{"title":"Controller Adaptation via Learning Solutions of Contextual Bayesian Optimization","authors":"Viet-Anh Le;Andreas A. Malikopoulos","doi":"10.1109/LRA.2025.3585716","DOIUrl":"https://doi.org/10.1109/LRA.2025.3585716","url":null,"abstract":"In this work, we propose a framework for adapting the controller's parameters based on learning optimal solutions from contextual black-box optimization problems. We consider a class of control design problems for dynamical systems operating in different environments or conditions represented by contextual parameters. The overarching goal is to identify the controller parameters that maximize the controlled system's performance, given different realizations of the contextual parameters. We formulate a contextual Bayesian optimization problem in which the solution is actively learned using Gaussian processes to approximate the controller adaptation strategy. We demonstrate the efficacy of the proposed framework with a sim-to-real example. We learn the optimal weighting strategy of a model predictive control for connected and automated vehicles interacting with human-driven vehicles from simulations and then deploy it in a real-time experiment.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 8","pages":"8308-8315"},"PeriodicalIF":4.6,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144597655","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}
Resul Dagdanov;Milan Andrejević;Dikai Liu;Chin-Teng Lin
{"title":"Improving Trust Estimation in Human-Robot Collaboration Using Beta Reputation at Fine-Grained Timescales","authors":"Resul Dagdanov;Milan Andrejević;Dikai Liu;Chin-Teng Lin","doi":"10.1109/LRA.2025.3585653","DOIUrl":"https://doi.org/10.1109/LRA.2025.3585653","url":null,"abstract":"When interacting with each other, humans adjust their behavior based on perceived trust. To achieve similar adaptability, robots must accurately estimate human trust at sufficiently granular timescales while collaborating with humans. Beta reputation is a popular way to formalize a mathematical estimation of human trust. However, it relies on binary performance, which updates trust estimations only after each task concludes. Additionally, manually crafting a reward function is the usual method of building a performance indicator, which is labor-intensive and time-consuming. These limitations prevent efficient capture of continuous trust changes at more granular timescales throughout the collaboration task. Therefore, this letter presents a new framework for the estimation of human trust using beta reputation at fine-grained timescales. To achieve granularity in beta reputation, we utilize continuous reward values to update trust estimates at each timestep of a task. We construct a continuous reward function using maximum entropy optimization to eliminate the need for the laborious specification of a performance indicator. The proposed framework improves trust estimations by increasing accuracy, eliminating the need to manually craft a reward function, and advancing toward the development of more intelligent robots.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 8","pages":"8562-8569"},"PeriodicalIF":4.6,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144641080","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}
Liana Bertoni;Lorenzo Baccelliere;Luca Muratore;Nikos G. Tsagarakis
{"title":"A Proximity-Based Framework for Human-Robot Seamless Close Interactions","authors":"Liana Bertoni;Lorenzo Baccelliere;Luca Muratore;Nikos G. Tsagarakis","doi":"10.1109/LRA.2025.3585762","DOIUrl":"https://doi.org/10.1109/LRA.2025.3585762","url":null,"abstract":"The administration and monitoring of shared workspaces are crucial for seamlessly integrating robots to operate in close interactions with humans. Adaptive, versatile, and reliable robot movements are key to achieving effective and successful human-robot synergy. In situations involving unexpected or unintended collisions, robots must react appropriately to minimize risks to humans while still staying focused on their primary tasks or safely resuming them. Although collision detection and identification algorithms are well-established, more advanced robot reactions beyond basic stop-and-wait reactions have not yet been widely adopted and understood. This limitation highlights the need for more sophisticated robot responses to better handle complex collision scenarios, ensuring both safety and task continuity. This letter introduces a novel complete robotic system that leverages the potential of on-board proximity sensor equipment to seamlessly furnish compatible robot reactions while operating in close interactions. With on-board distributed proximity sensors, the robot gains a continuous close workspace awareness, facilitating a transparent negotiation of potential collisions while executing tasks. The proposed system and framework are validated in a collaborative industrial task scenario composed of sub-tasks allocated to the human and the robot and performed within shared regions of the workspace, demonstrating the efficacy of the approach.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 8","pages":"8514-8521"},"PeriodicalIF":4.6,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144634685","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}
Oliver Grainge;Michael J. Milford;Indu Bodala;Sarvapali D. Ramchurn;Shoaib Ehsan
