IEEE Robotics and Automation Letters最新文献

{"title":"Safe Bayesian Optimization for Complex Control Systems via Additive Gaussian Processes","authors":"Hongxuan Wang;Xiaocong Li;Lihao Zheng;Adrish Bhaumik;Prahlad Vadakkepat","doi":"10.1109/LRA.2025.3612756","DOIUrl":"https://doi.org/10.1109/LRA.2025.3612756","url":null,"abstract":"Controller tuning and optimization have long been recognized as fundamental challenges in robotics and mechatronic systems. Traditional controller design techniques are usually model-based, and their closed-loop performance depends on the fidelity of the mathematical model. Subsequent tuning of the controller parameters is frequently carried out via empirical rules, which may still suffer from model inaccuracies. In control applications with complex dynamics, obtaining a precise model is often challenging, leading us towards a data-driven approach. While various researchers have explored the optimization of a single controller, it remains a challenge to obtain the optimal controller parameters safely and efficiently when multiple controllers are involved. In this letter, a method called <sc>SafeCtrlBO</small> is proposed to optimize multiple controllers simultaneously while ensuring safety. The exploration process in existing safe Bayesian optimization is simplified to reduce computational effort without sacrificing expansion capability. Additionally, additive Gaussian kernels are employed to enhance the efficiency of Gaussian process updates for unknown functions. Hardware experiments on a permanent magnet synchronous motor (PMSM) demonstrate that, compared to baseline safe Bayesian optimization algorithms, <sc>SafeCtrlBO</small> attains the best overall performance while ensuring safety.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 11","pages":"11538-11545"},"PeriodicalIF":5.3,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210182","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}

{"title":"Learning Routing Policy With Spatial Awareness: A Distance-Based Attention Mechanism for Multi-Robot Routing With Time Windows in Multi-Product Delivery","authors":"Site Qu;Guoqiang Hu","doi":"10.1109/LRA.2025.3611118","DOIUrl":"https://doi.org/10.1109/LRA.2025.3611118","url":null,"abstract":"Deep Reinforcement Learning (DRL) approaches with Attention Mechanism have shown efficiency and effectiveness for combinatorial optimization problem, such as routing problem for autonomous vehicles (VRP). However, the real-world routing problems often involve intricate constraints and multiple objectives, introducing substantial complexity. Current attention mechanism uniformly treats all the points within service region, neglecting the relative spatial relationship among points, which results in unguided exploration within the large solution space of multi-objective routing problem, leading to a potential distraction dilemma where model struggles to effectively balance multiple objectives. To address this issue, we propose a Distance-Based Attention Mechanism (DBAM) that enhances spatial awareness by incorporating relative spatial relationship information into attention-based model, and implement this model to study a new multi-objective VRP variant: the Capacitated Vehicle Routing Problem with soft Time Windows for Multi-kind products delivery tasks (MKVRPsTW), in which the DRL model is trained to plan routes for a fleet of autonomous vehicles to serve customers with multi-kind products demands, while minimizing the total length, time window violation and balancing route lengths among vehicles. Experimental results reveal that DBAM outperforms the original attention-based DRL methods, graph-based DRL methods, and traditional baselines. Additionally, fine-tuning experiments for balance-oriented objectives further substantiates DBAM's flexibility and stability for quick adaptation.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 11","pages":"11451-11458"},"PeriodicalIF":5.3,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145141705","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}

{"title":"Efficient Multi-Camera Tokenization With Triplanes for End-to-End Driving","authors":"Boris Ivanovic;Cristiano Saltori;Yurong You;Yan Wang;Wenjie Luo;Marco Pavone","doi":"10.1109/LRA.2025.3611145","DOIUrl":"https://doi.org/10.1109/LRA.2025.3611145","url":null,"abstract":"Autoregressive Transformers are increasingly being deployed as end-to-end robot and autonomous vehicle (AV) policy architectures, owing to their scalability and potential to leverage internet-scale pretraining for generalization. Accordingly, tokenizing sensor data <italic>efficiently</i> is paramount to ensuring the real-time feasibility of such architectures on embedded hardware. To this end, we present an efficient triplane-based multi-camera tokenization strategy that leverages recent advances in 3D neural reconstruction and rendering to produce sensor tokens that are agnostic to the number of input cameras and their resolution, while explicitly accounting for their geometry around an AV. Experiments on large-scale AV datasets and a state-of-the-art neural simulator demonstrate that our approach yields significant savings over current image patch-based tokenization strategies, producing up to 72% fewer tokens, resulting in up to 50% faster policy inference while achieving the same open-loop motion planning accuracy and improved offroad rates in closed-loop driving simulations.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 11","pages":"11713-11720"},"PeriodicalIF":5.3,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145255886","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}

