arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

期刊&会议

IEEE RA-L

IEEE Robotics and Automation Letters · 期刊 · Robotics

至 收录 2226
2606.03545 2026-06-03 cs.RO

Static and Dynamic Representations for Tactile Contact-Angle Estimation with Event-Based Sensors

基于事件传感器的触觉接触角估计的静态与动态表示

Yanhui Lu, Efi Psomopoulou, Benjamin Ward-Cherrier

机构 * School of Engineering Mathematics and Technology, University of Bristol(布里斯托大学工程数学与科技学院)

AI总结 本文利用事件触觉传感器(NeuroTac)的事件流,比较了三种事件衍生的空间轮廓表示(动态、静态及其组合)用于接触角估计,并验证了其在机器人操作中实现高频、低延迟触觉角度估计的潜力。

Comments 8 pages, 8 figures. Submitted to IEEE Robotics and Automation Letters (RAL), under review

URL PDF HTML 收藏
2606.03047 2026-06-03 cs.RO cs.MA

ModuLoop : Low-Level Code Generation using Modular Synthesizer and Closed-Loop Debugger for Robotic Control

ModuLoop: 使用模块化合成器和闭环调试器进行机器人控制的低级代码生成

Gina Yoon, Sumin Lee, Joo Yong Sim

机构 * Department of Mechanical Systems Engineering, Sookmyung Women’s University(苏州市女子大学机械系统工程系)

AI总结 提出闭环模块化代码合成框架,利用预训练大语言模型进行模块化代码规划与生成,并通过迭代执行和调试探针实现系统调试与优化,成功应用于RGB-D相机与机械臂标定及抓取任务。

Comments IEEE Robotics and Automation Letters (2025)

URL PDF HTML 收藏
2606.02879 2026-06-03 cs.RO

Direct Informed Sampling on Riemannian Manifolds via Loewner Order Lower Bounds

基于Loewner序下界的黎曼流形直接知情采样

Phone Thiha Kyaw, Jonathan Kelly

机构 * Space and Terrestrial Autonomous Robotic Systems (STARS) Laboratory, University of Toronto Institute for Aerospace Studies (UTIAS)(太空与地面自主机器人系统实验室,多伦多大学航空航天研究所)

AI总结 提出一种利用Loewner序计算度量张量最紧常数下界的矩阵值可容许启发式,将黎曼知情集映射为各向同性欧氏空间中的标准长球超椭球,实现直接无拒绝采样,加速多种最优运动规划器收敛。

Comments Submitted to IEEE Robotics and Automation Letters (RA-L)

URL PDF HTML 收藏
2605.16816 2026-06-03 cs.RO

"I'm Not Mad, Just Focused'': Understanding Human Emotions in Human-Robot Collaboration

“我没生气,只是专注”:理解人机协作中的人类情绪

Seung Chan Hong, Dana Kulić, Leimin Tian

机构 * Faculty of Engineering, Monash University(莫纳什大学工程学院) CSIRO Robotics(CSIRO机器人实验室)

AI总结 提出基于视觉语言模型(VLM)的情绪识别系统,利用上下文理解改善人机协作中的情绪解读,实验表明其语义相似性和情感对齐优于基线CNN系统,且用户偏好情绪自适应机器人行为。

Journal ref IEEE Robotics and Automation Letters, vol. 11, no. 7, pp. 8260-8267, July 2026

URL PDF HTML 收藏
2512.09065 2026-06-02 cs.RO cs.AI

ShelfAware: Real-Time Semantic Localization in Quasi-Static Environments with Low-Cost Sensors

ShelfAware:准静态环境下基于低成本传感器的实时语义定位

Shivendra Agrawal, Jake Brawer, Ashutosh Naik, Alessandro Roncone, Bradley Hayes

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

AI总结 提出ShelfAware语义粒子滤波器,通过将场景语义建模为类别统计证据而非固定地标,结合深度似然与类别语义相似度,并利用预计算语义视角进行逆语义提议,实现低成本视觉硬件上的鲁棒全局定位。

Comments 8 pages

Journal ref IEEE Robotics and Automation Letters (RA-L), 2026

URL PDF HTML 收藏
2512.11571 2026-06-01 cs.RO

Cross-Entropy Optimization of Physically Grounded Task and Motion Plans

物理基础的任务与运动规划的交叉熵优化

Andreu Matoses Gimenez, Nils Wilde, Chris Pek, Javier Alonso-Mora

机构 * Department of Cognitive Robotics, Delft University of Technology(德鲁夫特理工大学认知机器人学系) Faculty of Computer Science, Dalhousie University(达尔豪斯大学计算机科学学院)

