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
2607.06217 2026-07-08 cs.CV 新提交

EeveeDark: A Binary Neural Framework for Low-Light Video Enhancement via Event-Guided Sensor-Level Fusion

EeveeDark:一种通过事件引导的传感器级融合实现低光视频增强的二进制神经框架

Onur Eker, Erkut Erdem, Aykut Erdem

机构 * Department of Computer Engineering, Hacettepe University(哈杰泰佩大学计算机工程系) HAVELSAN Inc.(哈韦尔桑公司) Koc University Is Bank AI Center(科克大学伊希银行人工智能中心) Department of Computer Engineering, Koc University(科克大学计算机工程系)

AI总结 研究极端低光条件下视频增强难题,提出EeveeDark框架,结合传感器级RAW数据与事件流,采用二进制神经网络架构,含特定模态编码器、融合块和门控机制,实验证明其性能优于基于BNN的方法且兼顾效率。

Journal ref IEEE Robotics and Automation Letters, vol. 11, no. 4, pp. 4633-4640, Apr. 2026

URL PDF HTML 收藏
2604.20557 2026-07-08 cs.RO 版本更新

Passive Variable Impedance For Shared Control

被动可变阻抗用于共享控制

Maximilian Mühlbauer, Nepomuk Werner, Ribin Balachandran, Thomas Hulin, João Silvério, Freek Stulp, Alin Albu-Schäffer

机构 * German Aerospace Center (DLR), Robotics and Mechatronics Center(德国航空航天中心(DLR),机器人与机电中心)

AI总结 本文研究了共享控制中可变刚度和控制器仲裁的稳定性,通过加权叠加输出力矩实现整体框架,解决闭环系统中的被动性问题,验证了方法的有效性。

Comments submitted for publication at the IEEE Robotics and Automation Letters (RA-L)

URL PDF HTML 收藏
2511.03078 2026-07-07 cs.RO 版本更新

3D Cal: An Open-Source Software Library for Depth Reconstruction on Vision-Based Tactile Sensors

3D Cal:用于基于视觉的触觉传感器深度重建的开源软件库

Rohan Kota, Kaival Shah, J. Edward Colgate, Gregory Reardon

机构 * McCormick School of Engineering, Center for Robotics and Biosystems, Northwestern University(麦科姆ick工程学院,机器人与生物系统中心,西北大学)

AI总结 介绍3D Cal开源库,将低成本3D打印机变为自动探测设备,为校准基于视觉的触觉传感器生成大量标记训练数据,还提供端到端管道训练自定义卷积网络进行深度重建,给出校准准则并展示良好性能。

Comments Accepted for publication in IEEE Robotics and Automation Letters (RA-L). Project page: https://rohankotanu.github.io/3DCal/

URL PDF HTML 收藏
2606.28805 2026-07-02 cs.RO 版本更新

Physics Models for Sim-to-Real Transfer in Professional-Level Robot Table Tennis

面向专业级机器人乒乓球的仿真到现实迁移的物理模型

Christian Conti, Bilan Yang, Alexander Sigrist, Lorenzo Miele, Yamen Saraiji, Peter Dürr, Naoya Takahashi

机构 * Sony AI, Tokyo, Japan(索尼人工智能,东京,日本) Sony AI, Zürich, Switzerland(索尼人工智能,苏黎世,瑞士)

AI总结 提出空气动力学、球桌碰撞和球拍接触的物理模型,精确捕捉高速高旋球行为,首次训练出能与专业选手对战的机器人乒乓球AI智能体。

Comments 8 pages, 7 figures, additional information: https://ace.ai.sony/, Submitted to IEEE Robotics and Automation Letters (RA-L)

URL PDF HTML 收藏
2606.31941 2026-07-01 cs.RO cs.AI 新提交

LeCropFollow: Latent Space Planning for Navigation in Unstructured Crop Fields

LeCropFollow:非结构化农田中导航的潜在空间规划

Felipe Tommaselli, Francisco Affonso, Arthur Pompeu, Gianluca Capezzuto, Arun Narenthiran Sivakumar, Girish Chowdhary, Marcelo Becker

