IEEE Robotics and Automation Letters最新文献

{"title":"Online Learning-Based Inertial Parameter Identification of Unknown Object for Model-Based Control of Wheeled Humanoids","authors":"Donghoon Baek;Bo Peng;Saurabh Gupta;Joao Ramos","doi":"10.1109/LRA.2024.3483039","DOIUrl":"https://doi.org/10.1109/LRA.2024.3483039","url":null,"abstract":"Identifying the dynamic properties of manipulated objects is essential for safe and accurate robot control. Most methods rely on low-noise force-torque sensors, long exciting signals, and solving nonlinear optimization problems, making the estimation process slow. In this work, we propose a fast, online learning-based inertial parameter estimation framework that enhances model-based control. We aim to quickly and accurately estimate the parameters of an unknown object using only the robot's proprioception through end-to-end learning, which is applicable for real-time system. To effectively capture features in robot proprioception solely affected by object dynamics and address the challenge of obtaining ground truth inertial parameters in the real world, we developed a high-fidelity simulation that uses more accurate robot dynamics through real-to-sim adaptation. Since our adaptation focuses solely on the robot, task-relevant data (e.g., holding an object) is not required from the real world, simplifying the data collection process. Moreover, we address both parametric and non-parametric modeling errors independently using \u0000<italic>Robot System Identification</i>\u0000 and \u0000<italic>Gaussian Processes</i>\u0000. We validate our estimator to assess how quickly and accurately it can estimate physically feasible parameters of an manipulated object given a specific trajectory obtained from a wheeled humanoid robot. Our estimator achieves faster estimation speeds (around 0.1 seconds) while maintaining accuracy comparable to other methods. Additionally, our estimator further highlight its benefits in improving the performance of model based control by compensating object's dynamics and re initializing new equilibrium point of wheeled humanoid.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11154-11161"},"PeriodicalIF":4.6,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142598630","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":"Effective Search for Control Hierarchies Within the Policy Decomposition Framework","authors":"Ashwin Khadke;Hartmut Geyer","doi":"10.1109/LRA.2024.3483635","DOIUrl":"https://doi.org/10.1109/LRA.2024.3483635","url":null,"abstract":"Policy decomposition is a novel framework for approximating optimal control policies of complex dynamical systems with a hierarchy of policies derived from smaller but tractable subsystems. It stands out amongst the class of hierarchical control methods by estimating \u0000<italic>a priori</i>\u0000 how well the closed-loop behavior of different control hierarchies matches the optimal policy. However, the number of possible hierarchies grows prohibitively with the number of inputs and the dimension of the state-space of the system making it unrealistic to estimate the closed-loop performance for all hierarchies. Here, we present the development of two search methods based on Genetic Algorithm and Monte-Carlo Tree Search to tackle this combinatorial challenge, and demonstrate that it is indeed surmountable. We showcase the efficacy of our search methods and the generality of the framework by applying it towards finding hierarchies for control of three distinct robotic systems: a simplified biped, a planar manipulator, and a quadcopter. The discovered hierarchies, in comparison to heuristically designed ones, provide improved closed-loop performance or can be computed in minimal time with marginally worse control performance, and also exceed the control performance of policies obtained with popular deep reinforcement learning methods.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11114-11121"},"PeriodicalIF":4.6,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600220","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":"Fast Decentralized State Estimation for Legged Robot Locomotion via EKF and MHE","authors":"Jiarong Kang;Yi Wang;Xiaobin Xiong","doi":"10.1109/LRA.2024.3483043","DOIUrl":"https://doi.org/10.1109/LRA.2024.3483043","url":null,"abstract":"In this letter, we present a fast and decentralized state estimation framework for the control of legged locomotion. The nonlinear estimation of the floating base states is decentralized to \u0000<italic>an orientation estimation via Extended Kalman Filter (EKF)</i>\u0000 and \u0000<italic>a linear velocity estimation via Moving Horizon Estimation (MHE)</i>\u0000. The EKF fuses the inertia sensor with vision to estimate