AI总结 提出利用GPU并行物理模拟器和交叉熵优化,通过采样控制器参数获得低成本解决方案,以解决传统TAMP算法忽略动力学和接触的问题。

Comments Accepted for publication in IEEE Robotics and Automation Letters (RA-L)

Journal ref IEEE Robotics and Automation Letters, 2026

URL PDF HTML 收藏
2503.21168 2026-06-01 cs.RO cs.SY eess.SY

TAGA: A Tangent-Based Reactive Approach for Socially Compliant Robot Navigation Around Human Groups

TAGA:一种基于切线的反应式方法,用于在人群体周围实现社交合规的机器人导航

Utsha Kumar Roy, Sejuti Rahman

机构 * Department of Computer Science and Engineering, BRAC University(布拉格大学计算机科学与工程系) New Uzbekistan University(新乌兹别克斯坦大学)

AI总结 提出TAGA方法,通过切线路径检测群体边界并协调群体与个体避障,引入群体穿越率(GCR)指标,在多种人群动力学模型下验证了反应式与学习型方法的非对称性效果。

Comments 8 pages, 3 figures, 3 tables. Submitted to IEEE Robotics and Automation Letters (RA-L)

URL PDF HTML 收藏
2605.29599 2026-05-29 cs.RO cs.CV

How to Relieve Distribution Shifts in Semantic Segmentation for Off-Road Environments

如何缓解越野环境语义分割中的分布偏移

Ji-Hoon Hwang, Daeyoung Kim, Hyung-Suk Yoon, Dong-Wook Kim, Seung-Woo Seo

机构 * Department of Electrical and Communication Engineering, Seoul National University(电子与通信工程系,首尔国立大学)

AI总结 提出ST-Seg框架,通过风格扩展和纹理正则化缓解越野场景中源-目标域差异和传感器退化导致的分布偏移,提升语义分割鲁棒性。

Comments 8 pages, 6 figures. Accepted to IEEE Robotics and Automation Letters (RA-L). \c{opyright} 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses

Journal ref IEEE Robotics and Automation Letters, vol. 10, issue. 5, pp. 4500-4507, 2025

URL PDF HTML 收藏
2605.27917 2026-05-28 cs.RO

A Surveillance Evasion Game with Continuous Sensor Redeployment via Bilevel Optimization

基于双层优化的连续传感器重新部署的监视规避博弈

Jaehyeok Kim, Kartik A. Pant, Joseph Kinerson, Kylie Sommer-Kohrt, Worawis Sribunma, Li-Yu Lin, James M. Goppert

机构 * School of Aeronautics and Astronautics, Purdue University(航空宇航学院,普渡大学)

AI总结 针对无人机利用传感器时空间隙渗透禁飞区的问题,提出通过双层优化实现传感器沿建筑边界连续滑动部署,并利用对数-求和-指数平滑近似保持可微性,最终收敛到局部纳什均衡。

Comments 8 pages, 8 figures, submitted to IEEE Robotics and Automation Letters (RA-L)

URL PDF HTML 收藏
2311.02304 2026-05-28 cs.RO

Imitating and Finetuning Model Predictive Control for Robust and Symmetric Quadrupedal Locomotion

模仿与微调模型预测控制实现鲁棒且对称的四足运动

Donghoon Youm, Hyunyoung Jung, Hyeongjun Kim, Jemin Hwangbo, Hae-Won Park, Sehoon Ha

机构 * Korea Advanced Institute of Science and Technology(韩国科学技术院) Georgia Institute of Technology(佐治亚理工学院)

AI总结 提出模仿与微调模型预测控制(IFM)框架,结合模型预测控制与模仿学习及强化学习,提升四足机器人在复杂地形上的运动性能、对称性和能效。

Journal ref IEEE Robotics and Automation Letters ( Volume: 8, Issue: 11, November 2023

URL PDF HTML 收藏
2605.25029 2026-05-27 cs.RO

ParkingWorld: End-to-End Autonomous Parking Reinforcement Learning from Corrective Experience in 3DGS Simulation

ParkingWorld: 基于3DGS仿真中纠正性经验的端到端自主泊车强化学习

Zhengcheng Yu, Changze Li, Haoran Liu, Tong Qin

机构 * Tsinghua University(清华大学) Shanghai Jiaotong University(上海交通大学)