机构 * University of São Paulo(圣保罗大学) University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

AI总结 提出LeCropFollow框架,利用自监督语义热图和基于模型的强化学习规划器在潜在流形中优化轨迹,无需几何建模,实现从简化模拟到真实世界的零样本迁移,在玉米田间隙中语义故障减少2.4倍。

Comments 8 pages, 7 figures, 3 tables. Github Repo: https://github.com/Felipe-Tommaselli/lecropfollow

Journal ref IEEE Robotics and Automation Letters, 2026

URL PDF HTML 收藏
2606.31487 2026-07-01 cs.RO 新提交

Energy-Optimal Spatial Iterative Learning within a Virtual Tube

虚拟管道内的能量最优空间迭代学习

Chen Min, Shuli Lv, Pengda Mao, Huixin Cao, Li Hong, Quan Quan

机构 * School of Automation Science and Electrical Engineering, Beihang University(北京航空航天大学自动化科学与电气工程学院) Tianmushan Laboratory, Beihang University(北京航空航天大学天目山实验室)

AI总结 针对无人机续航受限问题,提出一种无模型在线迭代学习框架,通过O(n)复杂度的空间迭代优化降低能耗,在实验中比基于模型的IPOPT快50-60倍。

Comments 9 pages, 7 figures, submitted to RA-L

URL PDF HTML 收藏
2606.30817 2026-07-01 cs.RO 新提交

TAPE: Tether-Aware Path Planning for Autonomous Exploration of Unknown 3D Cavities Using a Tangle-Compatible Tethered Aerial Robot

TAPE:面向自主探索未知三维空腔的系绳感知路径规划,采用防缠绕系绳空中机器人

Louis Petit, Alexis Lussier Desbiens

机构 * Createk Design Lab, University of Sherbrooke(谢布克大学Createk设计实验室)

AI总结 提出一种两级分层路径规划方法,通过全局TSP最小化距离和局部可调决策函数平衡路径成本与系绳长度,实现未知三维空腔的自主探索,仿真和实地测试验证了有效性。

Comments 8 pages

Journal ref IEEE Robotics and Automation Letters, vol. 7, no. 4, pp. 10550-10557, 2022

URL PDF HTML 收藏
2603.05965 2026-07-01 cs.RO cs.CV 版本更新

PROBE: Probabilistic Occupancy BEV Encoding with Analytical Translation Robustness for 3D Place Recognition

PROBE: 具有解析平移鲁棒性的概率占用BEV编码用于3D地点识别

Jinseop Lee, Byoungho Lee, Gichul Yoo

机构 * SK Intellix

AI总结 提出无学习的LiDAR地点描述符PROBE,通过极坐标雅可比解析边缘化连续平移,实现距离自适应角度不确定性,在跨传感器泛化中取得高精度。

Comments 8 pages, 8 figures. Accepted for publication in IEEE Robotics and Automation Letters (RA-L). (c) 2026 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses

URL PDF HTML 收藏
2602.08653 2026-07-01 cs.RO 版本更新

High-Speed Vision-Based Flight in Clutter with Safety-Shielded Reinforcement Learning

基于安全盾牌强化学习的高速度视觉飞行在杂乱环境中

Jiarui Zhang, Chengyong Lei, Chengjiang Dai, Kenghou Hoi, Lijie Wang, Zhichao Han, Fei Gao

机构 * Institute of Cyber-Systems and Control, College of Control Science and Engineering, Zhejiang University(浙江大学控制科学与工程学院工业控制技术研究所) Differential Robotics(微分机器人)