{"title":"High Vacuum Pressure Constant-Mass Soft Origami Actuation for Passive Constant-Force Operation","authors":"Faqihah Abu Bakar;Altair Coutinho;Jae Hyuck Jang;Hugo Rodrigue","doi":"10.1109/LRA.2025.3611074","DOIUrl":"https://doi.org/10.1109/LRA.2025.3611074","url":null,"abstract":"This letter introduces a novel origami-inspired vacuum pneumatic actuator that operates as a passive force-generating element, capable of producing a near-constant force without active control. The actuator is fabricated from a Yoshimura-patterned film structure incorporating rigid facets and internal reinforcements, enabling large contraction strokes and consistent force output under constant vacuum conditions. A central feature of the design is its pre-vacuumed, sealed operation, which maintains stable internal pressure throughout the entire stroke without needing external pressure regulation. The combination of stable passive pressure and stable isobaric force results in a constant and passive force generated by the actuator. A numerical model based on conservation of energy and Boyle's law is presented to predict actuator behavior under both isobaric and constant-mass conditions. Experimental validation confirms the model's accuracy and demonstrates the actuator's stable force output at high constant-mass pressures. The actuator is further implemented in a wearable support suit aimed at reducing lower back strain during squatting and stooping motions. This work demonstrates a new approach for passive actuation using soft robotics principles and highlights potential applications in assistive wearable devices.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 11","pages":"11459-11465"},"PeriodicalIF":5.3,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145141704","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}

{"title":"Autonomous Decentralized Control for Motion Switching in an Intestine-Inspired Peristaltic Mixing Pump Adaptive to Physical Phase Transitions of Mixed Materials","authors":"Takaaki Tanno;Ryosuke Adachi;Koya Tsurumi;Fumio Ito;Tomoki Hanamura;Takuya Umedachi;Taro Nakamura","doi":"10.1109/LRA.2025.3610034","DOIUrl":"https://doi.org/10.1109/LRA.2025.3610034","url":null,"abstract":"In this letter, we developed an autonomous decentralized control method that incorporates phase-difference adjustment based on a sigmoid function, enabling the design of both increases and decreases in discrepancy. The method was applied to a peristaltic mixing pump capable of mixing and transporting solid–liquid multiphase fluids. This study aims to realize a soft robotics system that autonomously switches motion modes according to changes in the physical properties of the transported material, thereby integratively mimicking both the motility and motion-switching functions of the intestine. Conventional autonomous decentralized control methods have been applied to the locomotion of amoeba-type and snake-type robots. However, when such control laws are applied to pumps, it is difficult to achieve appropriate motion switching in environments where the contents harden due to mixing. In this letter, we employed a sigmoid function that allows bidirectional control of discrepancy and constructed a new control law based on target phase-difference adjustment without feedback. The control law was implemented in a four-unit pump, and we confirmed that the desired motion patterns could be reproduced according to the preset target phase differences. As a result, the phase differences between all units converged to the target values within approximately 10–30 s after actuation began, producing the intended motion patterns. Furthermore, polyvinyl alcohol solution and borax water were used as contents whose fluidity decreases during mixing. We verified that autonomous motion switching occurred as the discrepancy increased. The results showed that, in units containing hardened material, a conveying motion with a phase difference of π/3 was generated, whereas in units with residual unmixed material, a mixing motion with a phase difference of π was generated. These findings demonstrate that the proposed method enables motion control that adapts to changes in material properties.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 11","pages":"11498-11505"},"PeriodicalIF":5.3,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210185","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}

{"title":"Energy-Shaping Controller for Time-Invariant Multiple Contacts","authors":"Ehtisham ul Hasan;Angelika Peer","doi":"10.1109/LRA.2025.3610015","DOIUrl":"https://doi.org/10.1109/LRA.2025.3610015","url":null,"abstract":"While in the past industrial robots were strictly separated from humans, today robots serve humans in a variety of industrial applications that also involve close or even physical human-robot interaction. Hereby, safety is of utmost importance and thus, the design of the control system needs to ensure a stable and safe operation. In this context, safety has been mainly addressed for single interaction points. In this article, we present an energy shaping controller that is capable of ensuring safety even in the case of multiple human contact points that may occur when co-manipulating an object. The presented approach is tested and validated in experiments. Results indicate that for the studied co-manipulation task involving time-invariant multiple human contacts, a safe interaction can be achieved.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 11","pages":"11514-11521"},"PeriodicalIF":5.3,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210178","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}

{"title":"Kaiwu: A Multimodal Manipulation Dataset and Framework for Robot Learning and Human-Robot Interaction","authors":"Shuo Jiang;Haonan Li;Ruochen Ren;Yanmin Zhou;Zhipeng Wang;Bin He","doi":"10.1109/LRA.2025.3609615","DOIUrl":"https://doi.org/10.1109/LRA.2025.3609615","url":null,"abstract":"Cutting-edge robot learning techniques including foundation models and imitation learning from humans all pose huge demands on large-scale and high-quality datasets which constitute one of the bottleneck in the general intelligent robot fields. This paper presents the Kaiwu multimodal dataset to address the missing real-world synchronized multimodal data problems in the sophisticated assembling scenario, especially with dynamics information and its fine-grained labelling. The dataset first provides an integration of human, environment and robot data collection framework with 20 subjects and 30 interaction objects resulting in totally 11,664 instances of integrated actions. For each of the demonstration, hand motions, operation pressures, sounds of the assembling process, multi-view videos, high-precision motion capture information, eye gaze with first-person videos, electromyography signals are all recorded. Fine-grained multi-level annotation based on absolute timestamp, and semantic segmentation labelling are performed. Kaiwu dataset aims to facilitate robot learning, dexterous manipulation, human intention investigation and human-robot collaboration research.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 11","pages":"11482-11489"},"PeriodicalIF":5.3,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210179","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}

