IEEE Robotics and Automation Letters最新文献_第10页

Interactive Distance Field Mapping and Planning to Enable Human-Robot Collaboration 交互式距离场绘图和规划，实现人机协作

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2024-10-16 DOI: 10.1109/LRA.2024.3482128

Usama Ali;Lan Wu;Adrian Müller;Fouad Sukkar;Tobias Kaupp;Teresa Vidal-Calleja

{"title":"Interactive Distance Field Mapping and Planning to Enable Human-Robot Collaboration","authors":"Usama Ali;Lan Wu;Adrian Müller;Fouad Sukkar;Tobias Kaupp;Teresa Vidal-Calleja","doi":"10.1109/LRA.2024.3482128","DOIUrl":"https://doi.org/10.1109/LRA.2024.3482128","url":null,"abstract":"Human-robot collaborative applications require scene representations that are kept up-to-date and facilitate safe motions in dynamic scenes. In this letter, we present an interactive distance field mapping and planning (IDMP) framework that handles dynamic objects and collision avoidance through an efficient representation. We define \u0000<italic>interactive</i>\u0000 mapping and planning as the process of creating and updating the representation of the scene online while simultaneously planning and adapting the robot's actions based on that representation. The key aspect of this work is an efficient Gaussian Process field that performs incremental updates and handles dynamic objects reliably by identifying moving points via a simple and elegant formulation based on queries from a temporary latent model. In terms of mapping, IDMP is able to fuse point cloud data from single and multiple sensors, query the free space at any spatial resolution, and deal with moving objects without semantics. In terms of planning, IDMP allows seamless integration with gradient-based reactive planners facilitating dynamic obstacle avoidance for safe human-robot interactions. Our mapping performance is evaluated on both real and synthetic datasets. A comparison with similar state-of-the-art frameworks shows superior performance when handling dynamic objects and comparable or better performance in the accuracy of the computed distance and gradient field. Finally, we show how the framework can be used for fast motion planning in the presence of moving objects both in simulated and real-world scenes.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"10850-10857"},"PeriodicalIF":4.6,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142518205","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

Dual-Alignment Domain Adaptation for Pedestrian Trajectory Prediction 用于行人轨迹预测的双对齐域自适应技术

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2024-10-15 DOI: 10.1109/LRA.2024.3481831

Wenzhan Li;Fuhao Li;Xinghui Jing;Pingfa Feng;Long Zeng

{"title":"Dual-Alignment Domain Adaptation for Pedestrian Trajectory Prediction","authors":"Wenzhan Li;Fuhao Li;Xinghui Jing;Pingfa Feng;Long Zeng","doi":"10.1109/LRA.2024.3481831","DOIUrl":"https://doi.org/10.1109/LRA.2024.3481831","url":null,"abstract":"Predicting the plausible future paths of pedestrians is essential for human-involved applications (e.g., autonomous driving and service robotics). Existing pedestrian trajectory prediction methods mainly focus on the performance of multi-scene trained models in single-scene tests, neglecting the cross-scene knowledge differences in practice. To address this issue, we propose a generic dual-alignment framework for pedestrian trajectory prediction. Concretely, we analyze the domain difference at macro and micro scales and mitigate them respectively: at macro scale, an attention-based temporal convolutional generative model transfers the paths of pedestrians and their interaction information from the source domain to the target domain to align the data-level distributions; at micro scale, an auxiliary adversarial network is integrated to assist in training the prediction network to align the feature-level domain-invariant knowledge. Cross-domain experiments demonstrate that our approach significantly improves the performance of existing pedestrian trajectory prediction benchmarks (up to 53.5%) and outperforms previous domain adaptive works (up to 41.7%).","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"10962-10969"},"PeriodicalIF":4.6,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565509","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

Cut, Bond and Play: Volume-Preserved Reprogrammable Soft Pneumatic Actuators 切割、粘合和播放：体积保存型可重新编程软气动执行器

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2024-10-15 DOI: 10.1109/LRA.2024.3477170