AI总结 提出一种结合模型安全机制的端到端强化学习框架,通过物理信息奖励和实时安全滤波器实现高速飞行与严格避障,在杂乱环境和森林中速度达7.5 m/s。

Comments Published in IEEE Robotics and Automation Letters

Journal ref IEEE Robotics and Automation Letters, 2026

URL PDF HTML 收藏
2509.24575 2026-07-01 cs.RO cs.LG cs.MA 版本更新

Prompting Robot Teams with Natural Language

用自然语言提示机器人团队

Eduardo Sebastián, Nicolas Pfitzer, Ajay Shankar, Amanda Prorok

机构 * Department of Computer Science and Technology, University of Cambridge(剑桥大学计算机科学与技术系) Department of Mechanical and Process Engineering, ETH Zurich(苏黎世联邦理工学院机械与过程工程系)

AI总结 提出利用语言模型将高层任务分解为子任务,并蒸馏为循环神经网络(RNN)以支持多机器人团队的去中心化实时执行,通过图神经网络控制策略实现协作。

Comments This paper has been accepted for publication at IEEE Robotics and Automation Letters. Please, when citing the paper, refer to the official version

URL PDF HTML 收藏
2409.11972 2026-06-30 cs.RO cs.LG

Generation of Uncertainty-Aware High-Level Spatial Concepts in Factorized 3D Scene Graphs via Graph Neural Networks

通过图神经网络生成因子化3D场景图中的不确定性感知高层空间概念

Jose Andres Millan-Romera, Muhammad Shaheer, Miguel Fernandez-Cortizas, Martin R. Oswald, Holger Voos, Jose Luis Sanchez-Lopez

机构 * Automation and Robotics Research Group, Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg(卢森堡大学自动化与机器人研究组,安全、可靠性与信任跨学科研究中心(SnT))

AI总结 本文提出一种基于学习的方法,通过在线推断垂直平面中的空间概念,并将其作为SLAM后端可优化的因素,从而提升室内导航和映射的鲁棒性。

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

URL PDF HTML 收藏
2606.26928 2026-06-26 cs.RO cs.SI 新提交

UAV-MapFusion: RTK-Aligned Uncertainty-Aware Coarse-to-Fine Multi-Session UAV Mapping

UAV-MapFusion: RTK对齐的不确定性感知粗到细多会话无人机建图

Feng Pan, Chunran Zheng, Bing Xue, Yukang Cui, Jiayu Wen, Zhiyu Chen, Wei Wang

机构 * College of Automation, Harbin Engineering University(哈尔滨工程大学自动化学院) Department of Mechanical Engineering, University of Hong Kong(香港大学机械工程系) College of Mechatronics and Control Engineering, Shenzhen University(深圳大学机电与控制工程学院)

AI总结 提出一种不确定性感知的多会话点云地图合并与粗到细优化系统,通过RTK时空对齐和迭代平面因子优化,在抑制长距离漂移的同时保持局部几何精度。

Comments 8 pages, 5 figures, accepted by IEEE Robotics and Automation Letters (RA-L)

URL PDF HTML 收藏
2606.26341 2026-06-26 cs.RO 新提交

Scaling Nonlinear Optimization: Many Problems One GPU

扩展非线性优化:多问题单GPU

John Viljoen, Johanna Haffner, Masayoshi Tomizuka, Negar Mehr

机构 * Department of Mechanical Engineering, University of California, Berkeley(加州大学伯克利分校机械工程系) Department of Biosystems Science and Engineering, ETH Zürich(苏黎世联邦理工学院生物系统科学与工程系)

AI总结 提出首个基于JAX的GPU批处理NLP求解器jaxipm,通过异构迭代融合和迭代级批处理实现多问题并发求解,在四旋翼控制任务中吞吐量提升达32.85倍。

Comments 8 pages, 6 figures, ieeeconf style, submission for RA-L

URL PDF HTML 收藏
2603.15013 2026-06-26 cs.RO 版本更新

CycleRL: Sim-to-Real Deep Reinforcement Learning for Robust Autonomous Bicycle Control

