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

Locomotion of an Elastic Snake Robot via Natural Dynamics 基于自然动力学的弹性蛇形机器人运动

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2026-07-01 Epub Date: 2026-03-11 DOI: 10.1109/LRA.2026.3692039

Tristan Ehlert;Arne Sachtler;Annika Schmidt;Davide Calzolari;Alin Albu-Schäffer

{"title":"Locomotion of an Elastic Snake Robot via Natural Dynamics","authors":"Tristan Ehlert;Arne Sachtler;Annika Schmidt;Davide Calzolari;Alin Albu-Schäffer","doi":"10.1109/LRA.2026.3692039","DOIUrl":"https://doi.org/10.1109/LRA.2026.3692039","url":null,"abstract":"Nature suggests that exploiting the elasticities and natural dynamics of robotic systems could increase their locomotion efficiency. Prior work on elastic snake robots supports this hypothesis, but has not fully exploited the nonlinear dynamic behavior of the systems. Recent advances in eigenmanifold theory enable a better characterization of the natural dynamics in complex nonlinear systems. This letter investigates if and how the nonlinear natural dynamics of a kinematic elastic snake robot can be used to design efficient gaits. Two types of gaits based on natural dynamics are presented and compared to a state-of-the-art approach using dynamics simulations. The results reveal that a gait generated by switching between two nonlinear normal mode does not improve the locomotion efficiency of the robot. In contrast, gaits based on non-brake periodic trajectories (non-brake orbit) are perfectly efficient in the energy-conservative case. Further simulations with friction reveal that, in a more realistic scenario, non-brake orbit gaits achieve higher efficiency compared to the baseline gait on the rigid system. Overall, the investigation offers promising insights into the design of gaits based on natural dynamics, fostering further research.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"11 7","pages":"7908-7915"},"PeriodicalIF":5.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148509044","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

Prompt2Craft: Generating Functional Craft Assemblies With LLMs Prompt2Craft：生成功能工艺装配与llm

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2026-07-01 Epub Date: 2026-03-11 DOI: 10.1109/LRA.2026.3692045

Vitor Hideyo Isume;Takuya Kiyokawa;Natsuki Yamanobe;Yukiyasu Domae;Weiwei Wan;Kensuke Harada

{"title":"Prompt2Craft: Generating Functional Craft Assemblies With LLMs","authors":"Vitor Hideyo Isume;Takuya Kiyokawa;Natsuki Yamanobe;Yukiyasu Domae;Weiwei Wan;Kensuke Harada","doi":"10.1109/LRA.2026.3692045","DOIUrl":"https://doi.org/10.1109/LRA.2026.3692045","url":null,"abstract":"The Craft Assembly Task - a robotic assembly task inspired by handmade crafts - poses unique challenges relative to a traditional object assembly task.It involves open-ended decisions that are difficult to automate, with previous work relying on prior assumptions or expert knowledge, limiting scalability. In this work, we propose to address these limitations by employing an off-the-shelf Large Language Model (LLM) as the main decision maker in the available objects selection, pose estimation and connectivity between parts without additional training or fine-tuning, using the RGB image of the target object in the wild as a reference. The core of our method is a customized structure for the craft assembly description to constrain the LLM’s predictions. The proposals are validated through collision checks and physics simulation tests. We evaluate our approach on eight types of objects with three possible functions: “hit”, “support” and “rolling”. For visual similarity, we compare our generated final crafts with the 3D models generated by a state-of-the-art image-to-3D generation foundation model, and a baseline that uses image-to-3D part generation model. Our approach produces coherent, physically plausible assemblies, while the baseline often fails to generate or segment the object into parts suitable for assembly.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"11 7","pages":"7772-7779"},"PeriodicalIF":5.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148509276","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 From Multi-Quality Demonstrations in Dynamic Movement Primitives 从动态运动基元的多质量演示中学习

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2026-07-01 Epub Date: 2026-03-15 DOI: 10.1109/LRA.2026.3693990

