IEEE Robotics and Automation Letters最新文献_第7页

VIRAA-SLAM: Flexible Robust Visual-Inertial-Range-AOA Tightly-Coupled Localization VIRAA-SLAM：柔性鲁棒视觉-惯性距离- aoa紧密耦合定位

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-09-04 DOI: 10.1109/LRA.2025.3606384

Xingyu Ma;Ningyan Guo;Rui Xin;Zhigang Cen;Zhiyong Feng

{"title":"VIRAA-SLAM: Flexible Robust Visual-Inertial-Range-AOA Tightly-Coupled Localization","authors":"Xingyu Ma;Ningyan Guo;Rui Xin;Zhigang Cen;Zhiyong Feng","doi":"10.1109/LRA.2025.3606384","DOIUrl":"https://doi.org/10.1109/LRA.2025.3606384","url":null,"abstract":"In this letter, we propose a novel tightly-coupled fusion framework for robust and accurate long-term localization in fast-motion scenarios, integrating a monocular camera, a 6-DoF inertial measurement unit (IMU), and multiple position-unknown ultra-wideband (UWB) anchors. Unlike existing UWB fusion methods that rely on pre-calibrated anchors' positions, our approach leverages the relative UWB-derived angle and ranging measurements to constrain relative frame-to-frame relationships within a sliding window. These constraints are converted into priors through marginalization, significantly simplifying system complexity and the fusion process. Crucially, our method eliminates the need for the anchors' location estimations, supports an arbitrary number of anchors, and maintains robustness even under prolonged visual degradation. Experimental validation includes a challenging scenario where visual data is discarded between 15–60 seconds, demonstrating sustained operation without vision. Accuracy evaluations confirm that our method achieves superior performance compared to VINS-Mono, highlighting its precision and resilience in dynamic environments.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 10","pages":"10658-10665"},"PeriodicalIF":5.3,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145050785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing Reusability of Learned Skills for Robot Manipulation via Gaze Information and Motion Bottlenecks 通过注视信息和运动瓶颈增强机器人操作学习技能的可重用性

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-09-04 DOI: 10.1109/LRA.2025.3606390

Ryo Takizawa;Izumi Karino;Koki Nakagawa;Yoshiyuki Ohmura;Yasuo Kuniyoshi

引用次数: 0

Push-Grasp Policy Learning Using Equivariant Models and Grasp Score Optimization 使用等变模型和把握分数优化的推抓策略学习

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-09-04 DOI: 10.1109/LRA.2025.3606392

Boce Hu;Heng Tian;Dian Wang;Haojie Huang;Xupeng Zhu;Robin Walters;Robert Platt

{"title":"Push-Grasp Policy Learning Using Equivariant Models and Grasp Score Optimization","authors":"Boce Hu;Heng Tian;Dian Wang;Haojie Huang;Xupeng Zhu;Robin Walters;Robert Platt","doi":"10.1109/LRA.2025.3606392","DOIUrl":"https://doi.org/10.1109/LRA.2025.3606392","url":null,"abstract":"Goal-conditioned robotic grasping in cluttered environments remains a challenging problem due to occlusions caused by surrounding objects, which prevent direct access to the target object. A promising solution to mitigate this issue is combining pushing and grasping policies, enabling active rearrangement of the scene to facilitate target retrieval. However, existing methods often overlook the rich geometric structures inherent in such tasks, thus limiting their effectiveness in complex, heavily cluttered scenarios. To address this, we propose the Equivariant Push-Grasp Network, a novel framework for joint pushing and grasping policy learning. Our contributions are twofold: (1) leveraging <inline-formula><tex-math>$text{SE}(2)$</tex-math></inline-formula>-equivariance to improve both pushing and grasping performance and (2) a grasp score optimization-based training strategy that simplifies the joint learning process. Experimental results show that our method improves grasp success rates by 45% in simulation and by 35% in real-world scenarios compared to strong baselines, representing a significant advancement in push-grasp policy learning.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 11","pages":"11180-11187"},"PeriodicalIF":5.3,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145090037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Multimodal Dual-Segment Soft Robot With Ground-to-Ceiling Transition 具有从地到顶过渡的多模态双分段软机器人

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-09-02 DOI: 10.1109/LRA.2025.3605092