the floating base orientation. The MHE uses the estimated orientation with all the sensors within a time window in the past to estimate the linear velocities based on a time-varying linear dynamics formulation of the interested states with state constraints. More importantly, a marginalization method based on the optimization structure of the full information filter (FIF) is proposed to convert the equality-constrained FIF to an equivalent MHE. This decoupling of state estimation promotes the desired balance of computation efficiency, accuracy of estimation, and the inclusion of state constraints. The proposed method is shown to be capable of providing accurate state estimation to several legged robots, including the highly dynamic hopping robot PogoX, the bipedal robot Cassie, and the quadrupedal robot Unitree Go1, with a frequency at 200 Hz and a window interval of 0.1 s.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"10914-10921"},"PeriodicalIF":4.6,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142524132","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":"ViTract: Robust Object Shape Perception via Active Visuo-Tactile Interaction","authors":"Anirvan Dutta;Etienne Burdet;Mohsen Kaboli","doi":"10.1109/LRA.2024.3483037","DOIUrl":"https://doi.org/10.1109/LRA.2024.3483037","url":null,"abstract":"An essential problem in robotic systems that are to be deployed in unstructured environments is the accurate and autonomous perception of the shapes of previously unseen objects. Existing methods for shape estimation or reconstruction have leveraged either visual or tactile interactive exploration techniques or have relied on comprehensive visual or tactile information acquired in an offline manner. In this letter, a novel visuo-tactile interactive perception framework- ViTract, is introduced for shape estimation of unseen objects. Our framework estimates the shape of diverse objects robustly using low-dimensional, efficient, and generalizable shape primitives, which are superquadrics. The probabilistic formulation within our framework takes advantage of the complementary information provided by vision and tactile observations while accounting for associated noise. As part of our framework, we propose a novel modality-specific information gain to select the most informative and reliable exploratory action (using vision/tactile) to obtain iterative visuo/tactile information. Our real-robot experiments demonstrate superior and robust performance compared to state-of-the-art visuo-tactile-based shape estimation techniques.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11250-11257"},"PeriodicalIF":4.6,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10720798","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142598644","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":"Improving Visual Place Recognition Based Robot Navigation by Verifying Localization Estimates","authors":"Owen Claxton;Connor Malone;Helen Carson;Jason J. Ford;Gabe Bolton;Iman Shames;Michael Milford","doi":"10.1109/LRA.2024.3483045","DOIUrl":"https://doi.org/10.1109/LRA.2024.3483045","url":null,"abstract":"Visual Place Recognition (VPR) systems often have imperfect performance, affecting the ‘integrity’ of position estimates and subsequent robot navigation decisions. Previously, SVM classifiers have been used to monitor VPR integrity. This research introduces a novel Multi-Layer Perceptron (MLP) integrity monitor which demonstrates improved performance and generalizability, removing per-environment training and reducing manual tuning requirements. We test our proposed system in extensive real-world experiments, presenting two real-time integrity-based VPR verification methods: a single-query rejection method for robot navigation to a goal zone (Experiment 1); and a history-of-queries method that takes a best, verified, match from its recent trajectory and uses an odometer to extrapolate a current position estimate (Experiment 2). Noteworthy results for Experiment 1 include a decrease in aggregate mean along-track goal error from \u0000<inline-formula><tex-math>$ approx !9.8;{text{m}}$</tex-math></inline-formula>\u0000 to \u0000<inline-formula><tex-math>$ approx !3.1;{text{m}}$</tex-math></inline-formula>\u0000, and an increase in the aggregate rate of successful mission completion from \u0000<inline-formula><tex-math>$approx !41%$</tex-math></inline-formula>\u0000 to \u0000<inline-formula><tex-math>$approx !55%$</tex-math></inline-formula>\u0000. Experiment 2 showed a decrease in aggregate mean along-track localization error from \u0000<inline-formula><tex-math>$ approx !2.0;{text{m}}$</tex-math></inline-formula>\u0000 to \u0000<inline-formula><tex-math>$ approx !0.5;{text{m}}$</tex-math></inline-formula>\u0000, and an increase in the aggregate localization precision from \u0000<inline-formula><tex-math>$approx !97%$</tex-math></inline-formula>\u0000 to \u0000<inline-formula><tex-math>$approx !99%$</tex-math></inline-formula>\u0000. Overall, our results demonstrate the practical usefulness of a VPR integrity monitor in real-world robotics to improve VPR localization and consequent navigation performance.