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

共收录 3483
2605.23027 2026-05-25 cs.RO

PIMbot: A Self-Adaptive Attack Framework for Adversarial Manipulation of Multi-Robot Reinforcement Learning

PIMbot:一种用于多机器人强化学习对抗性操纵的自适应攻击框架

Zexin Li, Ziliang Zhang, Hyoseung Kim, Cong Liu

机构 * University of California, Riverside(加州大学河滨分校)

AI总结 提出PIMbot框架,通过奖励激励操纵和策略操纵两种互补杠杆,并采用自适应多目标控制器在线平衡,有效操纵多机器人社会困境环境,实验验证了其在仿真和真实嵌入式系统中的有效性。

Comments Extension version of IROS'23

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.14648 2026-05-22 cs.RO cs.AI

SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning

SENIOR: 在基于偏好的强化学习中高效查询选择与偏好引导探索

Hexian Ni, Tao Lu, Haoyuan Hu, Yinghao Cai, Shuo Wang

机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences(多模态人工智能系统国家重点实验室,自动化研究所) School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)

AI总结 本文提出SENIOR方法,通过高效查询选择和偏好引导探索提升人类反馈效率和策略学习速度,解决基于偏好的强化学习在反馈和样本效率方面的不足。

Comments 8 pages, 8 figures, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17363 2026-05-19 cs.CV cs.LG cs.RO

M2H: Multi-Task Learning with Efficient Window-Based Cross-Task Attention for Monocular Spatial Perception

M2H:基于高效窗口交叉任务注意力的多任务学习用于单目空间感知

U. V. B. L Udugama, George Vosselman, Francesco Nex

机构 * Department of Earth Observation Science(地球观测科学系)

AI总结 本文提出M2H框架,通过高效的窗口交叉任务注意力模块,实现单目图像上的语义分割、深度估计、边缘检测和表面法线估计,同时在计算效率上优于现有方法。

Comments Accepted to the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025). 8 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.00384 2026-05-04 cs.RO

PrefMoE: Robust Preference Modeling with Mixture-of-Experts Reward Learning

PrefMoE:基于专家混合的鲁棒偏好建模

Ziqin Yuan, Ruiqi Wang, Dezhong Zhao, Baijian Yang, Byung-Cheol Min

机构 * Purdue University(普渡大学) Beijing University of Chemical Technology(北京化工大学) Indiana University Bloomington(印第安纳大学布卢明顿分校)

AI总结 PrefMoE通过混合专家框架提升偏好建模鲁棒性,采用轨迹级软路由结合多个专用奖励专家,有效处理异质且部分冲突的偏好监督,提升下游策略学习可靠性。

Comments IROS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.17387 2026-04-29 cs.RO

High-Precision and High-Efficiency Trajectory Tracking for Excavators Based on Closed-Loop Dynamics

基于闭环动力学的高精度高效率挖掘机轨迹跟踪

Ziqing Zou, Cong Wang, Yue Hu, Xiao Liu, Bowen Xu, Rong Xiong, Changjie Fan, Yingfeng Chen, Yue Wang

机构 * Zhejiang University(浙江大学) Fuxi Robotics Lab, NetEase Inc.(网易弗西机器人实验室)

AI总结 本文提出EfficientTrack方法,结合模型学习和闭环动力学,解决液压挖掘机非线性动力学难题,提升轨迹跟踪精度与效率,实验证明其在仿真和实际应用中均优于传统方法。

Journal ref 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hangzhou, China, 2025, pp. 5617-5624

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.24906 2026-04-29 cs.RO cs.LG cs.SY eess.SY

An analysis of sensor selection for fruit picking with suction-based grippers

基于吸盘夹具的水果采摘传感器选择分析

Eva Krueger, Marcus Rosette, Joseph R. Davidson

机构 * Collaborative Robotics and Intelligent Systems (CoRIS) Institute(协作机器人与智能系统研究所)

AI总结 本文提出一种多模态传感系统,用于评估不同采摘阶段传感器的效用,通过实验证明随机森林和多层感知器在检测成功采摘和即将失败事件中的高准确率。

Comments IROS Conference Format, 6 pages, 6 figures, 1 table

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.12193 2026-04-29 cs.RO

Continual Domain Randomization

持续领域随机化

Josip Josifovski, Sayantan Auddy, Mohammadhossein Malmir, Justus Piater, Alois Knoll, Nicolás Navarro-Guerrero

