IEEE Robotics and Automation Letters最新文献_第3页

Storm: An Experience-Based Framework for Robot Learning From Demonstration Storm：一个基于经验的机器人学习示范框架

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-04-07 DOI: 10.1109/LRA.2025.3558696

Natalia Quiroga;Alex Mitrevski;Paul G. Plöger;Teena Hassan

{"title":"Storm: An Experience-Based Framework for Robot Learning From Demonstration","authors":"Natalia Quiroga;Alex Mitrevski;Paul G. Plöger;Teena Hassan","doi":"10.1109/LRA.2025.3558696","DOIUrl":"https://doi.org/10.1109/LRA.2025.3558696","url":null,"abstract":"Learning from demonstration (LfD) can be used to increase the behavioural repertoire of a robot, but most demonstration-based learning techniques do not enable a robot to acquire knowledge about the limitations of its own body and use that information during learning. In this letter, we propose Storm, an LfD framework that enables acquiring trajectories in high-dimensional spaces, incorporates collision awareness, and can be adapted to different robots. Storm combines a collection of modules: i) robot embodiment exploration using motor babbling in order to acquire knowledge about the robot's own body, stored in the form of joint-specific graphs that encode reachable points and reachability constraints, ii) human-robot model mapping based on which human skeleton observations are mapped to the robot's embodiment, and iii) demonstration-based trajectory learning and subsequent reproduction of the learned actions using Gaussian mixture regression. We validate various aspects of our approach experimentally: i) exploration with different numbers of babbling points for three distinct robots, ii) path planning performance, including in the presence of obstacles, and iii) the acceptance of reproduced trajectories through a small-scale, real-world user study. The results demonstrate that Storm can produce versatile behaviours on different robots, and that trajectory reproductions are generally rated well by external observers, which is important for overall user acceptance.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 5","pages":"5186-5193"},"PeriodicalIF":4.6,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143839943","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

Real-Time Shape Estimation of Tensegrity Structures Using Strut Inclination Angles 利用支柱倾角实时估算张拉结构的形状

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-04-07 DOI: 10.1109/LRA.2025.3558704

Tufail Ahmad Bhat;Yuhei Yoshimitsu;Kazuki Wada;Shuhei Ikemoto

引用次数: 0

A Neuromorphic Tactile System for Reliable Braille Reading in Noisy Environments 嘈杂环境下可靠盲文阅读的神经形态触觉系统

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-04-07 DOI: 10.1109/LRA.2025.3558707

Xingchen Xu;Nathan F. Lepora;Benjamin Ward-Cherrier

引用次数: 0

Enhancing Lane Segment Perception and Topology Reasoning With Crowdsourcing Trajectory Priors 基于众包轨迹先验的车道分段感知与拓扑推理

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-04-07 DOI: 10.1109/LRA.2025.3558698

Peijin Jia;Ziang Luo;Tuopu Wen;Mengmeng Yang;Kun Jiang;Le Cui;Diange Yang

{"title":"Enhancing Lane Segment Perception and Topology Reasoning With Crowdsourcing Trajectory Priors","authors":"Peijin Jia;Ziang Luo;Tuopu Wen;Mengmeng Yang;Kun Jiang;Le Cui;Diange Yang","doi":"10.1109/LRA.2025.3558698","DOIUrl":"https://doi.org/10.1109/LRA.2025.3558698","url":null,"abstract":"In autonomous driving, recent advances in online mapping provide autonomous vehicles with a comprehensive understanding of driving scenarios. Moreover, incorporating prior information input into such perception model represents an effective approach to ensure the robustness and accuracy. However, utilizing diverse sources of prior information still faces three key challenges: the acquisition of high-quality prior information, alignment between prior and online perception, efficient integration. To address these issues, we investigate prior augmentation from a novel perspective of trajectory priors. In this letter, we initially extract crowdsourcing trajectory data from Argoverse2 motion forecasting dataset and encode trajectory data into rasterized heatmap and vectorized instance tokens, then we incorporate such prior information into the online mapping model through different ways. Besides, with the purpose of mitigating the misalignment between prior and online perception, we design a confidence-based fusion module that takes alignment into account during the fusion process. We conduct extensive experiments on OpenLane-V2 dataset. The results indicate that our method's performance significantly outperforms the current state-of-the-art methods.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 6","pages":"5417-5424"},"PeriodicalIF":4.6,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143860887","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

Coil-Tac: Coiled Capacitor Mechanism With Liquid Metal for Tactile Sensing 线圈- tac：用于触觉感应的液态金属线圈电容器机构

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-04-07 DOI: 10.1109/LRA.2025.3558655

George P. Jenkinson;Andrew T. Conn;Antonia Tzemanaki

引用次数: 0

Contrastive Learning-Based Secure Unsupervised Domain Adaptation Framework and its Application in Cross-Factory Intelligent Manufacturing 基于对比学习的安全无监督域自适应框架及其在跨工厂智能制造中的应用