AI总结 提出一种基于纠正性经验的样本高效强化学习框架(CIL-SERL),在逼真的3D高斯溅射(3DGS)仿真器中训练端到端自主泊车策略,通过多级回放缓冲区机制提高成功率、效率和安全性。

Comments 9 pages(including 1 page of Appendix), 6 figures. Will be submitted to RA-L 2026

URL PDF HTML 收藏
2605.25790 2026-05-26 cs.RO

HoLoArm: Deformable Arms for Collision-Tolerant Quadrotor Flight

HoLoArm: 用于碰撞容忍四旋翼飞行的可变形臂

Quang Ngoc Pham, Jonas Eschmann, Yang Zhou, Alejandro Ojeda Olarte, Giuseppe Loianno, Van Anh Ho

机构 * Japan Advanced Institute of Science and Technology(日本先进科学技术研究所) University of California Berkeley(加州大学伯克利分校) New York University(纽约大学)

AI总结 受蜻蜓翅膀结脉结构启发,提出具有柔性臂的四旋翼HoLoArm,结合强化学习控制策略实现被动变形与快速恢复,在高达7.6 m/s碰撞速度下保持稳定飞行。

Comments 8 pages, 15 figures, 1 table, Accepted at the IEEE Robotics and Automation Letters (RA-L) and the IEEE International Conference on Robotics and Automation (ICRA), 2026

Journal ref IEEE Robotics and Automation Letters, vol. 11, no. 3, pp. 3582-3589, March 2026

URL PDF HTML 收藏
2605.25646 2026-05-26 cs.RO

G-DRAGON: Geospatial Reasoning and Dynamic Planning for Retrieval-Augmented Outdoor Navigation

G-DRAGON:面向检索增强的户外导航的地理空间推理与动态规划

Dongzhihan Wang, Yi Du, Jianan Sun, Yuan Xue, Yingchen Zhang, Bing Xiao, Chen Wang, Liang Xu

机构 * Spatial AI & Robotics Lab(空间人工智能与机器人实验室) University at Buffalo(布法罗大学) School of Future Technology(未来技术学院) Shanghai University(上海大学) University of Chinese Academy of Sciences(中国科学院大学)

AI总结 提出G-DRAGON框架,通过轻量级LLM的生成式检索将自然语言命令映射到本地OSM实体,结合全局路径规划与SLAM系统,并利用前沿探索和开放集语义体素映射实现最后一英里目标定位,在仿真和真实场景中优于现有方法。

Comments Accepted by IEEE Robotics and Automation Letters (RA-L)

URL PDF HTML 收藏
2605.25423 2026-05-26 cs.RO

OPAL: Omnidirectional Path-efficient Aerial 3D expLoration

OPAL: 全方位路径高效空中三维探索

Yoga Satwik Chappidi, Avideh Zakhor

机构 * Department of Electrical Engineering and Computer Sciences, University of California, Berkeley(加州大学伯克利分校电子工程与计算机科学系)

AI总结 提出OPAL框架,通过在歧义分支点进行360度偏航旋转替代计算密集的全局路径规划,实现计算简单、路径短且覆盖率高的自主探索。

Comments Submitted to IEEE Robotics and Automation Letters (RA-L)

URL PDF HTML 收藏
2512.00375 2026-05-26 cs.RO

DPNet: Doppler LiDAR Motion Planning for Highly-Dynamic Environments

DPNet: 面向高动态环境的多普勒激光雷达运动规划

Wei Zuo, Zeyi Ren, Chengyang Li, Yikun Wang, Mingle Zhao, Shuai Wang, Wei Sui, Fei Gao, Yik-Chung Wu, Chengzhong Xu

机构 * The University of Hong Kong(香港大学) Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究所) University of Macau(澳门大学) D-Robotics Zhejiang University(浙江大学)

AI总结 提出DPNet,通过多普勒卡尔曼神经网络跟踪快速障碍物并利用多普勒调谐模型预测控制实现高动态环境下的高频高精度运动规划。

Comments Accepted to IEEE Robotics and Automation Letters in April, 2026

URL PDF HTML 收藏
2605.24449 2026-05-26 cs.RO cs.LG

Vision-Guided Outdoor Flight and Obstacle Evasion via Reinforcement Learning

基于强化学习的视觉引导户外飞行与避障

Shiladitya Dutta, Aayush Gupta, Varun Saran, Avideh Zakhor

机构 * College of Engineering, Department of Electrical Engineering and Computer Science, University of California Berkeley(加州大学伯克利分校工程学院电气工程与计算机科学系)