Tao Wang;Qian Liu;Xi Wang;Guoqiang Fu;Caijiang Lu;Bo Li;Jinhua Zhang

{"title":"Cut, Bond and Play: Volume-Preserved Reprogrammable Soft Pneumatic Actuators","authors":"Tao Wang;Qian Liu;Xi Wang;Guoqiang Fu;Caijiang Lu;Bo Li;Jinhua Zhang","doi":"10.1109/LRA.2024.3477170","DOIUrl":"https://doi.org/10.1109/LRA.2024.3477170","url":null,"abstract":"Reprogrammable design enables soft actuators to change their performances after fabrication and obtain new deformation modes and functions. The reprogrammable design of soft pneumatic actuators is relatively difficult due to the intrinsic material being chemically inactive. This work proposes a new design concept for reprogrammable soft pneumatic actuators via volume-preserving cutting and bonding (VPCB) of solid silicone materials. The design concept and fabrication are presented to show the reprogramming process. As a result of VPCB, the incision becomes a key structural feature of this type of actuator, and the influence of its parameters on the deformation and blocking forces have been investigated. Simulation and experimental results show the large strain and nonlinear characteristics of these actuators. Then a ternary quadratic polynomial is chosen as the fitting model to fit the relationship between the deformation and the incision parameters within a prescribed pressure level and parameter range. And a multi-objective optimization based inverse design framework for this type of actuator is constructed. With the reprogrammable design and the inverse design framework, four real-life scenarios are chosen as the target configuration to verify the feasibility of the proposed design concept experimentally. The proposed VPCB design concept presents a new way for the reprogrammable design of soft pneumatic actuators, which does not involve external constraint structures and can always maintain the versatile of these actuators. It will provide inspiration for the development of new soft pneumatic actuators.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 11","pages":"10605-10611"},"PeriodicalIF":4.6,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142447074","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 Novel Assistive Imaging Device for Colon Map Reconstruction 用于结肠地图重建的新型辅助成像设备

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2024-10-14 DOI: 10.1109/LRA.2024.3479704

Neri Niccolò Dei;Sophia Bano;Francisco Vasconcelos;Vanni Consumi;Danail Stoyanov;Agostino Stilli;Gastone Ciuti

{"title":"A Novel Assistive Imaging Device for Colon Map Reconstruction","authors":"Neri Niccolò Dei;Sophia Bano;Francisco Vasconcelos;Vanni Consumi;Danail Stoyanov;Agostino Stilli;Gastone Ciuti","doi":"10.1109/LRA.2024.3479704","DOIUrl":"https://doi.org/10.1109/LRA.2024.3479704","url":null,"abstract":"Colonoscopy, recognised as the gold standard for diagnosing and treating colorectal cancer, faces limitations that may result in overlooking some colonic regions. This can lead to missed lesions and interval cancer, leading to incomplete treatment. Addressing this challenge, the authors present a novel Assistive Imaging Device for Colon Map Reconstruction (AID-CMR) to support clinicians in visualising the entire colonic mucosa and identifying areas that may have been missed during the procedure. The device is comprised of an overtube tooled with an imaging module on its distal end, which can be moved about a threaded silicone sleeve. The imaging module houses inflatable silicone chambers to distend the lumen, a side-viewing miniaturised full-HD camera with LEDs, a magnetic encoder, and an irrigation channel for camera cleansing. Before intervention, the device can be installed on standard colonoscopes or other tethered endoscopes. During the intervention, the device can be operated to (1) reconstruct assistive maps of the organ, (2) visualise the full anatomy, and (3) increase disease detection. Moreover, these maps may be employed for the quantification of missed regions during standard inspection. This letter introduces a proof of concept device and discusses locomotion and reconstruction tests conducted in two in-vitro conditions. These tests reveal overall procedural feasibility in terms of locomotion, exerted forces and colon map reconstruction, preserving polyp morphology.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"10780-10787"},"PeriodicalIF":4.6,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10715569","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142452696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Thermal Chameleon: Task-Adaptive Tone-Mapping for Radiometric Thermal-Infrared Images 热变色龙：辐射热红外图像的任务自适应色调映射

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2024-10-14 DOI: 10.1109/LRA.2024.3479700

Dong-Guw Lee;Jeongyun Kim;Younggun Cho;Ayoung Kim

引用次数: 0

SGBA: Semantic Gaussian Mixture Model-Based LiDAR Bundle Adjustment SGBA：基于语义高斯混杂模型的激光雷达捆绑调整

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2024-10-14 DOI: 10.1109/LRA.2024.3479699

Xingyu Ji;Shenghai Yuan;Jianping Li;Pengyu Yin;Haozhi Cao;Lihua Xie

{"title":"SGBA: Semantic Gaussian Mixture Model-Based LiDAR Bundle Adjustment","authors":"Xingyu Ji;Shenghai Yuan;Jianping Li;Pengyu Yin;Haozhi Cao;Lihua Xie","doi":"10.1109/LRA.2024.3479699","DOIUrl":"https://doi.org/10.1109/LRA.2024.3479699","url":null,"abstract":"LiDAR bundle adjustment (BA) is an effective approach to reduce the drifts in pose estimation from the front-end. Existing works on LiDAR BA usually rely on predefined geometric features for landmark representation. This reliance restricts generalizability, as the system will inevitably deteriorate in environments where these specific features are absent. To address this issue, we propose SGBA, a LiDAR BA scheme that models the environment as a semantic Gaussian mixture model (GMM) without predefined feature types. This approach encodes both geometric and semantic information, offering a comprehensive and general representation adaptable to various environments. Additionally, to limit computational complexity while ensuring generalizability, we propose an adaptive semantic selection framework that selects the most informative semantic clusters for optimization by evaluating the condition number of the cost function. Lastly, we introduce a probabilistic feature association scheme that considers the entire probability density of assignments, which can manage uncertainties in measurement and initial pose estimation. We have conducted various experiments and the results demonstrate that SGBA can achieve accurate and robust pose refinement even in challenging scenarios with low-quality initial pose estimation and limited geometric features.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"10922-10929"},"PeriodicalIF":4.6,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565552","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

