arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

International Conference on Robotics and Automation · 会议 · Robotics

共收录 4585
2605.17851 2026-05-19 cs.RO

A Dexterous and Compliant Gripper With Soft Hydraulic Actuation for Microgravity Manipulation

一种具有软液压驱动的灵活机械手用于微重力操作

William Su, Jordan Kam, Yixiao Wang, Jianshu Zhou

机构 * Aerospace Engineering Program, University of California, Berkeley(加州大学伯克利分校航空航天工程系) Department of Mechanical Engineering, University of California, Berkeley(加州大学伯克利分校机械工程系) Department of Mechanical Engineering, National University of Singapore(新加坡国立大学机械工程系)

AI总结 本文提出将DexCoHand灵活的双指六自由度机械手与Astrobee自由飞行机器人集成,以实现微重力环境下的灵活操作,该机械手在保持稳定接触的同时减少了对自由飞行基底的干扰,提高了操作的连续性和适应性。

Comments Accepted to the IEEE ICRA 2026 Space Robotics Workshop (SRW). 4 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.21787 2026-05-19 cs.CV

Benchmarking Recurrent Event-Based Object Detection for Industrial Multi-Class Recognition on MTevent

在MTevent上评估用于工业多类识别的循环事件基目标检测基准

Lokeshwaran Manohar, Moritz Roidl

机构 * Chair of Material Handling and Warehousing, TU Dortmund University, Dortmund, Germany(物料搬运与仓储学系,杜伊斯堡-艾森大学,多特蒙德,德国)

AI总结 本文研究了在MTevent数据集上使用循环ReYOLOv8s进行工业多类识别的性能,并通过非循环YOLOv8s作为基线分析时间记忆的影响,发现事件域预训练对性能提升更有效。

Comments Accepted at the Neuromorphic Field Robotics and Automation Workshop, ICRA 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.06807 2026-05-19 cs.RO cs.AI cs.LG

SuReNav: Superpixel Graph-based Constraint Relaxation for Navigation in Over-constrained Environments

SuReNav:基于超像素图的约束放松用于过约束环境中的导航

Keonyoung Koh, Moonkyeong Jung, Samuel Seungsup Lee, Daehyung Park

机构 * School of Computing, Korea Advanced Institute of Science and Technology, Korea(韩国科学技术院计算机学院)

AI总结 本文提出SuReNav方法,通过超像素图构建区域约束,利用图神经网络实现安全高效导航,适用于半静态环境中过约束规划问题,提升导航的人类类比性能。

Comments Accepted by ICRA 2026. Code and videos are available at https://sure-nav.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.07191 2026-05-19 cs.RO cs.LG stat.ME

Curb Your Attention: Causal Attention Gating for Robust Trajectory Prediction in Autonomous Driving

抑制注意力:因果注意力门控用于自动驾驶中的鲁棒轨迹预测

Ehsan Ahmadi, Ray Mercurius, Soheil Alizadeh, Kasra Rezaee, Amir Rasouli

机构 * University of Alberta(阿尔伯塔大学) Noah’s Ark Laboratory, Huawei Technologies Canada(华为加拿大诺亚实验室) Cornell University(康奈尔大学)

AI总结 本文提出CRiTIC模型,通过因果发现网络识别agent间因果关系,并引入因果注意力门控机制提升轨迹预测的鲁棒性和泛化能力,实验表明模型在对抗非因果扰动时鲁棒性提升54%。

Comments Accepted ICRA 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.16432 2026-05-19 cs.RO cs.AI cs.HC

MR-SLAM: Immersive Spatial Supervision for Multi-Robot Mapping via Mixed Reality

MR-SLAM:通过混合现实实现多机器人地图的沉浸式空间监督

Prakash Aryan, Cem Erdogdu, Kavinaya Kumarchokkappan, Timo Kehrer, Sebastiano Panichella

机构 * University of Bern, Bern, Switzerland(伯尔尼大学) AI4I -- The Italian Institute of Artificial Intelligence, Turin, Italy(意大利人工智能研究所)

