IEEE Transactions on Robotics最新文献_第10页

CliReg: Clique-Based Robust Point Cloud Registration CliReg：基于团的鲁棒点云配准

IF 9.4 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2025-02-19 DOI: 10.1109/TRO.2025.3542954

Javier Laserna Moratalla;Pablo San Segundo Carrillo;David Álvarez Sánchez

{"title":"CliReg: Clique-Based Robust Point Cloud Registration","authors":"Javier Laserna Moratalla;Pablo San Segundo Carrillo;David Álvarez Sánchez","doi":"10.1109/TRO.2025.3542954","DOIUrl":"10.1109/TRO.2025.3542954","url":null,"abstract":"We propose a branch-and-bound algorithm for robust rigid registration of two point clouds in the presence of a large number of outlier correspondences. For this purpose, we consider a maximum consensus formulation of the registration problem and reformulate it as a (large) maximal clique search in a correspondence graph, where a clique represents a complete rigid transformation. Specifically, we use a maximum clique algorithm to enumerate large maximal cliques and a fitness procedure that evaluates each clique by solving a least-squares optimization problem. The main advantages of our approach are 1) it is possible to exploit the cutting-edge optimization techniques employed by current exact maximum clique algorithms, such as partial maximum satisfiability-based bounds, branching by partitioning or the use of bitstrings, etc.; 2) the correspondence graphs are expected to be sparse in real problems (confirmed empirically in our tests), and, consequently, the maximum clique problem is expected to be easy; 3) it is possible to have a <italic>good control of suboptimality with a k-nearest neighbor analysis that determines the size of the correspondence graph as a function of <inline-formula> <tex-math>$k$</tex-math></inline-formula>. The new algorithm is called <monospace>CliReg</monospace> and has been implemented in C++. To evaluate <monospace>CliReg</monospace>, we have carried out extensive tests both on synthetic and real public datasets. The results show that <monospace>CliReg</monospace> clearly dominates the state of the art (e.g., <monospace>RANSAC</monospace>, <monospace>FGR</monospace>, and <monospace>TEASER++</monospace>) in terms of robustness, with a running time comparable to <monospace>TEASER++</monospace> and <monospace>RANSAC</monospace>. In addition, we have implemented a fast variant called <monospace>CliRegMutual</monospace> that performs similarly to the fastest heuristic <monospace>FGR</monospace>.","PeriodicalId":50388,"journal":{"name":"IEEE Transactions on Robotics","volume":"41 ","pages":"1898-1917"},"PeriodicalIF":9.4,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10892261","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143451609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

RING#: PR-By-PE Global Localization With Roto-Translation Equivariant Gram Learning 环#:PR-by-PE全局定位与旋转翻译等变图学习

IF 9.4 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2025-02-18 DOI: 10.1109/TRO.2025.3543267

Sha Lu;Xuecheng Xu;Dongkun Zhang;Yuxuan Wu;Haojian Lu;Xieyuanli Chen;Rong Xiong;Yue Wang

{"title":"RING#: PR-By-PE Global Localization With Roto-Translation Equivariant Gram Learning","authors":"Sha Lu;Xuecheng Xu;Dongkun Zhang;Yuxuan Wu;Haojian Lu;Xieyuanli Chen;Rong Xiong;Yue Wang","doi":"10.1109/TRO.2025.3543267","DOIUrl":"10.1109/TRO.2025.3543267","url":null,"abstract":"Global localization using onboard perception sensors, such as cameras and light detection and ranging (LiDAR) sensors, is crucial in autonomous driving and robotics applications when Global Positioning System (GPS) signals are unreliable. Most approaches achieve global localization by sequential place recognition (PR) and pose estimation (PE). Some methods train separate models for each task, while others employ a single model with dual heads, trained jointly with separate task-specific losses. However, the accuracy of localization heavily depends on the success of PR, which often fails in scenarios with significant changes in viewpoint or environmental appearance. Consequently, this renders the final PE of localization ineffective. To address this, we introduce a new paradigm, <italic>PR-by-PE localization, which bypasses the need for separate PR by directly deriving it from PE. We propose RING#, an end-to-end <italic>PR-by-PE localization network that operates in the bird's-eye-view (BEV) space, compatible with both vision and LiDAR sensors. RING# incorporates a novel design that learns two equivariant representations from BEV features, enabling globally convergent and computationally efficient PE. Comprehensive experiments on the north campus long-term vision and LiDAR (NCLT) and Oxford datasets show that RING# outperforms state-of-the-art methods in both vision and LiDAR modalities, validating the effectiveness of the proposed approach.","PeriodicalId":50388,"journal":{"name":"IEEE Transactions on Robotics","volume":"41 ","pages":"1861-1881"},"PeriodicalIF":9.4,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143546115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 Differential-Mechanism-Based Leg Configuration Balances the Load and Dynamic Contribution for All Actuators of the Quadruped Robot 基于差动机构的四足机器人腿结构平衡了所有执行机构的负载和动态贡献