Ruiyong Yuan;Kai Huang;Chengxiao Ying;Yanmiao Hu;Zihao Yuan;Feifei Chen

{"title":"A Multimodal Dual-Segment Soft Robot With Ground-to-Ceiling Transition","authors":"Ruiyong Yuan;Kai Huang;Chengxiao Ying;Yanmiao Hu;Zihao Yuan;Feifei Chen","doi":"10.1109/LRA.2025.3605092","DOIUrl":"https://doi.org/10.1109/LRA.2025.3605092","url":null,"abstract":"Although various soft robots with remarkable mobility have been developed, enabling a single robot to achieve multi-terrain locomotion with transitions across ground, vertical walls, and ceilings remains a formidable challenge. This letter presents a multimodal dual-segment soft robot capable of omnidirectional terrestrial locomotion, vertical climbing and ceiling crawling, and smooth inter-surface transitioning. The robot's wall and ceiling locomotion ability is realized through improved segment design featuring lightweight construction, enhanced deformability and load capacity, whereas its transitional capability is facilitated by coordinated dual-segmental gaits and compensation of gravity-induced deformation. Through cross-sectional improvement, the redesigned segment demonstrates enhanced bending capability with a maximum bending angle exceeding 180<inline-formula><tex-math>$^{circ }$</tex-math></inline-formula>, achieving a 105% workspace expansion compared to the baseline design. Experimental characterization reveals performance metrics of the robot: a maximum terrestrial velocity of 33.2 mm/s, angular turning rate of 30<inline-formula><tex-math>$^{circ }$</tex-math></inline-formula>/s, and transition capability while carrying 50 g payload. Furthermore, we demonstrate the robot's practical utility by integrating an onboard camera to successfully execute multi-surface inspection tasks in confined space and aircraft wing cavity, validating its potential for deployment in real-world unstructured environments.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 10","pages":"10729-10736"},"PeriodicalIF":5.3,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145050814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Minimum-Length Coverage Path Planning for Grid Environments With Approximation Guarantees 具有近似保证的网格环境的最小长度覆盖路径规划

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-09-02 DOI: 10.1109/LRA.2025.3604732

Megnath Ramesh;Frank Imeson;Baris Fidan;Stephen L. Smith

{"title":"Minimum-Length Coverage Path Planning for Grid Environments With Approximation Guarantees","authors":"Megnath Ramesh;Frank Imeson;Baris Fidan;Stephen L. Smith","doi":"10.1109/LRA.2025.3604732","DOIUrl":"https://doi.org/10.1109/LRA.2025.3604732","url":null,"abstract":"We focus on planning minimum-length robot paths to cover environments using the robot's sensor or coverage (e.g., cleaning) tool. Many algorithms use the following framework: (i) compute a grid decomposition of the environment, (ii) partition the grid to be covered by non-overlapping <italic>coverage lines</i> (straight-line paths), and (iii) compute a cost-minimizing tour of the coverage lines to get a coverage path. While this framework aims to minimize turns in the path, it does not yield guarantees on the resulting path length. In this letter, we show that this framework guarantees a coverage path of length <inline-formula><tex-math>$(1 + 1.5gamma)$</tex-math></inline-formula> times the optimal, where <inline-formula><tex-math>$gamma > 1$</tex-math></inline-formula> is the approximation factor to solve the metric traveling salesman problem (metric-TSP). Following this, we propose the Minimum Length Coverage Approx (MLC-Approx) approach that modifies this framework to achieve an approximation factor of <inline-formula><tex-math>$(1.5 + epsilon)$</tex-math></inline-formula>, where <inline-formula><tex-math>$epsilon ll 1$</tex-math></inline-formula> depends on the number of coverage lines. Instead of computing a tour of the coverage lines, MLC-Approx merges minimum-length <italic>sub-tours</i> of coverage lines while minimizing the turns added by the merges. We also propose a lazy variation of MLC-Approx that achieves the same result with faster empirical runtime. We validate MLC-Approx in simulations using maps of real-world environments and compare against state-of-the-art CPP approaches.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 10","pages":"10674-10681"},"PeriodicalIF":5.3,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145051018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Active Learning Design: Modeling Force Output for Axisymmetric Soft Pneumatic Actuators 主动学习设计：轴对称软气动执行器的力输出建模

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-09-02 DOI: 10.1109/LRA.2025.3605089

Gregory M. Campbell;Gentian Muhaxheri;Leonardo Ferreira Guilhoto;Christian D. Santangelo;Paris Perdikaris;James Pikul;Mark Yim

{"title":"Active Learning Design: Modeling Force Output for Axisymmetric Soft Pneumatic Actuators","authors":"Gregory M. Campbell;Gentian Muhaxheri;Leonardo Ferreira Guilhoto;Christian D. Santangelo;Paris Perdikaris;James Pikul;Mark Yim","doi":"10.1109/LRA.2025.3605089","DOIUrl":"https://doi.org/10.1109/LRA.2025.3605089","url":null,"abstract":"Soft pneumatic actuators (SPA) made from elastomeric materials can provide large strain and large force. The behavior of locally strain-restricted hyperelastic materials under inflation has been investigated thoroughly for shape reconfiguration, but requires further investigation for trajectories involving external force. In this work we model force-pressure-height relationships for a concentrically strain-limited class of soft pneumatic actuators and demonstrate the use of this model to design SPA response for object lifting. We predict relationships under different loadings by solving energy minimization equations and verify this theory by using an automated test rig to collect rich data for n = 22 Ecoflex 00-30 membranes. We collect data using an active learning pipeline to efficiently model the design space. We show that this learned model outperforms the theory-based model and a naive regression. We use our model to optimize membrane design for different lift tasks and compare this performance to other designs. These contributions represent a step towards understanding the natural response for this class of actuator and embodying intelligent lifts in a single-pressure input actuator system.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 10","pages":"10838-10845"},"PeriodicalIF":5.3,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145036789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