AI总结 提出一种基于立体视觉深度和视觉惯性里程计的传感器运动策略,通过强化学习和特权学习在仿真中训练,实现零样本迁移到未知户外环境和无人机平台进行自主避障导航。

Comments Published in IEEE Robotics and Automation Letters, vol 11, no 2. Presented at the IEEE International Conference on Robotics and Automation 2026

URL PDF HTML 收藏
2507.22345 2026-05-25 cs.RO

A Reconfigured Wheel-Legged Robot for Enhanced Steering and Adaptability

一种增强转向能力和适应性的重构轮腿机器人

Zhicheng Song, Jinglan Xu, Chunxin Zheng, Yulin Li, Zhihai Bi, Jun Ma

机构 * Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou)(机器人与自主系统方向,香港科技大学(广州))

AI总结 提出一种名为FLORES的新型轮腿机器人,通过将前腿的髋关节横滚自由度替换为偏航自由度,并设计定制强化学习控制器,实现了高效转向和多地形适应。

Journal ref IEEE Robotics and Automation Letters, vol. 11, no. 6, pp. 7444-7451, June 2026

URL PDF HTML 收藏
2605.22189 2026-05-22 cs.RO

Learning A Unified Risk Map for Autonomous Driving in Partially Observable Environments

在部分可观察环境中学习统一的风险图

Jie Jia, Yaofeng Su, Zeyu Bao, Yun Hong, Bingzhao Gao, Zhongxue Gan, Wenchao Ding

机构 * Fudan University(复旦大学) Tongji University(同济大学)

AI总结 本文提出了一种统一的风险图建模与学习框架,用于部分可观察环境中的自动驾驶,通过时空建模整合交通流风险和碰撞风险,以更精细地评估遮挡引起的危险,并引入扩散基场景生成框架来解决遮挡交互场景稀缺的问题,实验表明该方法在Waymo Open Motion Dataset上显著优于现有方法。

Comments Published in IEEE Robotics and Automation Letters

URL PDF HTML 收藏
2605.20392 2026-05-21 cs.RO

VBT-MPC: Vision-Based Tactile MPC for Contour Following

VBT-MPC:基于视觉的触觉MPC用于轮廓跟踪

Edison Velasco-Sanchez, Luis F. Recalde, Guanrui Li, Pablo Gil

机构 * AUROVA Lab, Computer Science Research Institute, University of Alicante(AUROVA实验室,计算机科学研究院,阿利坎特大学) Worcester Polytechnic Institute(沃思堡理工大学)

AI总结 本文提出了一种基于视觉的触觉模型预测控制(VBT-MPC)框架,用于机器人轮廓跟踪,通过眼在手配置安装的基于视觉的触觉传感器(VBTS)直接在轮廓特征空间中操作,避免了单独的姿态估计模块和复杂的力控制架构,并在仿真和实际实验中评估了在不同几何形状和材料物体上的轮廓跟踪性能。

Comments This article has been accepted for publication in IEEE Robotics and Automation Letters. This is a preprint version. This work was supported by the Interreg-VI Sudoe and European Regional Development Funds through the REMAIN Project under Grant S1/1.1/E0111

URL PDF HTML 收藏
2512.20931 2026-05-20 cs.RO

Certifiable Alignment of GNSS and Local Frames via Lagrangian Duality

通过拉格朗日对偶实现GNSS与局部框架的可验证对齐

Baoshan Song, Matthew Giamou, Penggao Yan, Chunxi Xia, Li-Ta Hsu

机构 * Department of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University, China(航空与航空工程系,香港理工大学,中国) Department of Computing and Software, McMaster University, Canada(计算与软件系,麦斯特大学,加拿大) School of Geodesy and Geomatics, Wuhan University, China(测绘学院,武汉大学,中国)

AI总结 本文提出了一种全局最优求解器,通过将原始伪距或多普勒测量转换为凸松弛问题,实现了GNSS与局部框架的可验证对齐,解决了传统方法在GNSS退化环境下的局限性。

Comments Final version in RA-L

URL PDF HTML 收藏
2408.06843 2026-05-20 cs.RO

Learn2Decompose: Learning Problem Decomposition for Efficient Sequential Multi-object Manipulation Planning

Learn2Decompose: 为高效连续多物体操作规划学习问题分解

Yan Zhang, Teng Xue, Amirreza Razmjoo, Sylvain Calinon

机构 * Idiap Research Institute(Idiap研究 institute) Ecole Polytechnique Fédérale de Lausanne(瑞士联邦理工学院洛桑分校)