机构 * School of Computation Information and Technology, Technical University of Munich(技术大学慕尼黑计算信息与技术学院) Department of Computer Science, University of Innsbruck(因斯布鲁克大学计算机科学系) L3S Research Center, Leibniz Universität Hannover(汉诺威莱布尼茨大学L3S研究中心) Digital Science Center (DiSC), University of Innsbruck(因斯布鲁克大学数字科学中心)

AI总结 本文提出持续领域随机化方法,结合领域随机化与持续学习,通过逐步随机化参数提升机器人抓取任务的仿真训练效果和现实性能。

Comments Accepted at IROS 2024. Equal contribution from first two authors

详情

展开后加载摘要…

URL PDF HTML 收藏
2206.06282 2026-04-29 cs.RO cs.AI

Analysis of Randomization Effects on Sim2Real Transfer in Reinforcement Learning for Robotic Manipulation Tasks

随机化对机器人操作任务中仿真到现实转移的影响分析

Josip Josifovski, Mohammadhossein Malmir, Noah Klarmann, Bare Luka Žagar, Nicolás Navarro-Guerrero, Alois Knoll

机构 * Department of Informatics, Technical University of Munich(慕尼黑技术大学信息学院) Rosenheim University of Applied Sciences(罗森海姆应用技术大学)

AI总结 本文提出一个可复现的实验框架,比较四种随机化策略在仿真和现实中的表现,发现更多随机化有助于仿真到现实转移,但可能影响仿真中策略的学习能力。

Comments Accepted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.23696 2026-04-28 cs.RO cs.SY eess.SY

Real-Time Non-Contact Force Compensation for Wrist-Mounted Force/Torque Sensors in Haptic-Enabled Robotic Surgery Training

用于力/扭矩传感器在触觉增强外科手术培训中的实时非接触力补偿

Walid Shaker, Mustafa Suphi Erden

机构 * School of Engineering and Physical Sciences, Heriot-Watt University(工程与物理科学学院,赫瑞-瓦特大学)

AI总结 本文提出一种基于递归最小二乘法的实时补偿方法,用于解决腕部力/扭矩传感器在触觉反馈训练中的非接触力干扰问题,实验显示其在力和扭矩补偿上的误差降低率分别超过95%和91%。

Comments Submitted to 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
2504.13713 2026-04-28 cs.RO cs.CV

SLAM&Render: A Benchmark for the Intersection Between Neural Rendering, Gaussian Splatting and SLAM

SLAM&Render: 一个用于神经渲染、高斯点绘和SLAM交叉领域的基准数据集

Samuel Cerezo, Gaetano Meli, Tomás Berriel Martins, Kirill Safronov, Javier Civera

机构 * Technology \& Innovation Center KUKA Deutschland GmbH Augsburg, Germany

AI总结 本文提出SLAM&Render数据集,用于评估神经渲染和SLAM在多模态、多视角和光照条件下的交叉方法,包含40个序列的RGB-D图像、IMU数据和机器人运动数据,验证了该数据集在新兴研究领域的相关性。

Comments 9 pages, 8 figures, 7 tables. Submitted to IROS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.20151 2026-04-23 cs.RO cs.LG

Toward Safe Autonomous Robotic Endovascular Interventions using World Models

迈向安全的自主机器人内血管干预的世模型

Harry Robertshaw, Nikola Fischer, Han-Ru Wu, Andrea Walker Perez, Weiyuan Deng, Benjamin Jackson, Christos Bergeles, Alejandro Granados, Thomas C Booth

机构 * Surgical & Interventional Engineering, School of Biomedical Engineering & Imaging Sciences, King’s College London(外科与介入工程系,生物医学工程与成像科学学院,伦敦国王学院) Department of Radiology, National Taiwan University Hospital(放射科,台湾大学医院) Department of Neuroradiology, King’s College Hospital(神经放射科,伦敦国王医院)

AI总结 本文提出基于世模型的框架,利用TD-MPC2方法在内血管导航中实现自主机械取栓,通过仿真和体外实验验证其在安全性和泛化性上的优势。

Comments This manuscript is a preprint and has been submitted 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
2506.15518 2026-04-23 cs.RO

Real-Time Initialization of Unknown Anchors for UWB-aided Navigation

UWB导航中未知锚点的实时初始化

Giulio Delama, Igor Borowski, Roland Jung, Stephan Weiss

机构 * Control of Networked Systems Group, University of Klagenfurt(网络化系统控制组,克雷根弗特大学)

AI总结 本文提出了一种实时初始化未知UWB锚点的框架,结合在线PDOP估计、轻量级异常检测和自适应鲁棒核,提升鲁棒性和实用性。通过保守的初始化指标,实现更优的初始化几何和更低的定位误差。