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-04-03 DOI: 10.1109/LRA.2025.3557669

Zeyi Liu;Weihua Gui;Keke Huang;Dehao Wu;Yue Liao;Chunhua Yang

{"title":"Contrastive Learning-Based Secure Unsupervised Domain Adaptation Framework and its Application in Cross-Factory Intelligent Manufacturing","authors":"Zeyi Liu;Weihua Gui;Keke Huang;Dehao Wu;Yue Liao;Chunhua Yang","doi":"10.1109/LRA.2025.3557669","DOIUrl":"https://doi.org/10.1109/LRA.2025.3557669","url":null,"abstract":"Machine learning has been widely applied in industrial intelligent manufacturing. However, significant domain differences in data across factories make it difficult for models trained on a single factory dataset to achieve cross-factory reuse. Unsupervised Domain Adaptation is a method to address this issue, but its basic assumption is the source domain data is available. With increasing attention to data and internet security in the modern manufacturing industry, privacy protection of source data makes it unavailable. To address this challenge, we propose a contrastive learning-based secure unsupervised domain adaptation framework, which does not require source domain data and can achieve high-precision domain alignment by relying on the source domain well-trained model and the target domain unlabeled data. We conduct sufficient experimental studies on a digital recognition benchmark transfer task and a real industrial case, demonstrating that the proposed method outperforms state-of-the-art methods in terms of performance. It is worth mentioning that the proposed method can eliminate the dependence on source domain data, effectively ensuring cross-factory data privacy protection and providing new possibilities for intelligent networked collaborative manufacturing.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 5","pages":"5106-5113"},"PeriodicalIF":4.6,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143856268","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 Planning Framework for Complex Flipping Manipulation of Multiple Mobile Manipulators 多移动机械手复杂翻转操作的规划框架

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-04-03 DOI: 10.1109/LRA.2025.3557749

Wenhang Liu;Meng Ren;Kun Song;Michael Yu Wang;Zhenhua Xiong

{"title":"A Planning Framework for Complex Flipping Manipulation of Multiple Mobile Manipulators","authors":"Wenhang Liu;Meng Ren;Kun Song;Michael Yu Wang;Zhenhua Xiong","doi":"10.1109/LRA.2025.3557749","DOIUrl":"https://doi.org/10.1109/LRA.2025.3557749","url":null,"abstract":"During complex object manipulation, manipulator systems often face the configuration disconnectivity problem due to closed-chain constraints. Although regrasping can be adopted to guarantee connectivity, it introduces additional issues such as impact and efficiency. Therefore, regrasping numbers should be minimized during manipulation. To address this problem, a novel planning framework is proposed for multiple mobile manipulator systems. Given the object trajectory and the grasping pose set, the planning framework includes three steps. First, the inverse kinematic solution is verified along the given trajectory based on different grasping poses. Coverable trajectory segments are determined for each robot for a specific grasping pose. Second, the trajectory choice problem is formulated into a set cover problem, by which we can quickly determine whether the manipulation can be completed without regrasping or with a minimal regrasping number. Finally, the motions of each mobile manipulator are planned with the assigned trajectory segments using existing methods. Both simulations and experimental results show the performance of the planner in complex flipping manipulation. Additionally, theoretical analysis and multiple simulations are conducted to demonstrate the performance of the planner.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 5","pages":"5162-5169"},"PeriodicalIF":4.6,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143839945","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

Dynamic Behavior Cloning With Temporal Feature Prediction: Enhancing Robotic Arm Manipulation in Moving Object Tasks 基于时间特征预测的动态行为克隆：增强机械臂在运动目标任务中的操作

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-04-03 DOI: 10.1109/LRA.2025.3557746

Yifan Zhang;Ruiping Wang;Xilin Chen

{"title":"Dynamic Behavior Cloning With Temporal Feature Prediction: Enhancing Robotic Arm Manipulation in Moving Object Tasks","authors":"Yifan Zhang;Ruiping Wang;Xilin Chen","doi":"10.1109/LRA.2025.3557746","DOIUrl":"https://doi.org/10.1109/LRA.2025.3557746","url":null,"abstract":"In numerous real-world applications, the ability to accurately perceive and respond to dynamic changes in the environment, while also maintaining the flexibility to transfer learned skills across different tasks, is crucial for the effective operation of robotic arms. Behavior cloning is particularly promising in this context due to its data efficiency and strong task transferability, enabling robots to quickly adapt to new tasks by learning from demonstrations. However, traditional behavior cloning methods, which rely primarily on the observation and state information of the current frame to predict subsequent actions, fall short in dynamic contexts due to their static nature. To address this limitation, we propose Dynamic Behavior Cloning with Temporal Feature Prediction (DBC-TFP), which integrates with behavior cloning by leveraging historical frames to capture dynamic features crucial for predicting future scene images. This method uses a loss function based on the mean squared error (MSE) between the predicted future scene image and the ground truth counterpart, improving the model's accuracy in action prediction for dynamic scenarios. To evaluate our approach, we design a benchmark comprising eight task scenarios, including six foundational tasks and two advanced tasks. Experimental results on this benchmark demonstrate that DBC-TFP significantly improves the success rate of behavior cloning in dynamic scenarios compared to traditional behavior cloning methods.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 6","pages":"5209-5216"},"PeriodicalIF":4.6,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143845435","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