{"title":"3D Foundation Model-Based Loop Closing for Decentralized Collaborative SLAM","authors":"Pierre-Yves Lajoie;Benjamin Ramtoula;Daniele De Martini;Giovanni Beltrame","doi":"10.1109/LRA.2025.3609204","DOIUrl":"https://doi.org/10.1109/LRA.2025.3609204","url":null,"abstract":"Decentralized Collaborative Simultaneous Localization and Mapping (C-SLAM) techniques often struggle to identify map overlaps due to significant viewpoint variations among robots. Motivated by recent advancements in 3D foundation models, which can register images despite large viewpoint differences, we propose a robust loop closing approach that leverages these models to establish inter-robot measurements. In contrast to resource-intensive methods requiring full 3D reconstruction within a centralized map, our approach integrates foundation models into existing SLAM pipelines, yielding scalable and robust multi-robot mapping. Our contributions include: 1) integrating 3D foundation models to reliably estimate relative poses from monocular image pairs within decentralized C-SLAM; 2) introducing robust outlier mitigation techniques critical to the use of these relative poses and 3) developing specialized pose graph optimization formulations that efficiently resolve scale ambiguities. We evaluate our method against state-of-the-art approaches, demonstrating improvements in localization and mapping accuracy, alongside significant gains in computational and memory efficiency. These results highlight the potential of our approach for deployment in large-scale multi-robot scenarios.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 11","pages":"11188-11195"},"PeriodicalIF":5.3,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145090009","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}

{"title":"RollUP: Rolling-Up End-Effector for Fabric Handling","authors":"Akinari Kobayashi;Wenbo Dong;Akira Seino;Fuyuki Tokuda;Kazuhiro Kosuge","doi":"10.1109/LRA.2025.3609086","DOIUrl":"https://doi.org/10.1109/LRA.2025.3609086","url":null,"abstract":"The fabric deforms easily due to the physical constraints of its environment. The deformation of the fabric shape, including wrinkles, makes the precise pick-and-place of a piece of fabric difficult to automate its handling. This letter proposes a <underline>Roll</u>ing <underline>UP</u> end-effector (RollUP) to pick-and-place a fabric piece while keeping it flat without making wrinkles. RollUP has a roller unit actuated by an electric motor and a vacuum suction slot on the roller. A fabric piece is picked up by air suction and rolled up. Rolling up the fabric reduces the unconstrained free area of the piece of fabric to be handled and makes it easier to handle a fabric with a large dimension. By attaching two RollUPs to the dual-arm manipulator, fabric tension can be controlled to keep it flat. Three experiments are conducted to evaluate the performance of RollUP. First, the grasping performance of the single RollUP for fabric pieces made of different materials and shapes is evaluated. Second, the relationship between the angle subtended by the fabric and the maximum force that can be applied to the fabric without slippage is investigated. Lastly, pick-and-place experiments involving a piece of fabric are performed using a dual manipulator system equipped with two RollUPs to evaluate performance.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 11","pages":"11204-11211"},"PeriodicalIF":5.3,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11159254","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145090038","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}

{"title":"Prespecified-Performance Kinematic Tracking Control for Aerial Manipulation","authors":"Hauzi Cao;Jiahao Shen;Zhengzhen Li;Qinquan Ren;Shiyu Zhao","doi":"10.1109/LRA.2025.3609098","DOIUrl":"https://doi.org/10.1109/LRA.2025.3609098","url":null,"abstract":"This letter studies the kinematic tracking control problem for aerial manipulators. Existing kinematic tracking control methods, which typically employ proportional-derivative feedback or tracking-error-based feedback strategies, may fail to achieve tracking objectives within specified time constraints. To address this limitation, we propose a novel control framework comprising two key components: end-effector tracking control based on a user-defined preset trajectory and quadratic programming-based reference allocation. Compared with state-of-the-art approaches, the proposed method has several attractive features. First, it ensures that the end-effector reaches the desired position within a preset time while keeping the tracking error within a performance envelope that reflects task requirements. Second, quadratic programming is employed to allocate the references of the quadcopter base and the Delta arm, while considering the physical constraints of the aerial manipulator, thus preventing solutions that may violate physical limitations. The proposed approach is validated through three experiments. Experimental results demonstrate the effectiveness of the proposed algorithm and its capability to guarantee that the target position is reached within the preset time.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 11","pages":"11086-11093"},"PeriodicalIF":5.3,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145073393","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}