RESPLE: Recursive Spline Estimation for LiDAR-Based Odometry 基于激光雷达测程的递归样条估计

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-09-02 DOI: 10.1109/LRA.2025.3604758

Ziyu Cao;William Talbot;Kailai Li

引用次数: 0

BiFlex: A Passive Bimodal Stiffness Flexible Wrist for Manipulation in Unstructured Environments BiFlex：一种用于非结构化环境操作的被动双峰刚度柔性手腕

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-09-02 DOI: 10.1109/LRA.2025.3605095

Gu-Cheol Jeong;Stefano Dalla Gasperina;Ashish D. Deshpande;Lillian Chin;Roberto Martín-Martín

{"title":"BiFlex: A Passive Bimodal Stiffness Flexible Wrist for Manipulation in Unstructured Environments","authors":"Gu-Cheol Jeong;Stefano Dalla Gasperina;Ashish D. Deshpande;Lillian Chin;Roberto Martín-Martín","doi":"10.1109/LRA.2025.3605095","DOIUrl":"https://doi.org/10.1109/LRA.2025.3605095","url":null,"abstract":"Robotic manipulation in unstructured, human-centric environments poses a dual challenge: achieving the precision need for delicate free-space operation while ensuring safety during unexpected contact events. Traditional wrists struggle to balance these demands, often relying on complex control schemes or complicated mechanical designs to mitigate potential damage from force overload. In response, we present BiFlex, a flexible robotic wrist that uses a soft buckling honeycomb structure to provide a natural bimodal stiffness response. The higher stiffness mode enables precise household object manipulation, while the lower stiffness mode provides the compliance needed to adapt to external forces. We design BiFlex to maintain a fingertip deflection of less than 1 cm while supporting loads up to 500 g and create a BiFlex wrist for many grippers, including Panda, Robotiq, and BaRiFlex. We validate BiFlex under several real-world experimental evaluations, including surface wiping, precise pick-and-place, and grasping under environmental constraints. We demonstrate that BiFlex simplifies control while maintaining precise object manipulation and enhanced safety in real-world applications.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 10","pages":"10783-10790"},"PeriodicalIF":5.3,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145036782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimal Design of Integrated Aerial Platforms With Passive Joints 带被动接头的综合航空平台优化设计

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-09-02 DOI: 10.1109/LRA.2025.3604735

Yushu Yu;Kaidi Wang;Xin Meng;Jianrui Du;Jiali Sun;Ganghua Lai;Yibo Zhang

{"title":"Optimal Design of Integrated Aerial Platforms With Passive Joints","authors":"Yushu Yu;Kaidi Wang;Xin Meng;Jianrui Du;Jiali Sun;Ganghua Lai;Yibo Zhang","doi":"10.1109/LRA.2025.3604735","DOIUrl":"https://doi.org/10.1109/LRA.2025.3604735","url":null,"abstract":"The Integrated Aerial Platform (IAP) uses multiple quadrotor sub-vehicles, acting as independent thrust generators, connected to a central platform via passive joints. This setup allows the sub-vehicles to collectively apply forces and torques to the central platform, achieving full six-degree-of-freedom (6-DoF) motion through coordinated thrust and posture adjustments. The IAP's modular design offers significant advantages in terms of mechanical simplicity, reconfigurability for diverse scenarios, and enhanced mission adaptability. This letter presents a comprehensive framework for IAP modeling and optimal design. We introduce a “design matrix” that encapsulates key architectural parameters, including the number of sub-vehicles, their spatial configuration, and the types of passive joints used. To improve control performance and ensure balanced wrench generation capabilities, we propose an optimized design strategy that minimizes the condition number of this design matrix. Two distinct IAP configurations were optimally designed based on two typical application scenarios. The efficacy of the proposed optimization methodology was subsequently validated through comparative analysis against unoptimized platforms. Moreover, the full actuation capability of the IAP was empirically confirmed via extensive simulations and real-world flight experiments, which also demonstrated its operational performance through direct wrench control experiment.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 10","pages":"10538-10545"},"PeriodicalIF":5.3,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144998156","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Shaping Collective Behaviors in Swarm Robotics Through Probabilistic Motion Decision-Making 基于概率运动决策的群体机器人群体行为塑造

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-09-02 DOI: 10.1109/LRA.2025.3604751

Zhicheng Zheng;Tao Wang;Yalun Xiang;Xiaokang Lei;Xingguang Peng

引用次数: 0