AI总结 本文提出MR-SLAM系统,利用混合现实技术实现多机器人SLAM的沉浸式空间监督,通过实时可视化和空间锚定面板提升多机器人定位与建图效率。

Comments Accepted to ICRA 2026 Workshop "MM-SpatialAI Workshop: Multi-Modal Spatial AI for Robust Navigation and Open-World Understanding"

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.16300 2026-05-19 cs.CY cs.AI cs.MA cs.RO

Consent Chain Degradation in Embodied Multi-Agent Systems: Bridging the Gap Between AI Agent Governance and Robot Ethics

具身多智能体系统中的同意链退化:弥合人工智能代理治理与机器人伦理之间的鸿沟

Mehmet Haklidir

机构 * Artificial Intelligence Institute, TÜBİTAK BİLGEM(人工智能研究所,TÜBİTAK BİLGEM)

AI总结 本文提出同意链退化(CCD)概念,探讨多机器人委托链中人类同意的具体性、有效性及范围如何退化,并通过医疗、家庭和工业机器人场景展示其实际表现,分析现有法规对CCD核心维度的缺失。

Comments Accepted for oral presentation at the 2nd Workshop on Robot Ethics (WoRoBet), ICRA 2026, Vienna, Austria, June 1, 2026. 6 pages, 3 tables, 1 figure

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.16056 2026-05-18 cs.RO

Health-Conditioned Vision-Language-Action Models for Malfunction-Aware Robot Control

面向故障感知的视觉-语言-动作模型用于机器人故障-aware 控制

Hüseyin Arslan, Özgür Erkent

机构 * Computer Engineering, Hacettepe University, Ankara, Turkey(哈切特佩大学计算机工程系,安卡拉,土耳其)

AI总结 本文提出一种故障感知的视觉-语言-动作模型,通过引入健康投影模块,使机器人在关节退化等物理故障情况下仍能完成任务。

Comments VLA Pipelines Workshop at IEEE International Conference on Robotics and Automation (ICRA) 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.16043 2026-05-18 cs.RO cs.AI

Learning Sim-Grounded Policies for Bimanual Rope Manipulation from Human Teleoperation Data

从人类遥控数据中学习双臂绳子操作的模拟 grounded 策略

Gina Wigginghaus, Tim Missal, Berk Guler, Simon Manschitz, Jan Peters

机构 * Technical University of Darmstadt(德累斯顿技术大学) German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心) Robotics Institute Germany (RIG)(德国机器人研究所) Centre for Cognitive Science(认知科学研究中心) Honda Research Institute Europe GmbH(本田欧洲研究院)

AI总结 本文研究了基于视觉的策略在解结任务中泛化能力不足是否源于观察空间而非策略架构或数据规模,通过比较两种基于动作分块与变压器的策略,发现基于物理状态的策略在预测初始抓取和拉拽动作时L1误差降低了30.8%。

Comments Accepted to the Beyond Teleoperation Workshop at ICRA 2026, 5 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.15619 2026-05-18 cs.RO

Wind-Aware Optimal Trajectory Planning for Efficient Gliding of Fixed-Wing Aerial Systems

考虑风的高效滑翔轨迹规划

Luca Morando, Nishanth Bobbili, Giuseppe Loianno

机构 * New York University(纽约大学) University of California Berkeley(加州大学伯克利分校)

AI总结 本文提出非线性多目标轨迹规划器,通过伯恩斯坦多项式生成三次连续轨迹,结合风速估算优化滑翔性能,实验证明在风扰和障碍物情况下具有稳定性和可靠性。

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

Journal ref IEEE International Conference on Robotics and Automation (ICRA 2026) held in Vienna

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.04310 2026-05-18 cs.RO

frax: Fast Robot Kinematics and Dynamics in JAX

frax:基于JAX的快速机器人运动学与动力学

Daniel Morton, Marco Pavone

机构 * Departments of Mechanical Engineering and Aeronautics & Astronautics, Stanford University(机械工程系和航空与航天系,斯坦福大学)