CycleRL:面向鲁棒自主自行车控制的仿真到现实深度强化学习

Gelu Liu, Teng Wang, Zhijie Wu, Junliang Wu, Songyuan Li, Xiangwei Zhu

机构 * School of Electronics and Communication Engineering and Shenzhen Key Laboratory of Navigation and Communication Integration, Sun Yat-sen University(电子工程学院和深圳导航通信集成重点实验室,中山大学)

AI总结 提出CycleRL框架,利用高保真仿真环境和域随机化,通过PPO算法实现自主自行车的平衡、速度跟踪和转向控制,在仿真中达到99.90%平衡成功率,并成功迁移到真实硬件。

Comments 8 pages, 7 figures, 8 tables. Accepted for publication in IEEE Robotics and Automation Letters (L-RA). See: https://ieeexplore.ieee.org/document/11568521

Journal ref IEEE Robotics and Automation Letters, vol. 11, no. 8, pp. 9343-9350, 2026

URL PDF HTML 收藏
2602.13720 2026-06-26 cs.RO 版本更新

FC-Vision: Real-Time Visibility-Aware Replanning for Occlusion-Free Aerial Target Structure Scanning in Unknown Environments

FC-Vision:未知环境中无遮挡空中目标结构扫描的实时可见性感知重规划

Chen Feng, Yang Xu, Shaojie Shen

机构 * Dept. of Electronic and Computer Engineering, The Hong Kong University of Science and Technology(电子与计算机工程系,香港科学与技术大学)

AI总结 提出FC-Vision框架,通过双层分解(无遮挡视点修复和分段清洁感知连接)实时施加密集表面可见性约束,在保持覆盖率和效率的同时主动防止目标遮挡,实现55.32%的覆盖率提升和73.17%的遮挡率降低。

Comments Accepted by IEEE Robotics and Automation Letters. 8 pages, 8 figures, 3 tables. Code: https://github.com/FC-Family/FC-Vision. Video: https://www.youtube.com/watch?v=H3C42zlDOAI

URL PDF HTML 收藏
2606.25503 2026-06-25 cs.RO cs.CV 新提交

AISPO: Enhancing Depth Reliability for Robotic Manipulation of Non-Lambertian Objects via Affine-Invariant Shape Prior

AISPO: 通过仿射不变形状先验增强非朗伯体物体机器人操作的深度可靠性

Zhiming Chen, Linfang Zheng, Kun Zhang, Hyung Jin Chang, Wei Zhang, Hongyu Yu, Hua Chen

机构 * The Hong Kong University of Science & Technology(香港科技大学) The University of Hong Kong(香港大学) Southern University of Science & Technology(南方科技大学) Zhejiang University(浙江大学) LimX Dynamics

AI总结 提出AISPO深度补全框架,结合多尺度RGB-D特征融合与仿射不变形状先验,提升非朗伯体物体(如透明、高反光表面)的深度可靠性,显著提高机器人抓取成功率。

Comments Published in IEEE Robotics and Automation Letters. 8 pages. Accepted April 2026

Journal ref IEEE Robotics and Automation Letters, vol. 11, no. 7, pp. 7996-8003, July 2026

URL PDF HTML 收藏
2602.22733 2026-06-25 cs.RO

Pixel2Catch: Multi-Agent Sim-to-Real Transfer for Agile Manipulation with a Single RGB Camera

Pixel2Catch:基于单个RGB相机的多智能体仿真到现实迁移用于敏捷操作

Seongyong Kim, Junhyeon Cho, Kang-Won Lee, Soo-Chul Lim

机构 * Dongguk University(东国大学)

AI总结 本文提出Pixel2Catch方法,通过单个RGB相机提取像素级视觉信息,实现多智能体仿真到现实迁移,用于敏捷操作中的物体捕捉任务。

Journal ref IEEE Robotics and Automation Letters, vol. 11, no. 8, pp. 9287-9294, Aug. 2026