Learning Dual-Arm Push and Grasp Synergy in Dense Clutter 学习密集杂波中的双臂推握协同作用

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-04-03 DOI: 10.1109/LRA.2025.3557753

Yongliang Wang;Hamidreza Kasaei

{"title":"Learning Dual-Arm Push and Grasp Synergy in Dense Clutter","authors":"Yongliang Wang;Hamidreza Kasaei","doi":"10.1109/LRA.2025.3557753","DOIUrl":"https://doi.org/10.1109/LRA.2025.3557753","url":null,"abstract":"Robotic grasping in densely cluttered environments is challenging due to scarce collision-free grasp affordances. Non-prehensile actions can increase feasible grasps in cluttered environments, but most research focuses on single-arm rather than dual-arm manipulation. Policies from single-arm systems fail to fully leverage the advantages of dual-arm coordination. We propose a target-oriented hierarchical deep reinforcement learning (DRL) framework that learns dual-arm push-grasp synergy for grasping objects to enhance dexterous manipulation in dense clutter. Our framework maps visual observations to actions via a pre-trained deep learning backbone and a novel CNN-based DRL model, trained with Proximal Policy Optimization (PPO), to develop a dual-arm push-grasp strategy. The backbone enhances feature mapping in densely cluttered environments. A novel fuzzy-based reward function is introduced to accelerate efficient strategy learning. Our system is developed and trained in Isaac Gym and then tested in simulations and on a real robot. Experimental results show that our framework effectively maps visual data to dual push-grasp motions, enabling the dual-arm system to grasp target objects in complex environments. Compared to other methods, our approach generates 6-DoF grasp candidates and enables dual-arm push actions, mimicking human behavior.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 5","pages":"5154-5161"},"PeriodicalIF":4.6,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143856280","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

Evetac Meets Sparse Probabilistic Spiking Neural Network: Enhancing Snap-Fit Recognition Efficiency and Performance Evetac满足稀疏概率峰值神经网络：提高Snap-Fit识别效率和性能

IF 4.6 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2025-04-03 DOI: 10.1109/LRA.2025.3557744

Senlin Fang;Haoran Ding;Yangjun Liu;Jiashu Liu;Yupo Zhang;Yilin Li;Hoiio Kong;Zhengkun Yi

{"title":"Evetac Meets Sparse Probabilistic Spiking Neural Network: Enhancing Snap-Fit Recognition Efficiency and Performance","authors":"Senlin Fang;Haoran Ding;Yangjun Liu;Jiashu Liu;Yupo Zhang;Yilin Li;Hoiio Kong;Zhengkun Yi","doi":"10.1109/LRA.2025.3557744","DOIUrl":"https://doi.org/10.1109/LRA.2025.3557744","url":null,"abstract":"Snap-fit peg-in-hole assembly is common in industrial robotics, particularly for 3 C electronics, where fast and accurate tactile recognition is crucial for protecting fragile components. Event-based optical sensors, such as Evetac, are well-suited for this task due to their high sparsity and sensitivity in detecting small, rapid force changes. However, existing research often converts event data into dense images and processing them with dense methods, leading to higher computational complexity. In this letter, we propose a Sparse Probabilistic Spiking Neural Network (SPSNN) that utilizes sparse convolutions to extract features from the event data, avoiding computations on non-zero cells. We introduce the Forward and Backward Propagation Through Probability (FBPTP) method, which enables simultaneous gradient computation across all time steps, eliminating the need for the step-by-step traversal required by traditional Forward and Backward Propagation Through Time (FBPTT). Additionally, the Temporal Weight Prediction (TWP) method dynamically allocates weights for different time outputs, enhancing recognition performance with minimal impact on model efficiency. We integrate the Evetac sensor compactly into our robotic system and collected two datasets, named Tactile Event Ethernet (TacEve-Eth) and Tactile Event Type-C (TacEve-TC), corresponding to cantilever and annular snap-fit structures. Experiments show that the SPSNN achieves the superior trade-off between recognition performance and efficiency compared to other widely used methods, achieving the highest average recognition performance while reducing inference time by over 90% compared to FBPTT-based dense SNN baselines.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 6","pages":"5353-5360"},"PeriodicalIF":4.6,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143856137","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