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11098-11105"},"PeriodicalIF":4.6,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600251","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":"Long-Term Human Trajectory Prediction Using 3D Dynamic Scene Graphs","authors":"Nicolas Gorlo;Lukas Schmid;Luca Carlone","doi":"10.1109/LRA.2024.3482169","DOIUrl":"https://doi.org/10.1109/LRA.2024.3482169","url":null,"abstract":"We present a novel approach for long-term human trajectory prediction in indoor human-centric environments, which is essential for long-horizon robot planning in these environments. State-of-the-art human trajectory prediction methods are limited by their focus on collision avoidance and short-term planning, and their inability to model complex interactions of humans with the environment. In contrast, our approach overcomes these limitations by predicting sequences of human interactions with the environment and using this information to guide trajectory predictions over a horizon of up to \u0000<inline-formula><tex-math>$mathrm{60}$</tex-math></inline-formula>\u0000<inline-formula><tex-math>$mathrm{s}$</tex-math></inline-formula>\u0000. We leverage Large Language Models (LLMs) to predict interactions with the environment by conditioning the LLM prediction on rich contextual information about the scene. This information is given as a 3D Dynamic Scene Graph that encodes the geometry, semantics, and traversability of the environment into a hierarchical representation. We then ground these interaction sequences into multi-modal spatio-temporal distributions over human positions using a probabilistic approach based on continuous-time Markov Chains. To evaluate our approach, we introduce a new semi-synthetic dataset of long-term human trajectories in complex indoor environments, which also includes annotations of human-object interactions. We show in thorough experimental evaluations that our approach achieves a 54% lower average negative log-likelihood and a 26.5% lower Best-of-20 displacement error compared to the best non-privileged (i.e., evaluated in a zero-shot fashion on the dataset) baselines for a time horizon of \u0000<inline-formula><tex-math>$mathrm{60}$</tex-math></inline-formula>\u0000<inline-formula><tex-math>$mathrm{s}$</tex-math></inline-formula>\u0000.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"10978-10985"},"PeriodicalIF":4.6,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565561","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":"Simulation of Optical Tactile Sensors Supporting Slip and Rotation Using Path Tracing and IMPM","authors":"Zirong Shen;Yuhao Sun;Shixin Zhang;Zixi Chen;Heyi Sun;Fuchun Sun;Bin Fang","doi":"10.1109/LRA.2024.3481829","DOIUrl":"https://doi.org/10.1109/LRA.2024.3481829","url":null,"abstract":"Optical tactile sensors are extensively utilized in intelligent robot manipulation due to their ability to acquire high-resolution tactile information at a lower cost. However, achieving adequate reality and versatility in simulating optical tactile sensors is challenging. In this letter, we propose a simulation method and validate its effectiveness through experiments. We utilize path tracing for image rendering, achieving higher similarity to real data than the baseline method in simulating pressing scenarios. Additionally, we apply the improved Material Point Method(IMPM) algorithm to simulate the relative rest between the object and the elastomer surface when the object is in motion, enabling more accurate simulation of complex manipulations such as slip and rotation.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"11218-11225"},"PeriodicalIF":4.6,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142598678","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":"BEVNav: Robot Autonomous Navigation via Spatial-Temporal Contrastive Learning in Bird's-Eye View","authors":"Jiahao Jiang;Yuxiang Yang;Yingqi Deng;Chenlong Ma;Jing Zhang","doi":"10.1109/LRA.2024.3482190","DOIUrl":"https://doi.org/10.1109/LRA.2024.3482190","url":null,"abstract":"Goal-driven mobile robot navigation in map-less environments requires effective state representations for reliable decision-making. Inspired by the favorable properties of Bird's-Eye View (BEV) in point clouds for visual perception, this paper introduces