Hao Jiang;Jianping He;Xiaoming Duan

{"title":"Learning From Multi-Quality Demonstrations in Dynamic Movement Primitives","authors":"Hao Jiang;Jianping He;Xiaoming Duan","doi":"10.1109/LRA.2026.3693990","DOIUrl":"https://doi.org/10.1109/LRA.2026.3693990","url":null,"abstract":"Learning from Demonstrations (LfD) is an attractive paradigm in robot learning, enabling robots to acquire skills by observing human demonstrations without explicit programming. However, existing LfD approaches typically assume that users provide ideal demonstrations, which rarely holds in practice, especially as non-expert inputs often vary in quality. Such multi-quality demonstrations can cause instability in LfD models and produce outputs that deviate from the desired behavior. To address this, recent studies have improved high-level LfD approaches with notable success, whereas low-level approaches represented by the Dynamic Movement Primitives (DMPs) have received limited attention. In this letter, we propose a novel method that enables DMP to effectively learn from multi-quality demonstrations, capturing user intents and mitigating quality inconsistencies. Specifically, the proposed method combines Dynamic Time Warping (DTW) with a representation learning model (TS2Vec) for unsupervised identification, estimating the relative qualities of DMP's forcing terms and assigning scores. Then, when modeling these terms with a Gaussian Mixture Model, we introduce a latent variable representing the desired forcing term and formulate a weighted joint Maximum A Posteriori objective, enabling reliable modeling guided by the identified scores. Simulation and experimental results show that our method enables DMPs to produce outputs closer to the desired behavior, with improvements in compactness (<inline-formula><tex-math>$18times$</tex-math></inline-formula>), smoothness (<inline-formula><tex-math>$20times$</tex-math></inline-formula>), and similarity to the desired demo (<inline-formula><tex-math>$5times$</tex-math></inline-formula>).","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"11 7","pages":"8100-8107"},"PeriodicalIF":5.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148509998","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

HOTFLoc++: End-to-End Hierarchical LiDAR Place Recognition, Re-Ranking, and 6-DoF Metric Localisation in Forests HOTFLoc++：端到端分层激光雷达位置识别，重新排序和森林中的6自由度度量定位

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2026-07-01 Epub Date: 2026-03-11 DOI: 10.1109/LRA.2026.3692033

Ethan Griffiths;Maryam Haghighat;Simon Denman;Clinton Fookes;Milad Ramezani

{"title":"HOTFLoc++: End-to-End Hierarchical LiDAR Place Recognition, Re-Ranking, and 6-DoF Metric Localisation in Forests","authors":"Ethan Griffiths;Maryam Haghighat;Simon Denman;Clinton Fookes;Milad Ramezani","doi":"10.1109/LRA.2026.3692033","DOIUrl":"https://doi.org/10.1109/LRA.2026.3692033","url":null,"abstract":"This article presents HOTFLoc++, an end-to-end hierarchical framework for LiDAR place recognition, re-ranking, and 6-DoF metric localisation in forests. Leveraging an octree-based transformer, our approach extracts features at multiple granularities to increase robustness to clutter, self-similarity, and viewpoint changes in challenging scenarios, including ground-to-ground and ground-to-aerial in forest and urban environments. We propose learnable multi-scale geometric verification to reduce re-ranking failures due to degraded single-scale correspondences. Our joint training protocol enforces multi-scale geometric consistency of the octree hierarchy via joint optimisation of place recognition with re-ranking and localisation, improving place recognition convergence. Our system achieves comparable or lower localisation errors to baselines, with runtime improvements of almost two orders of magnitude over RANSAC-based registration for dense point clouds. Experimental results on public datasets show the superiority of our approach compared to state-of-the-art methods, achieving an average Recall@1 of 90.7% on CS-Wild-Places: an improvement of 29.6 percentage points over baselines, while maintaining high performance on single-source benchmarks with an average Recall@1 of 91.7% and 97.9% on Wild-Places and MulRan, respectively. Our method achieves under 2 m and 5<inline-formula><tex-math>$^{circ }$</tex-math></inline-formula> error for 97.2% of 6-DoF registration attempts, with our multi-scale re-ranking module reducing localisation errors by <inline-formula><tex-math>$sim !2times$</tex-math></inline-formula> on average.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"11 7","pages":"7860-7867"},"PeriodicalIF":5.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148510743","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