AI总结 frax提供高性能纯Python接口,支持CPU、GPU和TPU,实现高效的实时控制与并行计算,适用于机器人运动学和动力学的高性能计算需求。

Comments ICRA 2026 Workshop on Frontiers of Optimization for Robotics

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.13350 2026-05-18 cs.RO

Approximating Global Contact-Implicit MPC via Sampling and Local Complementarity

通过采样和局部互补性近似全局接触-隐式MPC

Sharanya Venkatesh, Bibit Bianchini, Alp Aydinoglu, William Yang, Michael Posa

机构 * GRASP Laboratory at the University of Pennsylvania(宾夕法尼亚大学GRASP实验室) Boston Dynamics(波士顿动力) Amazon Robotics(亚马逊机器人技术)

AI总结 本文提出一种结合局部互补性控制与全局采样方法的控制器,用于实时灵活操作。通过在每个控制循环中先进行无接触阶段再进行接触密集阶段,实现对非凸物体的精确非抓取操作。

Comments S.V. and B.B. contributed equally to this work. Accepted to RA-L 2025; presented at ICRA 2026. Project page: https://approximating-global-ci-mpc.github.io

Journal ref IEEE Robotics and Automation Letters, volume 10, number 11, pages 12117-12124, September 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.14801 2026-05-15 cs.RO

Exploring Bottlenecks in VLM-LLM Navigation: How 3D Scene Understanding Capability Impacts Zero-Shot VLN

探索VLM-LLM导航中的瓶颈:3D场景理解能力如何影响零样本VLN

Ziyi Xia, Chaoran Xiong, Litao Wei, Xinhao Hu, Ling Pei

机构 * Shanghai Key Laboratory of Navigation and Location Based Services, Shanghai Jiao Tong University(上海导航与基于位置的服务关键实验室,上海交通大学)

AI总结 本文研究了零样本视觉-语言导航中3D场景理解能力对性能的影响,提出了统计成功率上限,揭示了感知饱和现象,建议转向导航相关的核心词汇和准确的边界框比例。

Comments Accepted by ICRA Workshop MM-Spatial AI, Oral

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.04646 2026-05-15 cs.RO cs.LG

ActivePusher: Active Learning and Planning with Residual Physics for Nonprehensile Manipulation

ActivePusher: 基于残差物理的主动学习与规划用于非抓取操作

Zhuoyun Zhong, Seyedali Golestaneh, Constantinos Chamzas

机构 * Department of Robotics Engineering, Worcester Polytechnic Institute (WPI)(机器人工程系,沃斯特理工学院(WPI))

AI总结 本文提出ActivePusher框架,结合残差物理模型与不确定性主动学习,提升非抓取操作的数据效率和规划成功率。

Comments Accepted by the 2026 IEEE International Conference on Robotics & Automation (ICRA 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13578 2026-05-14 math.QA math.RT

Quiver varieties and dual canonical bases

有向图品种与对偶规范基

Ming Lu, Xiaolong Pan

AI总结 本文综述了量子群和$\imath$量子群对偶规范基理论的最新进展,介绍了$\imath$有向图代数,并展示了其在ADE类型准分裂$\imath$量子群中的两种实现方式,同时解决了若干猜想。

Comments 34 pages. To appear in Proc. ICRA 21 (2024), published by European Math. Soc. arXiv admin note: substantial text overlap with arXiv:2504.19073

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13208 2026-05-14 cs.RO

Calibration-Free Gas Source Localization with Mobile Robots: Source Term Estimation Based on Concentration Measurement Ranking

无需校准的移动机器人气体源定位:基于浓度测量排名的源项估计

Wanting Jin, Agatha Duranceau, İzzet Kağan Erünsal, Alcherio Martinoli

机构 * Distributed Intelligent Systems and Algorithms Laboratory, School of Architecture, Civil and Environmental Engineering, École Polytechnique Fédérale de Lausanne (EPFL)(分布式智能系统与算法实验室,建筑、 civil 和环境工程学院,洛桑联邦理工学院(EPFL))

AI总结 本文提出一种无需校准的气体源定位方法,通过分析移动机器人收集的浓度测量排名差异,估计源位置的概率分布,适用于真实环境。

Comments This paper has been 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
2605.13123 2026-05-14 cs.RO

Multi-Depth Uniform Coverage Path Planning for Unmanned Surface Vehicle Surveying