AI总结 本文提出了一种高效的任务与运动重计划方法,用于动态环境中连续多物体操作的规划。通过从示范中学习问题分解来加速TAMP求解器,核心方法包括目标分解学习、计算距离学习和物体减少,有效提升了重计划效率。

Comments Extension of RAL version: added PR2 Whole-body kitchen task and detailed discussion on limitations in main text; added pseudocode and robustness analysis of our approach, and formal analysis on why and when task goals are decomposable in appendix

URL PDF HTML 收藏
2605.19556 2026-05-20 cs.CV

EpiDiffVO: Geometry-Aware Epipolar Diffusion for Robust Visual Odometry

EpiDiffVO: 一种基于几何的视差扩散用于鲁棒视觉里程计

Prateeth Rao

机构 * International Institute of Information Technology Bangalore(国际信息科技学院班加罗尔)

AI总结 本文提出了一种稀疏视差匹配框架,通过优化几何一致性来减少冗余,并结合视差扩散过程和图神经网络实现高效的视觉里程计。

Comments 8 pages, 5 figures, in revision to be submitted to IEEE RA-L

URL PDF HTML 收藏
2604.26450 2026-05-19 cs.RO

Reactive Motion Generation via Phase-varying Neural Potential Functions

通过相变神经势函数实现反应性运动生成

Ahmet Tekden, Dimitrios Kanoulas, Aude Billard, Yasemin Bekiroglu

机构 * Chalmers AI Research Center (CHAIR)(查尔姆斯人工智能研究中心(CHAIR)) Chalmers Gender Initiative for Excellence (Genie)(查尔姆斯卓越性别倡议(Genie)) Wallenberg AI, Autonomous Systems and Software Program (WASP)(瓦兰贝格人工智能、自主系统和软件计划(WASP)) University College London(伦敦大学学院) Ecole Polytechnique Federale de Lausanne (EPFL)(瑞士联邦理工学院(EPFL))

AI总结 本文提出了一种基于相变神经势函数(PNPF)的运动生成框架,通过直接从状态进展估计相变量来条件势函数,从而在点到点、周期性和全6D运动任务中实现更有效的泛化,并在有交点轨迹和外部干扰下表现出更强的鲁棒性。

Comments Accepted by IEEE Robotics and Automation Letters (RAL)

URL PDF HTML 收藏
2510.26018 2026-05-19 cs.RO cs.AI

RADRON: Cooperative Localization of Ionizing Radiation Sources by MAVs with Compton Cameras

RADRON:通过配备康普顿相机的微型飞行器进行离子化辐射源的协同定位

Petr Stibinger, Tomas Baca, Daniela Doubravova, Jan Rusnak, Jaroslav Solc, Jan Jakubek, Petr Stepan, Martin Saska

AI总结 该研究提出了一种利用微型飞行器协同定位放射性物质的新方法,通过康普顿相机实时估计辐射源位置,即使在稀疏测量条件下也能实现高灵敏度检测。

Comments 8 pages, 9 figures, submitted for review to IEEE RA-L

URL PDF HTML 收藏
2605.17556 2026-05-19 cs.RO cs.AI

Visual Sculpting: Visually-Aligned Planning Representations for Long-Horizon Robot Clay Sculpting

视觉雕刻:用于长周期机器人泥塑的视觉对齐规划表示

Peter Schaldenbrand, Jean Oh

机构 * The Robotics Institute, Carnegie Mellon University(卡内基梅隆大学机器人研究所)

AI总结 本文提出了一种视觉对齐的规划表示方法,用于长周期机器人泥塑任务,通过捕捉光照和纹理特征,提高了对可变形材料动态的建模能力,并展示了在不同可变形材料和末端执行器下的性能。

Comments 8 pages, 14 figures. Accepted for publication in IEEE Robotics and Automation Letters (RA-L)

URL PDF HTML 收藏
2504.14820 2026-05-19 cs.RO

A Visual Reinforcement Learning-Based Separate Primitive Policy for Peg-in-Hole Tasks

基于视觉强化学习的分步策略:用于铆钉入孔任务

Zichun Xu, Zhaomin Wang, Yuntao Li, Lei Zhuang, Zhiyuan Zhao, Guocai Yang, Jingdong Zhao

机构 * State Key Laboratory of Robotics and Systems, Harbin Institute of Technology(机器人系统国家重点实验室,哈尔滨工业大学) Ubtech Robotics(优必选科技) Meituan Academy of Robotics(美团机器人研究院) School of Mechanical Engineering, Shandong University(山东大学机械工程学院)