Impact-Aware Robust Convex Model Predictive Control for Quadruped Locomotion on Uncertain Terrain 不确定地形下四足运动的冲击感知鲁棒凸模型预测控制

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2026-07-01 Epub Date: 2026-03-11 DOI: 10.1109/LRA.2026.3692086

Kuikui Xue;Xin Xin;Jiangyong Hu

{"title":"Impact-Aware Robust Convex Model Predictive Control for Quadruped Locomotion on Uncertain Terrain","authors":"Kuikui Xue;Xin Xin;Jiangyong Hu","doi":"10.1109/LRA.2026.3692086","DOIUrl":"https://doi.org/10.1109/LRA.2026.3692086","url":null,"abstract":"Deploying legged robots in complex environments requires robust traversal capabilities on unstructured terrain. However, existing locomotion controllers may exhibit degraded robustness when subjected to rapidly varying terrain-induced impact disturbances. To address this challenge, we propose an impact-aware robust convex model predictive control (IRCMPC) for quadruped locomotion by explicitly modeling terrain-induced impacts as bounded uncertainties in the single rigid body (SRB) dynamics. The proposed IRCMPC integrates robust control principles into the model predictive control to handle the impact disturbances experienced by the robot. First, we model a momentum-based bound on the maximum potential impact at each step and introduce a relaxation factor that reduces conservatism when severe impacts are unlikely to occur. We then formulate a robust min–max MPC problem and transform this problem into a standard quadratic optimization problem to ensure computational efficiency. Comparative simulation and hardware experiments on a Unitree Go2 robot demonstrate that IRCMPC improves locomotion robustness under intensified impact conditions where conventional convex model predictive control (CMPC) fails. The results further show that, in the tested scenarios, IRCMPC achieves a more favorable trade-off between traversal robustness and tracking performance than adaptive nonlinear centroidal model predictive control (ANCMPC).","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"11 7","pages":"7820-7827"},"PeriodicalIF":5.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148510756","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

Recent Advances in Intelligent Energy Management for Design and Operation of Green Hospitals 面向绿色医院设计与运营的智能能源管理研究进展

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2026-07-01 Epub Date: 2026-06-08 DOI: 10.1109/LRA.2026.3701567

Qing Wang;Leqi Weng;Taojun Wang;Jingshan Li

{"title":"Recent Advances in Intelligent Energy Management for Design and Operation of Green Hospitals","authors":"Qing Wang;Leqi Weng;Taojun Wang;Jingshan Li","doi":"10.1109/LRA.2026.3701567","DOIUrl":"https://doi.org/10.1109/LRA.2026.3701567","url":null,"abstract":"Reducing energy consumption and adopting alternative or renewable energy in hospitals and healthcare facilities are of significant importance for sustainable development, energy savings, and healthcare-related emission reduction. Thus, green hospitals have been introduced as a paradigm shift in healthcare. In this paper, a review of recent advances in intelligent energy management for the design and operation of green hospitals is presented from the perspectives of energy efficiency improvement, alternative or renewable energy integration, sustainable building design, and green logistics, particularly in terms of optimization and artificial intelligence (AI) applications. Representative methods and practical cases are summarized to show how optimization models, data-driven approaches, and AI technologies can support energy savings, operational resilience, and carbon footprint reduction in healthcare facilities. Major challenges are also discussed, including data quality, system interoperability, model interpretability, cybersecurity, and policy support. This review provides a concise overview of recent progress and potential research directions for sustainable and AI-enabled green hospitals.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"11 7","pages":"8952-8959"},"PeriodicalIF":5.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148443012","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 Maclaurin-Series-Based Vision-Language-Action Model 基于动态maclaurin序列的视觉语言-动作模型

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2026-07-01 Epub Date: 2026-04-13 DOI: 10.1109/LRA.2026.3683324

Chong Yu;Zhongxue Gan

引用次数: 0

“I'm Not Mad, Just Focused”: Understanding Human Emotions in Human-Robot Collaboration “我没有疯，只是专注”：理解人机协作中的人类情感