多深度均匀覆盖路径规划用于无人水面舰艇勘测

Maider Larrazabal, Tong Yang, Izaro Goienetxea, Jaime Valls Miro

机构 * AZTI Foundation(AZTI基金会) Tsinghua University(清华大学) University of the Basque Country (UPV/EHU)(巴斯克国家大学(UPV/EHU)) University of Technology Sydney(悉尼技术大学) IKERBASQUE

AI总结 本文提出一种新型自动覆盖路径规划算法,用于无人水面舰艇的水深勘测。通过整合粗略的深度信息预处理目标区域,并自适应引导路径生成和探测范围配置,优化路径间距以实现更一致的海底覆盖。

Comments Accepted by ICRA 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13067 2026-05-14 cs.RO cs.AI

When Absolute State Fails: Evaluating Proprioceptive Encodings for Robust Manipulation

当绝对状态失效:评估本体感觉编码以实现鲁棒操作

Maxime Alvarez, Ryo Watanabe, Paul Crook, Afshin Zeinaddini Meymand, Suvin Kurian, Pablo Ferreiro, Genki Sano

机构 * TELEXISTENCE Inc, Foundation Model Division(TELEXISTENCE公司基础模型部门) The University of Tokyo(东京大学)

AI总结 研究探讨了本体感觉状态编码策略,通过系统分析联合表示发现,简单的回合间相对框架在任务性能与鲁棒性之间提供了最佳平衡,优于基线方法。

Comments Accepted to ICRA 2026 Workshop: From Data to Decisions

详情

展开后加载摘要…

URL PDF HTML 收藏
2310.07844 2026-05-14 cs.RO

Saturation-Aware Angular Velocity Estimation: Extending the Robustness of SLAM to Aggressive Motions

考虑饱和的角速度估计:将SLAM的鲁棒性扩展到激进运动

Simon-Pierre Deschênes, Dominic Baril, Matěj Boxan, Johann Laconte, Philippe Giguère, François Pomerleau

机构 * Northern Robotics Laboratory, Université Laval, Quebec City, Quebec, Canada(北方机器人实验室,拉瓦尔大学,魁北克市,魁北克,加拿大)

AI总结 本文提出一种新的角速度估计方法,以提高SLAM算法在剧烈运动引起的陀螺仪饱和情况下的鲁棒性。通过使用加速度计在机器人翻滚时估计角速度,显著降低定位误差,并提出TIGS数据集以支持研究。

Comments 7 pages, 7 figures, published in 2024 IEEE International Conference on Robotics and Automation (ICRA), Yokohama, Japan

Journal ref 2024 IEEE International Conference on Robotics and Automation (ICRA), Yokohama, Japan, 2024, pp. 10711-10718

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.05120 2026-05-13 cs.RO cs.SY eess.SY

Rollbot: a Spherical Robot Driven by a Single Actuator

Rollbot:由单个执行器驱动的球形机器人

Jingxian Wang, Michael Rubenstein

机构 * Center for Robotics and Biosystems, Northwestern University(机器人与生物系统中心,西北大学)

AI总结 Rollbot是首个能通过单个执行器在二维平面上可控移动的球形机器人,通过改变轨迹曲率实现运动控制,验证了理论框架的有效性。

Comments Accepted by ICRA 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.04541 2026-05-12 cs.CV

Angle-I2P: Angle-Consistent-Aware Hierarchical Attention for Cross-Modality Outlier Rejection

Angle-I2P:基于角度一致性的层次注意力交叉模态异常剔除

Muyao Peng, Shun Zou, Pei An, You Yang, Qiong Liu

机构 * School of Electronic Information and Communications, Huazhong University of Science and Technology(华中科技大学电子信息与通信学院)

AI总结 本文提出Angle-I2P方法,通过角度一致性的几何约束和层次注意力机制提升跨模态异常剔除性能,实验表明在多个数据集上均取得最佳效果。

Comments Accepted by ICRA 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.12027 2026-05-12 cs.RO

3DRO: Lidar-level SE(3) Direct Radar Odometry Using a 2D Imaging Radar and a Gyroscope