URL PDF HTML 收藏
2602.11575 2026-06-25 cs.RO cs.AI cs.CV 版本更新

ReaDy-Go: Real-to-Sim Dynamic 3D Gaussian Splatting Simulation for Environment-Specific Visual Navigation with Moving Obstacles

ReaDy-Go: 面向动态障碍物环境特定视觉导航的实到仿动态3D高斯泼溅仿真

Seungyeon Yoo, Youngseok Jang, Dabin Kim, Youngsoo Han, Seungwoo Jung, H. Jin Kim

机构 * Department of Aerospace Engineering, Seoul National University(首尔国立大学航空航天工程系) InnoCORE AI-Transformed Aerospace Research Center, KAIST(韩国科学技术院(KAIST)人工智能赋能航空航天研究中心)

AI总结 提出ReaDy-Go仿真管线,通过将静态3D高斯场景与动态人体高斯障碍物结合生成逼真动态场景,并训练导航策略,有效缩小仿真到现实的差距并处理移动障碍物。

Comments Accepted by IEEE Robotics and Automation Letters (RA-L). Project page: https://syeon-yoo.github.io/ready-go-site/

URL PDF HTML 收藏
2606.24767 2026-06-24 cs.CV cs.RO 新提交

Compact Object-Level Representations with Open-Vocabulary Understanding for Indoor Visual Relocalization

具有开放词汇理解的紧凑对象级表示用于室内视觉重定位

Zhaopeng Cui, Jiarui Hu, Jingbo Liu, Boming Zhao, Xiyue Guo, Boyin Feng, Haocheng Peng, Yujun Shen, Hujun Bao, Guofeng Zhang

机构 * State Key Lab of CAD&CG, Zhejiang University(浙江大学CAD&CG国家重点实验室) Ant Group(蚂蚁集团)

AI总结 提出OpenReLoc系统,利用基础模型实现多模态开放词汇语义匹配、基于DIOU的参考帧选择和双路径2D ICP损失,仅用对象单元实现室内视觉重定位,提升可解释性和准确性。

Comments Accepted by RA-L 2026

URL PDF HTML 收藏
2606.23293 2026-06-23 cs.CV cs.RO 新提交

Flow6D: Discrete-to-Continuous Flow Matching for Efficient and Accurate Category-Level 6D Pose Estimation

Flow6D: 离散到连续的流匹配用于高效且准确的类别级6D姿态估计

Mingyu Mei, Li Zhang, Zibo Dai, Han Sun, Xinyue Zhao, Huiliang Shen, Zaixing He

机构 * Zhejiang University(浙江大学) University of Science and Technology of China(中国科学技术大学) Shanghai Jiao Tong University(上海交通大学)

AI总结 提出Flow6D分层流匹配框架,通过两阶段离散潜空间定位-连续姿态回归策略,先离散化姿态参数并用离散流匹配缩小搜索空间,再连续流匹配预测局部残差优化姿态,在合成和真实数据集上以70 FPS实现实时推理,性能优于现有方法。

Comments Accepted for publication in IEEE Robotics and Automation Letters (RA-L), 2026

URL PDF HTML 收藏
2602.20466 2026-06-23 cs.RO

Grasp to Act: Dexterous Grasping for Tool Use in Dynamic Settings

抓取到动作:动态环境中的灵巧抓取与工具使用

Harsh Gupta, Mohammad Amin Mirzaee, Wenzhen Yuan

机构 * University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

AI总结 本文提出Grasp-to-Act系统,结合物理基抓取优化与强化学习适应,实现动态环境下稳定抓取。在五种动态工具使用任务中表现优异,减少手内滑动并提高任务完成率。

Comments Result videos can be found at https://grasp2act.github.io/

Journal ref IEEE Robotics and Automation Letters, 11(5):6288-6295, 2026

URL PDF HTML 收藏
2606.20428 2026-06-19 cs.RO 新提交

ARC: Adaptive Robust Joint State and Covariance Estimation

ARC:自适应鲁棒联合状态与协方差估计

Alexandre Hadji-Thomas, Andrew Stirling, James R. Forbes

AI总结 提出统一块坐标下降框架,结合自适应鲁棒损失、迭代重加权最小二乘状态更新和最小加权协方差行列式估计器,实现离群值下状态与协方差的自适应联合估计。

Comments Submitted to information IEEE Robotics and Automation Letters (RA-L), June 2026. 8 pages, 7 figures, 1 table