IF 9.4 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2025-02-18 DOI: 10.1109/TRO.2025.3543262

Zeyu Wang;Wenchuan Jia;Yi Sun;Tianxu Bao;Zihan Ding;Qi Chen

{"title":"A Differential-Mechanism-Based Leg Configuration Balances the Load and Dynamic Contribution for All Actuators of the Quadruped Robot","authors":"Zeyu Wang;Wenchuan Jia;Yi Sun;Tianxu Bao;Zihan Ding;Qi Chen","doi":"10.1109/TRO.2025.3543262","DOIUrl":"10.1109/TRO.2025.3543262","url":null,"abstract":"Kinematic performance of a quadruped robot is determined by the mechanical structure. This article presents a novel leg structure for legged robots that integrates a differential mechanism into the conventional design. This approach enables all actuators to be positioned within the robot's torso at fixed locations, significantly reducing the leg's inertia. Furthermore, the new structure introduces a parallel transmission system that balances motion and torque distribution among the joint actuators, effectively reducing torque peaks and enhancing the drive capability during dynamic motions. A family of configurations of differential leg structures is constructed, and their mapping to the classic serial leg structure is dissected in kinematic and mathematic. Simulations of various single-leg models are conducted to validate the performance of the new configuration under typical gait conditions. Subsequently, a leg prototype is designed, manufactured, and tested in experiments involving tasks, such as trajectory tracking, weighted squats, and squat jumps. The development of a prototype quadruped robot featuring this novel leg structure is also presented.","PeriodicalId":50388,"journal":{"name":"IEEE Transactions on Robotics","volume":"41 ","pages":"2014-2030"},"PeriodicalIF":9.4,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10891906","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143443333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

From Flies to Robots: Inverted Landing in Small Quadcopters With Dynamic Perching 从苍蝇到机器人：小型四轴飞行器的动态着陆

IF 9.4 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2025-02-18 DOI: 10.1109/TRO.2025.3543263

Bryan Habas;Bo Cheng

{"title":"From Flies to Robots: Inverted Landing in Small Quadcopters With Dynamic Perching","authors":"Bryan Habas;Bo Cheng","doi":"10.1109/TRO.2025.3543263","DOIUrl":"10.1109/TRO.2025.3543263","url":null,"abstract":"Inverted landing is a routine behavior among a number of animal fliers. However, mastering this feat poses a considerable challenge for robotic fliers, especially to perform dynamic perching with rapid body rotations (or flips) and landing against gravity. Inverted landing in flies have suggested that optical flow senses are closely linked to the precise triggering and control of body flips that lead to a variety of successful landing behaviors. Building upon this knowledge, we aimed to replicate the flies' landing behaviors in small quadcopters by developing a control policy general to arbitrary ceiling-approach conditions. First, we employed reinforcement learning in simulation to optimize discrete sensory-motor pairs across a broad spectrum of ceiling-approach velocities and directions. Next, we converted the sensory-motor pairs to a two-stage control policy in a continuous optical flow space augmented by ceiling distance measurement. The control policy consists of a first-stage Flip-Trigger Policy, which employs a one-class support vector machine, and a second-stage Flip-Action Policy, implemented as a feed-forward neural network. To transfer the inverted-landing policy to physical systems, we utilized domain randomization and system identification techniques for a zero-shot sim-to-real transfer with emulated optical flow using external motion tracking. As a result, we successfully achieved a range of robust inverted-landing behaviors in small quadcopters, emulating those observed in flies.","PeriodicalId":50388,"journal":{"name":"IEEE Transactions on Robotics","volume":"41 ","pages":"1773-1790"},"PeriodicalIF":9.4,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143443308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