3DRO:基于2D成像雷达和陀螺仪的激光雷达级SE(3)直接雷达里程计

Cedric Le Gentil, Daniil Lisus, Timothy D. Barfoot

机构 * Robotics Institute, University of Toronto(多伦多大学机器人研究所) Mobile Robotics Lab, ETH Zurich(苏黎世联邦理工学院移动机器人实验室)

AI总结 本文提出3DRO,扩展SE(2)直接雷达里程计框架以实现SE(3)状态估计,通过2D速度估计保持数据平面性并结合3D陀螺仪测量,实现激光雷达级精度。

Comments Accepted for presentation at the ICRA 2026 Workshop on Radar in Robotics (poster: https://drive.google.com/file/d/1P_iBrGxPiZL644B-dHxbvdY-UJUzd4Kp/view )

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.07686 2026-05-12 cs.RO cs.CV

UniUncer: Unified Dynamic Static Uncertainty for End to End Driving

UniUncer: 统一的动态静态不确定性用于端到端驾驶

Yu Gao, Jijun Wang, Zongzheng Zhang, Anqing Jiang, Yiru Wang, Yuwen Heng, Shuo Wang, Hao Sun, Zhangfeng Hu, Hao Zhao

机构 * Bosch Corporate Research(博世企业研究)

AI总结 本文提出UniUncer,一种轻量级统一不确定性框架,用于端到端驾驶规划中同时估计和利用静态和动态场景元素的不确定性,通过概率回归器、不确定性融合模块和不确定性感知门控模块,降低轨迹误差并提升整体性能。

Comments Accepted ICRA 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.08886 2026-05-12 eess.IV cs.RO

VISTA: A Benchmark for Real-Time Video Streaming under Network Impairments in Surgical Teleoperation

VISTA:用于手术远程操控中网络干扰下实时视频流的基准测试

Zexin Deng, Zhenhui Yuan, Tian Lu, Gaofeng Li, Meipeng Huang, Longhao Zou

机构 * School of Engineering, University of Warwick(战争学院工程学院) Institute for Applied and Translational Technologies in Surgery, University Hospitals Coventry & Warwickshire NHS Trust(外科应用与转化技术研究所,科文伯恩与沃里克郡国家健康信托基金会) Pengcheng Laboratory(鹏城实验室) South China University of Technology(华南理工大学) Southern University of Science and Technology(南方科技大学)

AI总结 本文提出VISTA基准测试,评估网络干扰对视频质量、时间连续性和任务性能的影响,通过模拟五种网络条件验证了网络退化对手术远程操控性能的显著影响。

Comments Oral presentation at the Connected Autonomous Robotic Systems Workshop, ICRA 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.08722 2026-05-12 cs.RO cs.MA

HULK: Large-scale Hierarchical Coordination under Continual and Uncertain Temporal Tasks

HULK:大规模层次协调在连续和不确定的时间任务中

Qingyuan Luo, Jie Li, Meng Guo

机构 * Department of Mechanics and Engineering Science, College of Engineering, Peking University(力学与工程科学系,工程学院,北京大学) National University of Defense Technology(国防科学技术大学)

AI总结 本文提出HULK框架,解决连续和不确定时间任务下的大规模协调问题,通过分层结构提升计算效率和鲁棒性。

Comments Accepted to the IEEE International Conference on Robotics and Automation. 7 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.07771 2026-05-11 cs.RO

Sensitivity-Based Robust NMPC for Close-Proximity Offshore Wind Turbine Inspection with a Tilted Multirotor

基于灵敏度的稳健非线性模型预测控制用于近距海上风力涡轮机检查

Giuseppe Silano, Martin Saska

机构 * Ricerca sul Sistema Energetico S.p.A.(能源系统研究股份有限公司) Czech Technical University in Prague(布拉格捷克技术大学)

AI总结 本文提出一种基于灵敏度的稳健NMPC方法,用于近距海上风力涡轮机检查,通过在线约束紧缩提升塔筒 clearance 约束的鲁棒性,减少因风况和模型不匹配导致的约束违反问题。

Comments 5 pages. Accepted for presentation at the ICRA 2026 Workshop on "Aerial inspection for marine infrastructures," June 1, 2026, Vienna, Austria

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.07625 2026-05-11 cs.RO cs.SY eess.SY