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
2308.00513 2026-04-23 cs.RO

UVIO: An UWB-Aided Visual-Inertial Odometry Framework with Bias-Compensated Anchors Initialization

UVIO:一种结合UWB的视觉-惯性里程计框架,具有偏置补偿的锚点初始化

Giulio Delama, Farhad Shamsfakhr, Stephan Weiss, Daniele Fontanelli, Alessandro Fornasier

机构 * Control of Networked Systems Group, University of Klagenfurt(网络化系统控制组,克雷根弗特大学) Department of Industrial Engineering, University of Trento(工业工程系,特伦托大学)

AI总结 UVIO框架利用UWB技术和视觉-惯性里程计实现鲁棒低漂移定位,通过无人机自主初始化未知锚点,利用GDOP优化锚点位置估计,减少映射不确定性,最终消除初始化锚点范围内的VIO漂移。

Journal ref 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.16967 2026-04-21 cs.RO cs.AI

NaviFormer: A Deep Reinforcement Learning Transformer-like Model to Holistically Solve the Navigation Problem

NaviFormer:一种深度强化学习变换器模型,以整体解决导航问题

Daniel Fuertes, Andrea Cavallaro, Carlos R. del-Blanco, Fernando Jaureguizar, Narciso García

机构 * Grupo de Tratamiento de Imágenes, Information Processing and Telecommunications Center, ETSI Telecomunicación, Universidad Politécnica de Madrid(图像处理与电信中心,信息处理与电信中心,电信工程学院,马德里理工大学) Idiap Research Institute(Idiap研究机构)

AI总结 NaviFormer通过预测高层路线和底层轨迹,整体解决导航问题,实验表明其在准确性和计算速度上表现优异,适用于实时任务。

Comments Published in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.16850 2026-04-21 cs.RO cs.AI cs.SY eess.SY

Refinement of Accelerated Demonstrations via Incremental Iterative Reference Learning Control for Fast Contact-Rich Imitation Learning

通过增量迭代参考学习控制细化加速演示

Koki Yamane, Cristian C. Beltran-Hernandez, Steven Oh, Masashi Hamaya, Sho Sakaino

机构 * OMRON SINIC X Corporation(OMRON SINIC X公司) University of Tsukuba(茨口大学) Waseda University(早稻田大学)

AI总结 本文提出I2RLC方法,通过逐步提升速度并更新参考轨迹,实现高保真度的加速演示,提升接触密集模仿学习的效率与稳定性。

Comments 8 pages, 11 figures, submitted to IROS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.16739 2026-04-20 cs.CV

Two-Stage Framework for Efficient UAV-Based Wildfire Video Analysis with Adaptive Compression and Fire Source Detection

面向高效无人机 wildfire 视频分析的两阶段框架:具有自适应压缩和火源检测

Yanbing Bai, Rui-Yang Ju, Lemeng Zhao, Junjie Hu, Jianchao Bi, Erick Mas, Shunichi Koshimura

机构 * Center for Applied Statistics, School of Statistics, Renmin University of China(应用统计中心,统计学院,中国人民大学) Graduate School of Informatics, Kyoto University(信息研究生院,京都大学) Shenzhen Institute of Artificial Intelligence and Robotics for Society(社会人工智能与机器人研究所,深圳) International Research Institute of Disaster Science, Tohoku University(灾害科学国际研究所,东北大学)

AI总结 本文提出一种轻量高效的两阶段框架,通过自适应压缩和火源检测技术,降低无人机在灾难应急响应中的计算成本,提升 wildfire 监测效率。

Comments IEEE JSTARS; Extended Journal Version of IROS 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.00214 2026-04-20 cs.RO

Tendon-driven Grasper Design for Aerial Robot Perching on Tree Branches

基于肌腱驱动的抓取器设计用于空中机器人在树枝上着陆

Haichuan Li, Ziang Zhao, Ziniu Wu, Parth Potdar, Long Tran, Ali Tahir Karasahin, Shane Windsor, Stephen G. Burrow, Basaran Bahadir Kocer

机构 * School of Civil, Aerospace and Design Engineering, University of Bristol(布里斯托大学土木、航空航天与设计工程学院) Department of Engineering, University of Cambridge(剑桥大学工程系) School of Engineering Mathematics and Technology, University of Bristol(布里斯托大学工程数学与科技学院) Faculty of Engineering, Department of Mechatronics Engineering, Necmettin Erbakan University, Turkey(土耳其内姆ettin埃尔巴坎大学工程学院)