a novel navigation approach named BEVNav. It employs deep reinforcement learning to learn BEV representations and enhance decision-making reliability. First, we propose a self-supervised spatial-temporal contrastive learning approach to learn BEV representations. Spatially, two randomly augmented views from a point cloud predict each other, enhancing spatial features. Temporally, we combine the current observation with consecutive frames' actions to predict future features, establishing the relationship between observation transitions and actions to capture temporal cues. Then, incorporating this spatial-temporal contrastive learning in the Soft Actor-Critic reinforcement learning framework, our BEVNav offers a superior navigation policy. Extensive experiments demonstrate BEVNav's robustness in environments with dense pedestrians, outperforming state-of-the-art methods across multiple benchmarks.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"10796-10802"},"PeriodicalIF":4.6,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142518167","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":"Enhanced Tiny Haptic Dial With T-Shaped Shaft Based on Magnetorheological Fluid","authors":"Yong Hae Heo;Seongho Kim;Sang-Youn Kim","doi":"10.1109/LRA.2024.3481830","DOIUrl":"https://doi.org/10.1109/LRA.2024.3481830","url":null,"abstract":"This letter introduces a tiny haptic dial utilizing magnetorheological fluid (MRF) to enhance its resistive torque feedback. Moreover, we design the T-shaped rotary shaft with bumps and embed it into the haptic dial to enhance its haptic performance (resistive torque). This structure enables two operation modes (shear and flow) of MRF that contribute to the actuation simultaneously in the proposed haptic dial. This structure allows the magnetic flux to flow towards the MRF, helping further maximize the resistive torque. We conduct a simulation to confirm that the magnetic flux generated from a solenoid forms a closed-loop magnetic path without magnetic saturation or leakage in the proposed haptic dial. The resistive torque of the proposed haptic dial varied from 8 N·mm to 47 N·mm as the input current changed from 0 to 300 mA, thus indicating that the proposed haptic dial can create a variety of haptic sensations in a tiny size (diameter: 20 mm; height: 20 mm).","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"10835-10841"},"PeriodicalIF":4.6,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142518170","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":"VibroBot: A Lightweight and Wirelessly Programmable Vibration Bot for Haptic Guidance","authors":"Xiaosa Li;Runze Zhao;Xinyue Chai;Zimo Wang;Qianqian Tong;Wenbo Ding","doi":"10.1109/LRA.2024.3481828","DOIUrl":"https://doi.org/10.1109/LRA.2024.3481828","url":null,"abstract":"Cutaneous haptics is helpful to tame the human-machine mismatch by interactive tactile feedback and perform precise manipulations for virtual immersive interactions. However, wearable tactile gloves cover the palm and fingers greatly, thus reducing the tactile information from interactive objects and causing the inconsistency between virtual and practical operations. In this work, we design a lightweight finger-worn vibration bot, named VibroBot, to provide the individual vibrotactile feedback to each finger without compromising the hand dexterity. Each VibroBot, weighing only 2.9 grams, integrates components of the power, a wireless chip and a coil actuator, to receive programmable waveform signals and perform the real-time vibration feedback wirelessly on finger. Our design features six rapidly distinguishable vibration modes with the 96.4% recognition rate in 2.0 s, each guiding one of three finger joints for flexing or extending to a specified angular range. When worn on all five fingers, VibroBots can collaboratively guide the user with multi-dimension semantics, to adjust five fingers for target hand gestures at the same time. In virtual gesture training experiments, VibroBots were used to correct users' muscle memory bias for common gestures, and reduced the average gesture error from about 30\u0000<inline-formula><tex-math>$^circ$</tex-math></inline-formula>\u0000 to less than 15\u0000<inline-formula><tex-math>$^circ$</tex-math></inline-formula>\u0000. Haptic guidance by VibroBots shows its potential in various Tactile Internet scenarios that require a large number of pretrained hand operations, such as robotic teleoperation and virtual surgical training.","PeriodicalId":13241,"journal":{"name":"IEEE Robotics and Automation Letters","volume":"9 12","pages":"10882-10889"},"PeriodicalIF":4.6,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142518182","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}