GATO: GPU-Accelerated and Batched Trajectory Optimization for Scalable Edge Model Predictive Control

GATO:用于可扩展边缘模型预测控制的GPU加速和批处理轨迹优化

Alexander Du, Emre Adabag, Gabriel Bravo-Palacios, Brian Plancher

机构 * School of Engineering and Applied Science, Columbia University(哥伦比亚大学工程与应用科学学院) University of Michigan(密歇根大学) Barnard College, Columbia University and Dartmouth College(哥伦比亚大学巴纳德学院和达特茅斯学院)

AI总结 GATO通过算法、软件和计算硬件的协同设计,实现对中等批量大小的实时轨迹优化,提升边缘模型预测控制的性能。

Comments Accepted to ICRA 2026. 8 pages, 8 figures, 2 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.04839 2026-05-11 cs.RO

TAG-K: Tail-Averaged Greedy Kaczmarz for Computationally Efficient and Performant Online Inertial Parameter Estimation

TAG-K:尾部平均贪心Kaczmarz用于计算高效且性能优异的在线惯性参数估计

Shuo Sha, Anupam Bhakta, Zhenyuan Jiang, Kevin Qiu, Ishaan Mahajan, Gabriel Bravo-Palacios, Brian Plancher

机构 * School of Applied Science, Columbia University(哥伦比亚大学应用科学学院) Columbia College, Columbia University(哥伦比亚大学哥伦比亚学院) Barnard College, Columbia University and Dartmouth College(哥伦比亚大学巴纳德学院和达特茅斯学院)

AI总结 本文提出TAG-K算法,结合贪心随机行选择和尾部平均,实现高效稳定的在线惯性参数估计,在计算受限的机器人系统中表现出更快的求解速度和更高的鲁棒性。

Comments Accepted to ICRA 2026. 3 Figures. 3 Tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.18149 2026-05-11 cs.RO cs.SY eess.SY math.OC

Code Generation and Conic Constraints for Model-Predictive Control on Microcontrollers with Conic-TinyMPC

基于锥约束的模型预测控制与代码生成:适用于微控制器的Conic-TinyMPC

Ishaan Mahajan, Khai Nguyen, Sam Schoedel, Elakhya Nedumaran, Moises Mata, Brian Plancher, Zachary Manchester

机构 * School of Engineering and Applied Science, Columbia University(哥伦比亚大学工程与应用科学学院) Carnegie Mellon University(卡内基梅隆大学) Massachusetts Institute of Technology(麻省理工学院) Barnard College, Columbia University and Dartmouth College(哥伦比亚大学巴纳德学院和达特茅斯学院)

AI总结 本文提出一种适用于微控制器的模型预测控制方法,通过支持二次锥约束和自动生成C++代码,显著提升了嵌入式系统的求解速度和问题规模。

Comments Accepted to ICRA 2026. 4 Figures. 2 Tables. First three authors contributed equally

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.07367 2026-05-11 cs.RO cs.CV

Weather-Robust Scene Semantics with Vision-Aligned 4D Radar

具有视觉对齐4D雷达的抗天气场景语义

Kali Hamilton, Christoffer Heckman

机构 * Autonomous Robotics and Perception Group(自主机器人与感知组)

AI总结 本文提出通过冻结视觉语言模型将雷达编码器对齐于SigLIP嵌入,以提升恶劣天气下的场景语义理解,实验表明雷达配置在雾、轻雪和重雪条件下优于相机基线。

Comments 5 pages + references, 2 appendix pages. ICRA 2026 Radar in Robotics Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.06966 2026-05-11 cs.RO cs.SE

Traffic Scenario Orchestration from Language via Constraint Satisfaction

通过约束满足实现基于语言的交通场景编排

Frieda Rong, Chris Zhang, Kelvin Wong, Raquel Urtasun

机构 * University of Toronto(多伦多大学) Waabi

AI总结 本文提出一种基于约束满足的交通场景编排方法,通过自然语言生成约束条件,利用现成求解器实现闭环测试中的精确场景控制,显著提高了场景编排成功率。

Comments 19 pages, 10 figures; full version of paper accepted for poster presentation at ICRA 2026

详情

展开后加载摘要…

URL PDF HTML 收藏