AI总结 本文提出了一种生物启发的空中平台,通过肌腱驱动机制实现低能耗的树枝着陆,用于复杂森林环境的数据采集。

Comments 7 pages, 9 figures

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
2209.14774 2026-04-17 cs.CV cs.AI

RECALL: Rehearsal-free Continual Learning for Object Classification

RECALL: 无回放的持续学习用于物体分类

Markus Knauer, Maximilian Denninger, Rudolph Triebel

AI总结 RECALL通过计算旧类别的logits来避免遗忘,无需保存先前数据,为持续学习提供新类别分类方法,并在CORe50和iCIFAR-100上优于现有方法。

Comments Accepted as contributed paper at the 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022)

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.13142 2026-04-16 cs.RO cs.CV cs.DB

Multi-modal panoramic 3D outdoor datasets for place categorization

多模态全景三维户外数据集用于场所分类

Hojung Jung, Yuki Oto, Oscar M. Mozos, Yumi Iwashita, Ryo Kurazume

机构 * Graduate School of Information Science and Electrical Engineering, Kyushu University(九州大学信息科学与电子工程研究生院) Polytechnic University of Cartagena (UPCT)(卡塔赫纳理工学院) Faculty of Information Science and Electrical Engineering, Kyushu University(九州大学信息科学与电子工程学系)

AI总结 本文提出两个多模态全景三维户外数据集,用于语义场所分类,包含森林、海岸、住宅区、城市区及室内外停车场六类,通过激光扫描和同步图像获取数据,并比较了多种分类方法,取得高准确率。

Comments This is the authors' manuscript. The final published article was presented at IROS 2026, and it is available at https://doi.org/10.1109/IROS.2016.7759669

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.11372 2026-04-16 cs.RO

MR.ScaleMaster: Scale-Consistent Collaborative Mapping from Crowd-Sourced Monocular Videos

MR.ScaleMaster: 从众源单目视频实现一致性协作制图

Hyoseok Ju, Giseop Kim

机构 * Department of Robotics and Mechatronics Engineering, DGIST(机器人与机电工程系,DGIST)

AI总结 本文提出MR.ScaleMaster系统,通过解决尺度崩溃和漂移问题,实现众源单目视频的协作制图,显著提升精度并支持多机器人融合。

Comments 8 pages, 7 figures, submitted to IROS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.12418 2026-04-15 cs.RO cs.AI

RACF: A Resilient Autonomous Car Framework with Object Distance Correction

RACF:一种具有物体距离校正的鲁棒自动驾驶框架

Chieh Tsai, Hossein Rastgoftar, Salim Hariri

机构 * Department of Electrical and Computer Engineering, University of Arizona, Tucson, AZ, USA(电气与计算机工程系,亚利桑那大学,图森,亚利桑那州,美国) Department of Aerospace and Mechanical Engineering, University of Arizona, Tucson, AZ, USA(航空航天与机械工程系,亚利桑那大学,图森,亚利桑那州,美国)

AI总结 本文提出RACF框架,通过多传感器冗余和多样性提升自动驾驶感知鲁棒性,实验表明其在强干扰下可降低35%的RMSE,提升停车合规性和制动延迟。

Comments 8 pages, 9 figures, 5 tables. Submitted manuscript to IROS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.14634 2026-04-15 cs.RO

Physically Accurate Rigid-Body Dynamics in Particle-Based Simulation

基于物理的刚体动力学在粒子模拟中的实现

Ava Abderezaei, Nataliya Nechyporenko, Joseph Miceli, Gilberto Briscoe-Martinez, Alessandro Roncone

机构 * Department of Computer Science, University of Colorado Boulder(科罗拉多大学博尔德分校计算机科学系)

AI总结 本文提出PBD-R方法,通过新的动量守恒约束和修改的速度假设,提升粒子模拟在机器人中的物理准确性,并引入无solver基准测试评估性能。

Comments Submitted to IROS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.11295 2026-04-14 cs.RO

Modeling, Analysis and Activation of Planar Viscoelastically-combined Rimless Wheels

平面粘弹性结合无轮轮子的建模、分析与激活

Fumihiko Asano, Yuxuan Xiang, Yanqiu Zheng, Cong Yan

机构 * Japan Advanced Institute of Science and Technology(日本先端科学技术大学院大学)

AI总结 本文提出由两个十字形框架和八个粘弹性元件构成的新型被动动态步行器,介绍两种不同结构的VCRW,分析其步态特性并探讨其作为新型行走支撑装置的意义。

Comments This is a corrected version of the IROS 2022 paper. A typographical error in Eq. (14) has been corrected

Journal ref Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.17596 2026-04-14 cs.CV cs.AI cs.LG cs.RO

PRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Driving

PRIX:从原始像素学习计划以实现端到端自动驾驶

Maciej K. Wozniak, Lianhang Liu, Yixi Cai, Patric Jensfelt

机构 * KTH Royal Institute of Technology(瑞典皇家理工学院) SCANIA(斯堪尼亚)

AI总结 PRIX通过使用仅需摄像头数据的端到端驾驶架构,无需BEV表示和LiDAR,直接从原始像素预测安全轨迹,实现了高效且实用的自动驾驶解决方案。

Comments Accepted for Robotics and Automation Letters (RA-L) and will be presented at iROS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.00088 2026-04-14 cs.CV cs.RO

The Monado SLAM Dataset for Egocentric Visual-Inertial Tracking

用于第一人称视觉-惯性跟踪的Monado SLAM数据集

Mateo de Mayo, Daniel Cremers, Taihú Pire

机构 * Technical University of Munich(慕尼黑工业大学) Munich Center for Machine Learning(慕尼黑机器学习中心) Collabora Ltd.(Collabora有限公司) CIFASIS, CONICET-UNR

AI总结 本文提出Monado SLAM数据集,用于解决头戴式设备中高动态运动、动态遮挡等挑战性场景下的视觉-惯性里程计与SLAM问题。

Comments Accepted to IROS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.08258 2026-04-10 cs.RO

EvoGymCM: Harnessing Continuous Material Stiffness for Soft Robot Co-Design

EvoGymCM:利用连续材料刚度进行软机器人协同设计

Le Shen, Kangyao Huang, Wentao Zhao, Huaping Liu

机构 * College of Control Science and Engineering, Zhejiang University(浙江大学控制科学与工程学院) Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系)

AI总结 本文提出EvoGymCM平台,通过将连续材料刚度作为第一类设计变量,解决传统平台对材料维度的离散化限制,提升软机器人性能与协同效应。

Comments 8 pages, 11 figures. Preprint. Under review at IROS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.06341 2026-04-09 cs.RO

Occlusion Handling by Pushing for Enhanced Fruit Detection

通过推动提升水果检测的遮挡处理

Ege Gursoy, Dana Kulić, Andrea Cherubini

机构 * LIRMM, Univ. Montpellier, CNRS(蒙彼利埃大学-法国国家科学研究中心-蒙彼利埃机器人研究所) Monash University(莫纳什大学)

AI总结 本文提出通过推动清除遮挡物提升水果检测效果,结合深度学习、经典图像处理和3D霍夫变换实现遮挡处理。

Journal ref IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.09035 2026-04-09 cs.RO cs.AI cs.SY eess.SY

ManeuverGPT Agentic Control for Safe Autonomous Stunt Maneuvers

ManeuverGPT 代理控制用于安全的自动驾驶特技动作

Shawn Azdam, Pranav Doma, Aliasghar Moj Arab

机构 * New York University(纽约大学) Tandon School of Engineering, New York University(纽约大学坦登工程学院) General Autonomy Inc.(通用自主公司) Azdam AI

AI总结 本文提出ManeuverGPT框架,利用大语言模型代理生成并执行高动态特技动作,通过迭代提示法优化车辆控制参数,实现安全的J-turn等特技动作执行。

Comments 6 Pages, Submitted to IROS

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.05070 2026-04-08 cs.AI cs.CV cs.RO

Part-Level 3D Gaussian Vehicle Generation with Joint and Hinge Axis Estimation

基于关节和铰链轴估计的部件级3D高斯车辆生成

Shiyao Qian, Yuan Ren, Dongfeng Bai, Bingbing Liu

机构 * University of Toronto(多伦多大学)

AI总结 本文提出生成可动画的3D高斯车辆框架,解决静态生成与可动画车辆模型间的差距,通过部件边 refinement 和运动学推理头预测关节位置和铰链轴。

Comments submitted to IROS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.02657 2026-04-07 cs.RO

Watch Your Step: Learning Semantically-Guided Locomotion in Cluttered Environment

小心脚下:在杂乱环境中学习语义引导的运动

Denan Liang, Yuan Zhu, Ruimeng Liu, Thien-Minh Nguyen, Shenghai Yuan, Lihua Xie

机构 * School of Electrical and Electronic Engineering, Nanyang Technological University(南洋理工大学电气与电子工程学院) School of Mechanical and Mining Engineering, The University of Queensland(昆士兰大学机械与采矿工程学院)

AI总结 本文提出SemLoco框架,通过结合软硬约束的强化学习方法,在杂乱环境中精准避障,提升机器人安全导航能力。

Comments Submitted to IROS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