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)机器人与自主系统学域) Faculty of Science and Engineering, University of Nottingham Ningbo China(宁波诺丁汉大学理工学院)

AI总结 提出CoRDE框架,通过概念先验引导路由和低秩专家池,解决扩散模型在多任务长时程操作中的结构泛化不足和路由崩溃问题。

Comments 8 pages, 3 figures, Accepted to the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.21866 2026-06-23 cs.RO 新提交

SurGE: Surrogate Gradient-guided Evolution for Co-design of Legged Robots with Parallel Elasticity

SurGE: 基于代理梯度引导的并行弹性腿式机器人协同设计进化

Yulun Zhuang, Yue Qin, Justin Lu, Zelin Shen, Yichen Wang, Sicheng He, Yanran Ding

机构 * University of Michigan, Ann Arbor(密歇根大学安娜堡分校) University of Tennessee, Knoxville(田纳西大学诺克斯维尔分校)

AI总结 提出SurGE框架,通过可微运动动力学模型和设计感知控制策略计算代理梯度,并注入CMA-ES实现非可微协同设计,在跳跃机器人上降低37.65%的设计目标。

Comments 8 pages, 7 figures. Accepted for publication at IROS 2026. Website at https://arcad-lab-um.github.io/surge-codesign/

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.21792 2026-06-23 cs.RO cs.AI 新提交

THREAD: Trajectory Planning for Hybrid Rigid-Soft Manipulators with Environment-Aware Diffusion

THREAD: 面向混合刚柔机械臂的环境感知扩散轨迹规划

Shivani Kamtikar, Pranav Asthana, Naveen Kumar Uppalapati, Girish Krishnan, Girish Chowdhary

机构 * University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) University of Maryland College Park(马里兰大学帕克分校)

AI总结 提出首个基于扩散的混合刚柔机械臂轨迹规划器THREAD,通过物理启发损失联合约束刚柔段,实现狭窄环境穿行,任务成功率92.4%,碰撞减少5倍。

Comments Project Page: https://robot-thread.github.io, IROS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.21737 2026-06-23 cs.RO 新提交

Programmable magnetic soft robots with controlled locomotion and directional liquid cargo release

可编程磁控软体机器人:可控运动与定向液体货物释放

Youyi Zhou, Zoe Evelyn Gureno, Meghna Majumder, Yunus Alapan

机构 * Bio-integrated Robotics Lab at Mechanical Engineering(机械工程系生物集成机器人实验室) University of Wisconsin - Madison(威斯康星大学麦迪逊分校)

AI总结 提出一种优化磁化分布策略,实现磁控软体机器人的定向液体释放,同时保持形状变形和运动能力,为胃肠道靶向药物递送奠定基础。

Comments This manuscript 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
2606.21594 2026-06-23 cs.CV cs.RO 新提交

Boundary-by-Mask: Few-Shot Instance Segmentation with Mask-Conditioned Boundary Learning for Texture-Poor Industrial Parts

Boundary-by-Mask: 基于掩码条件边界学习的少样本实例分割用于弱纹理工业零件

Yutaka Yoshinaga, Naoya Chiba, Koichi Hashimoto

机构 * Graduate School of Information Sciences, Tohoku University(东北大学信息科学研究科) Cybermedia Center, Osaka University(大阪大学网络媒体中心)

AI总结 提出Boundary-by-Mask框架,通过监督边界而非内部外观,利用基础模型编码器和轻量级SDF头实现弱纹理工业零件的少样本实例分割,支持灵活定义实例目标。

Comments 8 pages, 8 figures, accepted to IROS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.21258 2026-06-23 cs.RO cs.CV 新提交

Spectral GS-SLAM: Observability-Aware, Degeneracy-Robust Tracking for Real-Time 3D Gaussian Splatting SLAM

Spectral GS-SLAM:面向实时3D高斯泼溅SLAM的可观测性感知与退化鲁棒跟踪

Edward Beng Wai Tan, Siew-Kei Lam, Dongshuo Zhang

机构 * College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算机与数据科学学院)

AI总结 提出Spectral GS-SLAM,通过自适应补偿退化场景中的欠约束方向,结合ICP与特征约束实现鲁棒跟踪,并利用高斯感知平面性加权机制融合几何信息,在无结构/纹理环境中保持实时性能(40.14 FPS)。

Comments This work has been accepted to IROS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.21100 2026-06-23 cs.RO 新提交

Factor-Aware Mixture-of-Experts with Pretrained Encoder for Combinatorial Generalization