AIVIO: Closed-Loop, Object-Relative Navigation of UAVs With AI-Aided Visual Inertial Odometry AIVIO：利用人工智能辅助视觉惯性测距技术实现无人飞行器的闭环物体相关导航

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2024-10-14 DOI: 10.1109/LRA.2024.3479713

Thomas Jantos;Martin Scheiber;Christian Brommer;Eren Allak;Stephan Weiss;Jan Steinbrener

{"title":"AIVIO: Closed-Loop, Object-Relative Navigation of UAVs With AI-Aided Visual Inertial Odometry","authors":"Thomas Jantos;Martin Scheiber;Christian Brommer;Eren Allak;Stephan Weiss;Jan Steinbrener","doi":"10.1109/LRA.2024.3479713","DOIUrl":"https://doi.org/10.1109/LRA.2024.3479713","url":null,"abstract":"Object-relative mobile robot navigation is essential for a variety of tasks, e.g. autonomous critical infrastructure inspection, but requires the capability to extract semantic information about the objects of interest from raw sensory data. While deep learning-based (DL) methods excel at inferring semantic object information from images, such as class and relative 6\u0000<inline-formula><tex-math>$^{circ }$</tex-math></inline-formula>\u0000 of freedom (6-DoF) pose, they are computationally demanding and thus often not suitable for payload constrained mobile robots. In this letter we present a real-time capable unmanned aerial vehicle (UAV) system for object-relative, closed-loop navigation with a minimal sensor configuration consisting of an inertial measurement unit (IMU) and RGB camera. Utilizing a DL-based object pose estimator, solely trained on synthetic data and optimized for companion board deployment, the object-relative pose measurements are fused with the IMU data to perform object-relative localization. We conduct multiple real-world experiments to validate the performance of our system for the challenging use case of power pole inspection. An example closed-loop flight is presented in the supplementary video.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"10764-10771"},"PeriodicalIF":4.6,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10715655","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142452760","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Serial Robot Kinematic Calibration Using a Novel Linear Finite Screw Deviation Model 使用新型线性有限螺杆偏差模型进行串行机器人运动校准

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2024-10-14 DOI: 10.1109/LRA.2024.3480521

Jaehyung Kim;Min Cheol Lee

引用次数: 0

Kinetostatic Modeling of Retractable and Prismatic Spring Body for Continuum Climbing Robots in Discontinuous Terrains 用于不连续地形中连续爬行机器人的可伸缩和棱柱形弹簧体的运动静力学建模

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2024-10-14 DOI: 10.1109/LRA.2024.3479697

Pengpeng Yang;Jialin Zang;Ge Jin;Junliang Long;Bo Huang;Jianwen Zhao

{"title":"Kinetostatic Modeling of Retractable and Prismatic Spring Body for Continuum Climbing Robots in Discontinuous Terrains","authors":"Pengpeng Yang;Jialin Zang;Ge Jin;Junliang Long;Bo Huang;Jianwen Zhao","doi":"10.1109/LRA.2024.3479697","DOIUrl":"https://doi.org/10.1109/LRA.2024.3479697","url":null,"abstract":"There are few studies on the mechanics of the retractable backbone for continuum climbing robots, especially the non-circular cross-section. The retractable non-circular structure endows the robot with more compact structure, adjustability in initial stiffness, and dexterous mobility in narrow space. Consequently, a retractable prismatic spring backbone is proposed. Aiming at rectangular helical characteristic and coupling deformation, the backbone is equivalent to an elastic beam, whose equivalent stiffness is solved by the projection principle of the micro-segment deformation. Then the finite piecewise method and continuous differential method are used to establish its mechanical model. The piecewise method uses linear superposition principle to decouple the compression and bending deformation, and the rotation angle is solved by using the projection principle of the bending deformation. The continuous method uses the Cosserat-rod theory to establish the variable-curvature mechanics based on the equivalent beam, whose boundary-value problem is solved by gradually extending the integral region. Finally, two theory methods are in good agreement with FEA and experiment results; the continuous method has higher accuracy and piecewise method has lower computation cost; a multipurpose continuum climbing robot composed of the spring backbone, rotatable joint and flexible claw is applied to inspection in enclosed equipment.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"10954-10961"},"PeriodicalIF":4.6,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565614","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

Analysis and Verification on Backstepping Control of Antagonistic Variable Stiffness Actuators 拮抗变刚度致动器的反步态控制分析与验证

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2024-10-14 DOI: 10.1109/LRA.2024.3479782

Yongping Pan;Zhigang Zou;Kai Guo;Changyun Wen

引用次数: 0