System Design of a Soft Underwater Exosuit to Reduce Metabolic Cost Across Multiple Aquatic Movements During Diving 降低潜水过程中多种水上运动代谢成本的软式水下外服系统设计

IF 9.4 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2025-02-18 DOI: 10.1109/TRO.2025.3543264

Xiangyang Wang;Chunjie Chen;Jianquan Sun;Sida Du;Yue Ma;Xinyu Wu

{"title":"System Design of a Soft Underwater Exosuit to Reduce Metabolic Cost Across Multiple Aquatic Movements During Diving","authors":"Xiangyang Wang;Chunjie Chen;Jianquan Sun;Sida Du;Yue Ma;Xinyu Wu","doi":"10.1109/TRO.2025.3543264","DOIUrl":"10.1109/TRO.2025.3543264","url":null,"abstract":"Assisting underwater movements improves divers' efficiency and reduces the risk of decompression sickness from physical activity. Although exoskeletons have been developed for numerous land-based scenarios, their application in underwater diving remains unexplored. This article proposes a soft underwater lower-limb exosuit designed to assist three aquatic movements: flutter kick, breaststroke kick, and underwater walk. We presented the mechanical design of the exosuit that is capable of assisting bidirectional leg movements in full kicking/gait cycle, while ensuring natural leg mobility without impeding normal leg function. A cascade force integral controller is also designed to resolve issues related to uncontrollable states and stiffness variations within the system. To verify the assistive performance of the system, experiments were conducted with nine participants to assess how the proposed exosuit aids in reducing metabolic cost across various motion patterns and frequencies. The findings indicate that the underwater exosuit effectively reduces the air consumption rate by <inline-formula><tex-math>$29.77pm 7.68$</tex-math></inline-formula>% during flutter kick, <inline-formula><tex-math>$25.70pm 5.99$</tex-math></inline-formula>% during breaststroke kick, and <inline-formula><tex-math>$18.35pm 4.53$</tex-math></inline-formula>% during underwater walk.","PeriodicalId":50388,"journal":{"name":"IEEE Transactions on Robotics","volume":"41 ","pages":"2127-2143"},"PeriodicalIF":9.4,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143443335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

AAGE: Air-Assisted Ground Robotic Autonomous Exploration in Large-Scale Unknown Environments AAGE：空中辅助地面机器人在大规模未知环境中的自主探索

IF 9.4 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2025-02-18 DOI: 10.1109/TRO.2025.3543275

Lanxiang Zheng;Mingxin Wei;Ruidong Mei;Kai Xu;Junlong Huang;Hui Cheng

{"title":"AAGE: Air-Assisted Ground Robotic Autonomous Exploration in Large-Scale Unknown Environments","authors":"Lanxiang Zheng;Mingxin Wei;Ruidong Mei;Kai Xu;Junlong Huang;Hui Cheng","doi":"10.1109/TRO.2025.3543275","DOIUrl":"10.1109/TRO.2025.3543275","url":null,"abstract":"The article presents an air-assisted ground robotic autonomous exploration framework, which leverages the high mobility and wide aerial perspective of unmanned aerial vehicles (UAVs) to assist unmanned ground vehicles (UGVs) in detailed exploration, enhancing exploration efficiency and improving the quality of point cloud collection in regions of interest in large-scale, unknown environments. In this framework, the UAV, equipped with an onboard RGB camera, rapidly surveys large unknown areas and generates a bird's eye view (BEV) to identify critical zones for UGV exploration. With prior information about the unexplored area's outline from the real-time shared BEV, the UGV can carry out more efficient and informed exploration from a global perspective. To maximize the utility of this prior information and optimize point cloud collection, a hierarchical exploration strategy and an attention mechanism are incorporated to guide the UGV's focus toward areas requiring detailed mapping, rather than broad, featureless regions. Real-world experiments validate the effectiveness of the framework, demonstrating significant improvements in exploration efficiency and point cloud collection compared to state-of-the-art methods. The results further show that even with a coarse BEV, the UGV's exploration efficiency is greatly enhanced.","PeriodicalId":50388,"journal":{"name":"IEEE Transactions on Robotics","volume":"41 ","pages":"1918-1937"},"PeriodicalIF":9.4,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143443336","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