面向组合泛化的因子感知混合专家与预训练编码器

Feihong Zhang, Guojian Zhan, Zeyu He, Yinuo Wang, Likun Wang, Tianze Zhu, Yao Lyu, Tao Zhang, Tinghao Yi, Wei You, Shengbo Eben Li

机构 * Tsinghua University(清华大学) SunRisingAI Ltd.(日升AI有限公司) EFORT Intelligent Robot Co., Ltd.(埃夫特智能机器人有限公司)

AI总结 提出FAME框架,结合因子感知混合专家与预训练编码器,通过三阶段训练实现视觉机器人操作在多变环境中的组合泛化,在Meta-World和真实任务中分别提升34%和35%。

Comments 8 pages, 9 figures, accepted by the 2026 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
2606.21093 2026-06-23 cs.RO cs.CV 新提交

How Should a Robot Configure Its Laser Scanner for Inspection?

机器人应如何配置其激光扫描仪以进行检测?

Zhiling Chen, David Gorsich, Matthew P. Castanier, Yang Zhang, Jiong Tang, Farhad Imani

机构 * University of Connecticut(康涅狄格大学) US Army DEVCOM Ground Vehicle Systems Center (GVSC)(美国陆军DEVCOM地面车辆系统中心(GVSC))

AI总结 提出SenseHD系统,将扫描仪配置建模为指令条件感知决策,通过超维联想记忆选择稳定感知参数,提升检测可靠性。

Comments 8 pages, 9 figures. Accepted to the 2026 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
2606.21047 2026-06-23 cs.RO 新提交

Membrane-based Acoustic Microrobots

基于膜的声学微型机器人

Fatih Kocabas, Cemal Polat Avdar, Prithvi Venkatesh, Yunus Alapan

AI总结 提出一种基于柔性PDMS膜的声学微型机器人,通过物理阻隔气体扩散实现超过24小时稳定运行,并集成磁性微粒实现磁场定向控制,可扩展至约100微米。

Comments Accepted to the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026). For supplementary video contact fkocabas@wisc.edu

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.21011 2026-06-23 cs.RO 新提交

R2HandoverSim: A Simulation Framework and Benchmark for Robot-to-Human Object Handovers

R2HandoverSim:机器人到人类物体交接的仿真框架与基准

Hanxin Zhang, Abdulqader Dhafer, Hongbiao Dong, Zhou Daniel Hao

机构 * DANiLab, University of Leicester(莱斯特大学DANiLab) School of Computing and Mathematical Sciences, University of Leicester(莱斯特大学计算与数学科学学院) School of Metallurgy and Materials, University of Birmingham(伯明翰大学冶金与材料学院)

AI总结 提出R2HandoverSim仿真基准,通过用户研究和五个互补指标评估四种基线方法,证明仿真结果与真实世界评价相关。

Comments Accepted by the 2026 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
2606.20871 2026-06-23 cs.RO 新提交

Geometric Entropy: When Trajectory Diversity Helps and Hurts in Imitation Learning

几何熵:轨迹多样性在模仿学习中的利弊

Qian Luo, Ruizhe Liu, Pei Zhou, Xunzhe Zhou, Yanchao Yang

机构 * InfoBodied AI Lab, The University of Hong Kong(香港大学信息体人工智能实验室) Transcengram

AI总结 提出几何熵(H_G)量化演示轨迹的几何多样性,发现成功率与H_G呈倒U型关系,且最优熵随任务掌握度增加而降低,可用于数据集审计与校准。

Comments Accepted to IROS 2026. Project page: https://geometric-entropy.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.06870 2026-06-23 cs.RO 新提交

What Is My Robot Thinking? Design Considerations for Transparent and Trustworthy Shared Autonomy

我的机器人在想什么?透明且可信的共享自主性的设计考量

Atharv Belsare, Zohre Karimi, Connor Mattson, Rushiil Nakka, Daniel S. Brown

机构 * Kahlert School of Computing, University of Utah(犹他大学计算学院) Robotics Center, University of Utah(犹他大学机器人中心)

AI总结 通过用户实验研究共享自主系统中界面透明度(反馈模态和信息丰富度)对协调与信任的影响,发现反馈提高意图对齐、减少纠正干预,视觉优于听觉,信息丰富度偏好依赖任务复杂度,揭示完整信念分布并不一致提升对齐或信任。

Comments 9 pages, 5 Figures, Code, and videos are available at https://sites.google.com/view/design-t2-sa/home. Accepted at IROS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