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2026-07-01 Epub Date: 2026-03-18 DOI: 10.1109/LRA.2026.3694591

Seung Chan Hong;Dana Kulić;Leimin Tian

引用次数: 0

AdaTracker: Learning Adaptive In-Context Policy for Cross-Embodiment Active Visual Tracking AdaTracker：学习自适应上下文策略的交叉体现主动视觉跟踪

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2026-07-01 Epub Date: 2026-03-11 DOI: 10.1109/LRA.2026.3692075

Kui Wu;Hao Chen;Jinzhu Han;Haijun Liu;Churan Wang;Yizhou Wang;Zhoujun Li;Si Liu;Fangwei Zhong

{"title":"AdaTracker: Learning Adaptive In-Context Policy for Cross-Embodiment Active Visual Tracking","authors":"Kui Wu;Hao Chen;Jinzhu Han;Haijun Liu;Churan Wang;Yizhou Wang;Zhoujun Li;Si Liu;Fangwei Zhong","doi":"10.1109/LRA.2026.3692075","DOIUrl":"https://doi.org/10.1109/LRA.2026.3692075","url":null,"abstract":"Realizing active visual tracking with a single unified model across diverse robots is challenging, as the physical constraints and motion dynamics vary drastically from one platform to another. Existing approaches typically train separate models for each embodiment, leading to poor scalability and limited generalization. To address this, we propose AdaTracker, an adaptive in-context policy learning framework that robustly tracks targets on diverse robot morphologies. Our key insight is to explicitly model embodiment-specific constraints through an Embodiment Context Encoder, which infers embodiment-specific constraints from history. This contextual representation dynamically modulates a Context-Aware Policy, enabling it to infer optimal control actions for unseen embodiments in a zero-shot manner. To enhance robustness, we introduce two auxiliary objectives to ensure accurate context identification and temporal consistency. Experiments in both simulation and the real world demonstrate that AdaTracker significantly outperforms state-of-the-art methods in cross-embodiment generalization, sample efficiency, and zero-shot adaptation.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"11 7","pages":"8308-8314"},"PeriodicalIF":5.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504463","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

Reactive Motion Generation via Phase-Varying Neural Potential Functions 通过相位变化的神经电位函数产生反应性运动

IF 5.3 2区计算机科学

IEEE Robotics and Automation Letters Pub Date : 2026-07-01 Epub Date: 2026-03-11 DOI: 10.1109/LRA.2026.3692035

Ahmet Tekden;Dimitrios Kanoulas;Aude Billard;Yasemin Bekiroglu

{"title":"Reactive Motion Generation via Phase-Varying Neural Potential Functions","authors":"Ahmet Tekden;Dimitrios Kanoulas;Aude Billard;Yasemin Bekiroglu","doi":"10.1109/LRA.2026.3692035","DOIUrl":"https://doi.org/10.1109/LRA.2026.3692035","url":null,"abstract":"Dynamical systems (DS) methods for Learning-from-Demonstration (LfD) provide stable, continuous policies from few demonstrations. First-order dynamical systems (DS) are effective for many point-to-point and periodic tasks, as long as a unique velocity is defined for each state. For tasks with intersections (e.g., drawing an “8”), extensions such as second-order dynamics or phase variables are often used. However, by incorporating velocity, second-order models become sensitive to disturbances near intersections, as velocity is used to disambiguate motion direction. Moreover, this disambiguation may fail when nearly identical position–velocity pairs correspond to different onward motions. In contrast, phase-based methods rely on open-loop time or phase variables, which limit their ability to recover after perturbations. We introduce Phase-varying Neural Potential Functions (PNPF), an LfD framework that conditions a potential function on a phase variable which is estimated directly from state progression, rather than on open-loop temporal inputs. This phase variable allows the system to handle state revisits, while the learned potential function generates local vector fields for reactive and stable control. PNPF generalizes effectively across point-to-point, periodic, and full 6D motion tasks, outperforms existing baselines on trajectories with intersections, and demonstrates robust performance in real-time robotic manipulation under external disturbances.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"11 7","pages":"8292-8299"},"PeriodicalIF":5.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11513752","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504465","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