COLA: COarse-LAbel Multisource LiDAR Semantic Segmentation for Autonomous Driving 面向自动驾驶的粗标签多源激光雷达语义分割

IF 9.4 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2025-02-18 DOI: 10.1109/TRO.2025.3543302

Jules Sanchez;Jean-Emmanuel Deschaud;François Goulette

{"title":"COLA: COarse-LAbel Multisource LiDAR Semantic Segmentation for Autonomous Driving","authors":"Jules Sanchez;Jean-Emmanuel Deschaud;François Goulette","doi":"10.1109/TRO.2025.3543302","DOIUrl":"10.1109/TRO.2025.3543302","url":null,"abstract":"LiDAR semantic segmentation (LSS) for autonomous driving has been a growing field of interest in recent years. Datasets and methods have appeared and expanded very quickly, but methods have not been updated to exploit this new data availability and rely on the same classical datasets. Different ways of performing LSS training and inference can be divided into several subfields, which include the following: domain generalization, source-to-source segmentation, and pretraining. In this work, we aim to improve results in all of these subfields with the novel approach of multisource training. Multisource training relies on the availability of various datasets at training time. To overcome the common obstacles in multisource training, we introduce the coarse labels and call the newly created multisource dataset COLA. We propose three applications of this new dataset that display systematic improvement over single-source strategies: COLA-DG for domain generalization (+10% ), COLA-S2S for source-to-source segmentation (+5.3% ), and COLA-PT for pretraining (+12% ). We demonstrate that multisource approaches bring systematic improvement over single-source approaches.","PeriodicalId":50388,"journal":{"name":"IEEE Transactions on Robotics","volume":"41 ","pages":"1742-1754"},"PeriodicalIF":9.4,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143443305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Distributed Multirobot Multitarget Tracking Using Heterogeneous Limited-Range Sensors 基于异构有限距离传感器的分布式多机器人多目标跟踪

IF 9.4 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2025-02-18 DOI: 10.1109/TRO.2025.3543303

Jun Chen;Mohammed Abugurain;Philip Dames;Shinkyu Park

{"title":"Distributed Multirobot Multitarget Tracking Using Heterogeneous Limited-Range Sensors","authors":"Jun Chen;Mohammed Abugurain;Philip Dames;Shinkyu Park","doi":"10.1109/TRO.2025.3543303","DOIUrl":"10.1109/TRO.2025.3543303","url":null,"abstract":"Utilizing heterogeneous mobile sensors to actively gather information improves adaptability and reliability in extended environments. This article presents a cooperative multirobot multitarget search and tracking framework aimed at enhancing the efficiency of the heterogeneous sensor network, and consequently, improving the overall target tracking accuracy. The concept of <italic>normalized unused sensing capacity is introduced to quantify the information a sensor is currently gathering relative to its theoretical maximum. This measurement can be computed using entirely local information and is applicable to various sensor models, distinguishing it from previous literature on the subject. It is then utilized to develop a heuristics distributed coverage control strategy for a heterogeneous sensor network, adaptively balancing the workload based on each sensor's current unused capacity. The algorithm is validated through a series of robot operating system (ROS) and <sc>MATLAB simulations, demonstrating superior results compared to standard approaches that do not account for heterogeneity or current usage rates.","PeriodicalId":50388,"journal":{"name":"IEEE Transactions on Robotics","volume":"41 ","pages":"1755-1772"},"PeriodicalIF":9.4,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143443334","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