AI总结 本文提出S2P策略,通过视觉强化学习实现铆钉入孔任务中位置和插入动作的同步学习,提升了样本效率和成功率。

Comments Accepted for publication in IEEE Robotics and Automation Letters (RA-L)

URL PDF HTML 收藏
2506.14009 2026-05-19 cs.RO

GRaD-Nav++: Vision-Language Model Enabled Visual Drone Navigation with Gaussian Radiance Fields and Differentiable Dynamics

GRaD-Nav++: 基于视觉-语言模型的视觉无人机导航:高斯辐射场与可微动力学

Qianzhong Chen, Naixiang Gao, Suning Huang, JunEn Low, Timothy Chen, Jiankai Sun, Mac Schwager

机构 * Department of Mechanical Engineering, Stanford University(斯坦福大学机械工程系) Department of Aeronautics and Astronautics, Stanford University(斯坦福大学航空航天工程系)

AI总结 GRaD-Nav++提出一种轻量级视觉-语言-动作框架,通过可微强化学习在3D高斯点云模拟器中训练,实现基于自然语言指令的实时无人机导航,展示在多任务和多环境下的高效导航能力。

Comments Published in: IEEE Robotics and Automation Letters ( Volume: 11, Issue: 2, February 2026)

Journal ref Chen, Qianzhong, et al. "Grad-nav++: Vision-language model enabled visual drone navigation with gaussian radiance fields and differentiable dynamics." IEEE Robotics and Automation Letters 11.2 (2025): 1418-1425

URL PDF HTML 收藏
2601.09512 2026-05-18 cs.RO cs.LG

CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion

CLARE:通过自主适配器路由和扩展实现视觉-语言-动作模型的持续学习

Ralf Römer, Yi Zhang, Yuming Li, Angela P. Schoellig

机构 * Technical University of Munich(慕尼黑技术大学) TUM School of Computation, Information and Technology(TUM计算、信息与技术学院) Department of Computer Engineering, Learning Systems and Robotics Lab(计算机工程系、学习系统与机器人实验室) Munich Institute of Robotics and Machine Intelligence (MIRMI)(慕尼黑机器人与机器智能研究所(MIRMI)) Robotics Institute Germany(德国机器人研究所) Munich Center for Machine Learning(慕尼黑机器学习中心)

AI总结 CLARE提出一种参数高效、无需示例的持续学习框架,通过自主扩展模型模块,实现机器人在新任务中保持旧知识,优于基于示例的方法。

Comments Accepted to IEEE Robotics and Automation Letters 2026. Project page: https://tum-lsy.github.io/clare. 11 pages, 9 figures

URL PDF HTML 收藏
2605.15713 2026-05-18 cs.RO cs.AI

Learning Dynamic Pick-and-Place for a Legged Manipulator

学习动态抓取与放置用于四足机械臂

Moonkyu Jung, Jiseong Lee, Zhengmao He, Donghoon Youm, Juhyeok Mun, HyeongJun Kim, Hyunsik Oh, Donghyuk Choi, Jungwoo Hur, Jie Song, Jemin Hwangbo

机构 * Robotics and Artificial Intelligence Lab, KAIST(机器人与人工智能实验室,韩国科学技术院)

AI总结 本文提出一种分层强化学习框架,用于四足机械臂的动态抓取与放置任务,通过模拟和现实实验验证了其在不同负载和工作空间下的高成功率。

Comments Accepted to IEEE Robotics and Automation Letters 2026

Journal ref IEEE Robotics and Automation Letters, vol. 11, no. 6, pp. 7652-7659, 2026

URL PDF HTML 收藏
2605.15496 2026-05-18 cs.RO cs.CV

LAPS: Improving Incremental LiDAR Mapping using Active Pooling and Sampling for Neural Distance Fields

LAPS:利用主动池化和采样改进增量激光雷达映射

Dongjae Lee, Wooseong Yang, Yifu Tao, Maurice Fallon, Ayoung Kim

机构 * Department of Mechanical Engineering, Seoul National University(首尔国立大学机械工程系) Oxford Robotics Institute at the University of Oxford(牛津大学机器人研究所)

AI总结 LAPS通过主动池化和采样提升增量神经映射的回放管理,提高回放保留和分配,增强重建完整性与几何精度。

Comments accepted at RA-L 2026

URL PDF HTML 收藏