{"title":"TeTRA-VPR: A Ternary Transformer Approach for Compact Visual Place Recognition","authors":"Oliver Grainge;Michael J. Milford;Indu Bodala;Sarvapali D. Ramchurn;Shoaib Ehsan","doi":"10.1109/LRA.2025.3585715","DOIUrl":"https://doi.org/10.1109/LRA.2025.3585715","url":null,"abstract":"Visual Place Recognition (VPR) localizes a query image by matching it against a database of geo-tagged reference images, making it essential for navigation and mapping in robotics. Although Vision Transformer (ViT) solutions deliver high accuracy, their large models often exceed the memory and compute budgets of resource-constrained platforms such as drones and mobile robots. To address this issue, we propose <italic>TeTRA</i>, a ternary transformer approach that progressively quantizes the ViT backbone to 2-bit precision and binarizes its final embedding layer, offering substantial reductions in model size and latency. A carefully designed progressive distillation strategy preserves the representational power of a full-precision teacher, allowing <italic>TeTRA</i> to retain or even surpass the accuracy of uncompressed convolutional counterparts, despite using fewer resources. Experiments on standard VPR benchmarks demonstrate that TeTRA reduces memory consumption by up to 69% compared to efficient baselines, while lowering inference latency by 35%, with either no loss or a slight improvement in recall@1. These gains enable high-accuracy VPR on power-constrained, memory-limited robotic platforms, making <italic>TeTRA</i> an appealing solution for real-world deployment.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 8","pages":"8396-8403"},"PeriodicalIF":4.6,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144611941","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}
Zongwu Xie;Guanghu Xie;Yang Liu;Yonglong Zhang;Baoshi Cao;Yiming Ji;Zhengpu Wang;Hong Liu
{"title":"DexMGNet: Multi-Mode Dexterous Grasping in Cluttered Scenes With Generative Models","authors":"Zongwu Xie;Guanghu Xie;Yang Liu;Yonglong Zhang;Baoshi Cao;Yiming Ji;Zhengpu Wang;Hong Liu","doi":"10.1109/LRA.2025.3585761","DOIUrl":"https://doi.org/10.1109/LRA.2025.3585761","url":null,"abstract":"Dexterous grasping is a crucial technique in humanoid robot manipulation. However, existing methods still fall short in effectively detecting dexterous grasps in cluttered environments. In this work, we propose DexMGNet, a novel multi-mode dexterous grasping framework designed for such challenging scenarios. We introduce the concept of pre-grasping and redefine dexterous grasping to enhance adaptability. We propose an effective pre-grasp and grasp data sampling strategy and develop a conditional generative model for grasp and pre-grasp generation. Additionally, we integrate pre-grasp collision detection within the hand's workspace, significantly improving grasping performance in cluttered environments. Our method supports multi-mode grasping, including two-finger, three-finger, and four-finger grasps, enabling greater flexibility across diverse grasping tasks. In real-world desktop grasping experiments, our approach achieves a 93.3% success rate in single-object scenes and a 78.3% success rate in multi-object scenes, demonstrating its effectiveness and superiority.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 8","pages":"8483-8490"},"PeriodicalIF":4.6,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144634726","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 Minimal Solvers for Relative Pose Estimation With Known Rotation Angle","authors":"Qianliang Wu;Yaqing Ding;Jin Xie;Jian Yang","doi":"10.1109/LRA.2025.3585382","DOIUrl":"https://doi.org/10.1109/LRA.2025.3585382","url":null,"abstract":"In this letter, we propose novel minimal solvers for calibrated relative pose estimation with a known rotation angle. This scenario is particularly relevant for devices such as smartphones, tablets, and camera-IMU (Inertial Measurement Unit) systems, where gyroscopes provide precise measurements of the rotation angle. By leveraging the prior knowledge of the rotation angle from the gyroscope, the relative rotation between two views can be reduced to 2 degrees of freedom (DOF), and the relative pose estimation problem is simplified to 4-DOF. This reduction enables the estimation of the relative pose using only four-point correspondences. Unlike previous approaches, we address both cases where the four points are in general positions or coplanar. For points in general positions, we present a straightforward yet effective method to eliminate specific monomials in the equations, leading to a more computationally efficient solution. For coplanar points, we establish a connection between the homography matrix and the essential matrix, introducing new constraints on the homography matrix. Based on these constraints, we derive a new solver for homography-based relative pose estimation with a known rotation angle. We provide comprehensive analyses and comparisons against state-of-the-art algorithms, demonstrating the superior efficiency and effectiveness of our proposed method. Our results highlight the practical applicability of our solvers in real-world scenarios, particularly for devices equipped with IMUs.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 8","pages":"8404-8410"},"PeriodicalIF":4.6,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144611533","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":"Delicate Operation of a Microneedle-Forceps Mechanism for Ultra-Flexible Probe Implantation","authors":"Hanwei Chen;Bo Han;Chao Liu;Xinjun Sheng","doi":"10.1109/LRA.2025.3585356","DOIUrl":"https://doi.org/10.1109/LRA.2025.3585356","url":null,"abstract":"The implantation of ultra-flexible neural probes is one of the key technical challenges in the field of brain-computer interfaces. Existing implantation techniques are constrained in both the overall surgical procedure and operational reliability. This study introduces a novel microneedle-forceps mechanism designed to implant ultra-flexible probes individually into brain tissue. A multimode motion control framework based on multiple linear actuators and a hybrid PID controller is developed for delicate manipulation of the probes. A needle-probe interaction model is established for force analysis in the peeling and insertion process. Detailed experiments are conducted to demonstrate the clamping ability of forceps to promote probe peeling and reduce needle deflection. Moreover, cooperative pull-up, insertion, release and retraction by the microneedle-forceps are validated to achieve multiple probe implantations within a single insertion duration of 10 s and a density of 0.2 mm.