URL PDF HTML 收藏
2602.23172 2026-06-19 cs.CV cs.AI cs.RO 版本更新

Latent Gaussian Splatting for 4D Panoptic Occupancy Tracking

潜在高斯泼溅用于4D全景占据跟踪

Maximilian Luz, Rohit Mohan, Thomas Nürnberg, Yakov Miron, Daniele Cattaneo, Abhinav Valada

机构 * University of Freiburg(弗赖堡大学) Bosch Research(博世研究院) University of Haifa(海法大学)

AI总结 提出潜在高斯泼溅(LaGS)方法,通过特征高斯体作为动态关键点实现多视图特征聚合,用于4D全景占据跟踪,在Occ3D nuScenes和Waymo上达到最优性能。

Comments Accepted to IEEE Robotics and Automation Letters (RA-L), 2026

URL PDF HTML 收藏
2606.19233 2026-06-18 cs.RO 新提交

Mobile Pedipulation for Object Sliding via Hierarchical Control on a Wheeled Bipedal Robot

基于轮式双足机器人分层控制的移动式腿部操作物体滑动

Yue Qin, Yulun Zhuang, Zelin Shen, Yanran Ding

机构 * Department of Robotics, University of Michigan(密歇根大学机器人系)

AI总结 提出一种分层控制框架,使轮式双足机器人能用腿部滑动平面物体,通过简化三刚体动力学模型和轨迹优化运动规划器,在实验中成功实现1kg物体取回和4kg物体滑动。

Comments 8 pages, 7 figures

Journal ref IEEE Robotics and Automation Letters, vol. 11, no. 8, pp. 9787-9794, Aug. 2026

URL PDF HTML 收藏
2606.18948 2026-06-18 cs.RO 新提交

C-ARC: Continuous-Adaptive Range Clustering for Non-Repetitive LiDAR Sensors

C-ARC: 面向非重复式LiDAR传感器的连续自适应范围聚类

Nick B. Schroeder, Jonathan Lichtenfeld, Oskar von Stryk

机构 * Technical University of Darmstadt(德累斯顿技术大学) Simulation, Systems Optimization and Robotics Group(仿真、系统优化与机器人组)

AI总结 提出C-ARC框架,通过滑动窗口上的持久双图结构解耦高频点插入与按需聚类检索,并利用指数控制环自适应校准网格分辨率,实现非重复式LiDAR点云的实时聚类。

Comments Submitted to IEEE Robotics and Automation Letters. This work has been submitted to the IEEE for possible publication. 8 pages, 7 figures

URL PDF HTML 收藏
2506.17639 2026-06-17 cs.RO cs.AI 版本更新

RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models

RLRC:基于强化学习的压缩视觉-语言-动作模型恢复

Yuxuan Chen, Yixin Han, Yize Huang, Xiao Li

机构 * State Key Laboratory of Mechanical System and Vibration(机械系统与振动国家重点实验室) Shanghai Key Laboratory of Intelligent Robotics(上海智能机器人重点实验室) School of Mechanical Engineering, Shanghai Jiao Tong University(上海交通大学机械工程学院)

AI总结 提出RLRC三阶段压缩恢复流程,通过结构化剪枝、SFT和强化学习恢复以及量化,实现8倍内存减少和2.3倍推理加速,同时保持任务成功率。

Comments 8 pages, 10 figures; accepted by RA-L 2026

Journal ref IEEE Robotics and Automation Letters, vol. 11, no. 7, pp. 8864-8871, July 2026