Fast Ergodic Search With Kernel Functions 核函数快速遍历搜索

IF 9.4 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2025-02-18 DOI: 10.1109/TRO.2025.3543298

Max Muchen Sun;Ayush Gaggar;Pete Trautman;Todd Murphey

{"title":"Fast Ergodic Search With Kernel Functions","authors":"Max Muchen Sun;Ayush Gaggar;Pete Trautman;Todd Murphey","doi":"10.1109/TRO.2025.3543298","DOIUrl":"10.1109/TRO.2025.3543298","url":null,"abstract":"Ergodic search enables optimal exploration of an information distribution with guaranteed asymptotic coverage of the search space. However, current methods typically have exponential computational complexity and are limited to Euclidean space. We introduce a computationally efficient ergodic search method. Our contributions are two-fold as follows: First, we develop a kernel-based ergodic metric, generalizing it from Euclidean space to Lie groups. We prove this metric is consistent with the exact ergodic metric and ensures linear complexity. Second, we derive an iterative optimal control algorithm for trajectory optimization with the kernel metric. Numerical benchmarks show our method is two orders of magnitude faster than the state-of-the-art method. Finally, we demonstrate the proposed algorithm with a peg-in-hole insertion task. We formulate the problem as a coverage task in the space of SE(3) and use a 30-s-long human demonstration as the prior distribution for ergodic coverage. Ergodicity guarantees the asymptotic solution of the peg-in-hole problem so long as the solution resides within the prior information distribution, which is seen in the 100% success rate.","PeriodicalId":50388,"journal":{"name":"IEEE Transactions on Robotics","volume":"41 ","pages":"1841-1860"},"PeriodicalIF":9.4,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143443310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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

InvSlotGNN: Unsupervised Discovery of Viewpoint Invariant Multiobject Representations and Visual Dynamics 视点不变多目标表示和视觉动力学的无监督发现

IF 9.4 1区计算机科学

IEEE Transactions on Robotics Pub Date : 2025-02-18 DOI: 10.1109/TRO.2025.3543274

Alireza Rezazadeh;Houjian Yu;Karthik Desingh;Changhyun Choi

{"title":"InvSlotGNN: Unsupervised Discovery of Viewpoint Invariant Multiobject Representations and Visual Dynamics","authors":"Alireza Rezazadeh;Houjian Yu;Karthik Desingh;Changhyun Choi","doi":"10.1109/TRO.2025.3543274","DOIUrl":"10.1109/TRO.2025.3543274","url":null,"abstract":"Learning multiobject dynamics purely from visual data is challenging due to the need for robust object representations that can be learned through robot interactions. In previous work (Rezazadeh et al., 2023), we introduced two novel architectures: SlotTransport for discovering object-centric representations from singleview RGB images, referred to as slots, and SlotGNN for predicting scene dynamics from singleview RGB images and robot interactions using the discovered slots. This article introduces InvSlotGNN, a novel framework for learning multiview slot discovery and dynamics that are invariant to the camera viewpoint. First, we demonstrate that SlotTransport can be trained on multiview data such that a single model discovers temporally aligned, object-centric representations from a wide range of different camera angles. These slots bind to objects from various viewpoints, even under occlusion or absence. Next, we introduce InvSlotGNN, an extension of SlotGNN, that learns multiobject dynamics invariant to the camera angle and predicts the future state from observations taken by uncalibrated cameras. InvSlotGNN learns a graph representation of the scene using the slots from SlotTransport and performs relational and spatial reasoning to predict the future state of the scene for arbitrary viewpoints, conditioned on robot actions. We demonstrate the effectiveness of SlotTransport in learning multiview object-centric features that accurately encode visual and positional information. Furthermore, we highlight the accuracy of InvSlotGNN in downstream robotic tasks, including long-horizon prediction and multiobject rearrangement. Finally, with minimal real data, our framework robustly predicts slots and their dynamics in real-world multiview scenarios.","PeriodicalId":50388,"journal":{"name":"IEEE Transactions on Robotics","volume":"41 ","pages":"1812-1824"},"PeriodicalIF":9.4,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143443306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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