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 8","pages":"8427-8434"},"PeriodicalIF":4.6,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144623871","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":"HIPPo: Harnessing Image-to-3D Priors for Model-Free Zero-Shot 6D Pose Estimation","authors":"Yibo Liu;Zhaodong Jiang;Binbin Xu;Guile Wu;Yuan Ren;Tongtong Cao;Bingbing Liu;Rui Heng Yang;Amir Rasouli;Jinjun Shan","doi":"10.1109/LRA.2025.3585384","DOIUrl":"https://doi.org/10.1109/LRA.2025.3585384","url":null,"abstract":"This work focuses on the problem of 6D pose estimation for novel objects when a reference 3D model or posed reference images are not available. While existing methods can estimate the precise 6D pose of objects, they heavily rely on curated CAD models or reference images, the preparation of which is a time-consuming and labor-intensive process. Moreover, in real-world scenarios, 3D models or reference images may not be available in advance and instant robot reaction is desired. In this work, we propose a novel framework named HIPPo, which eliminates the need for curated CAD models and reference images by harnessing image-to-3D priors from Diffusion Models, enabling model-free zero-shot 6D pose estimation. Specifically, we construct HIPPo Dreamer, a rapid image-to-mesh model built on a multiview Diffusion Model and a 3D reconstruction foundation model. Our HIPPo Dreamer can generate a 3D mesh of any unseen objects from a single glance in just a few seconds. Then, as more observations are acquired, we propose to continuously refine the diffusion prior mesh model by joint optimization of object geometry and appearance. This is achieved by a measurement-guided scheme that gradually replaces the plausible diffusion priors with more reliable online observations. Consequently, HIPPo can instantly estimate and track the 6D pose of a novel object and maintain a complete mesh for immediate robotic applications. Thorough experiments on various benchmarks show that HIPPo outperforms state-of-the-art methods in 6D object pose estimation when prior reference images are limited.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 8","pages":"8284-8291"},"PeriodicalIF":4.6,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144597720","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}
Michael Neumeier;Nael Fasfous;Bing Li;Axel von Arnim
{"title":"SpikeClouds: Streaming Spike-Based Processing of LiDAR for Fast and Efficient Object Detection","authors":"Michael Neumeier;Nael Fasfous;Bing Li;Axel von Arnim","doi":"10.1109/LRA.2025.3585394","DOIUrl":"https://doi.org/10.1109/LRA.2025.3585394","url":null,"abstract":"LiDAR sensors are used to provide three-dimensional information about the environment in many robotics applications. The information, accumulated in 3D point clouds, is first acquired by the sensor and then processed further, which leads to high end-to-end latencies and large memory footprints. Streaming approaches tackle this problem by processing partial point cloud data during scanning of the environment. In contrast to existing work that is limited to power hungry, rotating mechanical scanners, in this letter, we present a streaming method for more efficient scanline-based LiDAR sensors. We process the sequence of scanlines in form of SpikeClouds with a Spiking Neural Network (SNN) backbone and perform 3D object detection from the accumulated information using a Convolutional Neural Network (CNN) head. Our method achieves close to state-of-the-art detection performance on datasets KITTI and JRDB22 while reducing the end-to-end latency by 10% and the average memory footprint by 95% on standard GPU hardware. Additionally, when ported onto neuromorphic hardware, our backbone requires 25× less energy compared to reference backbones. SpikeClouds achieves fast and efficient environmental perception for robotic applications by streaming LiDAR to enable spike-based processing.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 8","pages":"8411-8418"},"PeriodicalIF":4.6,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144611940","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":"State Torque Synergy-Based Comprehensive Design Method for Wire-Driven Flexible Robot Hands","authors":"Rina Kusuhara;Mitsuru Higashimori","doi":"10.1109/LRA.2025.3585365","DOIUrl":"https://doi.org/10.1109/LRA.2025.3585365","url":null,"abstract":"This letter presents a novel design method for wire-driven flexible robot hands. Conventional methods generally focus on the correlation patterns of desired postures called postural synergy. In contrast, the proposed method introduces state torque aggregating the influence of posture, contact force, and gravity. Utilizing the correlation patterns of state torques, referred to as state torque synergy, we achieve a comprehensive design for reproducing the desired postures and contact forces, including gravity compensation. First, based on an analytical model, the equilibrium equation of the torque acting on the hand is derived. The components of the equation are clearly separated into two torques: the mechanism torque depending on the wire routings and natural posture, and the state torque depending on the posture and contact forces. Next, giving multiple desired states as a design index, a design method for the hand mechanism is developed. Each desired state is converted to the desired state torque, and the state torque synergy is derived by principal component analysis. Based on the isomorphism of the mathematical structure in the state torque synergy and the mechanism torque, the mechanism parameters are analytically determined. Finally, through the design and development of a hand, the proposed method is validated.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"10 8","pages":"8578-8585"},"PeriodicalIF":4.6,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144641076","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}