URL PDF HTML 收藏
2606.16888 2026-06-16 cs.RO 新提交

LOPAL: Local Performance-Aware Active Learning from Imperfect Demonstrations

LOPAL:基于局部性能感知的不完美演示主动学习

Johannes Heidersberger, Shail Jadav, Dongheui Lee

机构 * Autonomous Systems Lab, Institute of Computer Technology, TU Wien(维也纳工业大学计算机技术研究所自主系统实验室) Institute of Robotics and Mechatronics, German Aerospace Center (DLR)(德国航空航天中心机器人与机电一体化研究所)

AI总结 提出LOPAL方法,利用局部演示质量信息,通过高斯混合模型编码轨迹与质量评估,结合共享自主权主动收集纠正数据,在不完美演示中提升任务性能。

Comments Accepted for publication in IEEE Robotics and Automation Letters (RAL), 2026

URL PDF HTML 收藏
2606.16474 2026-06-16 cs.CV cs.RO 新提交

MVOFormer: Flow-Semantic Transformer for Robust Monocular Visual Odometry

MVOFormer:用于鲁棒单目视觉里程计的流-语义Transformer

Jituo Li, Shunwang Sun, Jialu Zhang, Xinqi Liu, Jinyao Hu, Zhicheng Lu, Sajad Saeedi, Guodong Lu

机构 * State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University(浙江大学流体动力与机电系统国家重点实验室) Zhejiang Key Laboratory of Industrial Big Data and Robot Intelligent Systems(浙江省工业大数据与机器人智能系统重点实验室) School of Mechanical Engineering, Zhejiang University(浙江大学机械工程学院) Robotics Institute, Zhejiang University(浙江大学机器人研究院) School of Artificial Intelligence and Robotics, Hunan University(湖南大学人工智能与机器人学院) Rural Health Research Institute, Charles Sturt University(查尔斯特大学农村健康研究所) University College London(伦敦大学学院)

AI总结 提出MVOFormer,一种流-语义双分支编码器与迭代多模态解码器结合的Transformer框架,通过融合密集几何运动与语义先验实现粗到细位姿优化,在零样本泛化上显著超越现有方法。

Comments 8 pages, 6 figures. Accepted for publication in IEEE Robotics and Automation Letters (RA-L)

URL PDF HTML 收藏
2606.16232 2026-06-16 cs.RO 新提交

PolyMerge: Compressing 3D Gaussian Splats with Polytope Coverings for Provably Safe Resource-Constrained Navigation

PolyMerge: 用多面体覆盖压缩3D高斯泼溅以实现可证明安全的资源受限导航

Jihoon Hong, Chih-Yuan Chiu, Sara Fridovich-Keil, Glen Chou

机构 * Georgia Institute of Technology(佐治亚理工学院)

AI总结 提出PolyMerge,将大规模3D高斯泼溅模型转换为凸多面体覆盖,保证覆盖原模型所有障碍物,结合控制障碍函数实现实时安全路径规划,在Crazyflie无人机上验证。

Journal ref IEEE Robotics and Automation Letters, vol. 11, no. 7, pp. 8512-8519, July 2026

URL PDF HTML 收藏
2603.07920 2026-06-16 cs.CV 版本更新

RLPR: Radar-to-LiDAR Place Recognition via Two-Stage Asymmetric Cross-Modal Alignment for Autonomous Driving

RLPR:面向自动驾驶的两阶段非对称跨模态对齐雷达-激光雷达地点识别

Zhangshuo Qi, Jingyi Xu, Luqi Cheng, Shichen Wen, Guangming Xiong

机构 * Beijing Institute of Technology(北京理工大学) Shanghai Jiaotong University(上海交通大学)

AI总结 提出RLPR框架,通过双流网络提取结构特征,并利用两阶段非对称跨模态对齐策略,实现雷达与激光雷达之间的鲁棒地点识别,在四个数据集上达到最优性能。

Comments Accepted by IEEE Robotics and Automation Letters (RA-L) 2026

URL PDF HTML 收藏