检索结果-内蒙古大学图书馆

Pedestrians and Robots: A Novel Dataset for Learning Distinct Social Navigation Forces

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Agrawal, Subham Ostermann-Myrau, Nico Dengler, Nils Bennewitz, Maren Humanoid Robots Lab University of Bonn Germany Lamarr Institute for Machine Learning and Artificial Intelligence The Center for Robotics Bonn Germany

The increasing use of robots in human-centric public spaces such as shopping malls, sidewalks, and hospitals, requires understanding of how pedestrians respond to their presence. However, existing research lacks comprehensive datasets that capture the full range of pedestrian behaviors, e.g., including avoidance, neutrality, and attraction in the presence of robots. Such datasets can be used to effectively learn models capable of accurately predicting diverse responses of pedestrians to robot presence, which are crucial for advancing robot navigation strategies and optimizing pedestrian-aware motion planning. In this paper, we address these challenges by collecting a novel dataset of pedestrian motion in two outdoor locations under three distinct conditions, i.e., no robot presence, a stationary robot, and a moving robot. Thus, unlike existing datasets, ours explicitly encapsulates variations in pedestrian behavior across the different robot conditions. Using our dataset, we propose a novel Neural Social Robot Force Model (NSRFM), an extension of the traditional Social Force Model that integrates neural networks and robot-induced forces to better predict pedestrian behavior in the presence of robots. We validate the NSRFM by comparing its generated trajectories on different real-world datasets. Furthermore, we implemented it in simulation to enable the learning and benchmarking of robot navigation strategies based on their impact on pedestrian movement. Our results demonstrate the model’s effectiveness in replicating real-world pedestrian reactions and its its utility in developing, evaluating, and benchmarking social robot navigation algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Social robots

SharedAssembly: A Data Collection Approach via Shared Tele-Assembly

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wu, Yansong Chen, Xiao Chen, Yu Sadeghian, Hamid Wu, Fan Bing, Zhenshan Haddadin, Sami König, Alexander Knoll, Alois CMIRMI - Munich Institute of Robotics and Machine Intelligence Technical University of Munich Germany Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates

Assembly is a fundamental skill for robots in both modern manufacturing and service robotics. Existing datasets aim to address the data bottleneck in training general-purpose robot models, falling short of capturing contact-rich assembly tasks. To bridge this gap, we introduce SharedAssembly, a novel bilateral teleoperation approach with shared autonomy for scalable assembly execution and data collection. User studies demonstrate that the proposed approach enhances both success rates and efficiency, achieving a 97.0% success rate across various sub-millimeter-level assembly tasks. Notably, novice and intermediate users achieve performance comparable to experts using baseline teleoperation methods, significantly enhancing large-scale data *** Codes 68T40 © 2025, CC BY-NC-ND.

关键词： Robotic assembly

Exploring inter- and intra-modal relations in compositional zero-shot learning

学校读者我要写书评

暂无评论

Neurocomputing 2025年 639卷

作者： Zhang, Xiao Chen, Hui Jing, Haodong Ma, Yongqiang Zheng, Nanning National Key Laboratory of Human–Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Shaanxi Xi'an710049 China

Compositional Zero-Shot Learning (CZSL) aims to recognize unknown compositions by leveraging learned concepts of states and objects. Prior methods have typically emphasized either inter-modal relation for multi-modal fusion, ignoring the entanglement within state–object pairs, or solely intra-modal relation for enhancing representations, neglecting the association between vision and language domains. To tackle these limitations, we propose a CZSL framework that simultaneously learns inter- and intra-modal relations to improve image-label alignment. Firstly, we explore inter-modal relation to enable image features to grasp the cross-modal information from states and objects. The image–text fusion method facilitates the modeling of text-aware image features and image-aware text features, improving the model's compositional recognition capability. Secondly, due to the contextuality within state–object pairs, we further explore intra-modal relation to exploit semantic information from various representation subspaces, facilitating the comprehensive semantic expression of text features. Moreover, we propose a composition fusion module to establish semantic entanglement within state–object compositions. Extensive experiments demonstrate that our method significantly surpasses the state-of-the-art methods in both closed-world and open-world settings. © 2025 Elsevier B.V.

关键词： Zero-shot learning

D2S: Towards Efficient Sparse 3D Object Detection via Dense to Sparse Knowledge Distillation

学校读者我要写书评

暂无评论

D2S: Towards Efficient Sparse 3D Object Detection via Dense ...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yuqi Huang Longjun Liu Yingke Gao Haonan Zhang Haoteng Li Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China Beijing Institute of Control Engineering China Academy of Space Technology Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

LiDAR-based 3D object detection is widely used in high-level autonomous driving schemes. However, the cumbersome modules in most 3D detectors lead to substantial computational overhead. Despite knowledge distillation (KD) is an effective approach for compressing models, previous methods cannot be extended to the dense-to-sparse paradigm. To this end, we propose a simple yet effective Dense to Sparse Knowledge Distillation (D2S) framework for accelerating 3D detectors. Firstly, to compensate for the difference in predicted location between dense and sparse detectors, we introduce a lightweight feature diffusion (FeaD) module for spreading important features. Secondly, to achieve high performance, we propose a dual-stream distillation scheme to transfer knowledge. In this scheme, we align both of the feature and category prediction between distillation pairs at important positions. Extensive experiments on KITTI and Waymo Open Dataset demonstrate the effectiveness of our method. For example, on KITTI dataset, the sparse detector we obtained surpasses VoxelNeXt with around 2.0× fewer parameters and 1.6× fewer FLOPs.

关键词： Three-dimensional displays Computational modeling Detectors Object detection Signal processing Feature extraction Acoustics Speech processing Autonomous vehicles

Optimization-free Smooth Control Barrier Function for Polygonal Collision Avoidance

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wu, Shizhen Fang, Yongchun Sun, Ning Lu, Biao Liang, Xiao Zhao, Yiming Institute of Robotics and Automatic Information System College of Artificial Intelligence Nankai University Tianjin300353 China Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University Shenzhen518083 China

Polygonal collision avoidance (PCA) is short for the problem of collision avoidance between two polygons (i.e., polytopes in planar) that own their dynamic equations. This problem suffers the inherent difficulty in dealing with non-smooth boundaries and recently optimization-defined metrics, such as signed distance field (SDF) and its variants, have been proposed as control barrier functions (CBFs) to tackle PCA problems. In contrast, we propose an optimization-free smooth CBF method in this paper, which is computationally efficient and proved to be nonconservative. It is achieved by three main steps: a lower bound of SDF is expressed as a nested Boolean logic composition first, then its smooth approximation is established by applying the latest log-sum-exp method, after which a specified CBF-based safety filter is proposed to address this class of problems. To illustrate its wide applications, the optimization-free smooth CBF method is extended to solve distributed collision avoidance of two underactuated nonholonomic vehicles and drive an underactuated container crane to avoid a moving obstacle respectively, for which numerical simulations are also performed. © 2025, CC BY.

关键词： Magnetic levitation vehicles

Visual-Linguistic Feature Alignment with Semantic and Kinematic Guidance for Referring Multi-Object Tracking

学校读者我要写书评

暂无评论

IEEE Transactions on Multimedia 2025年 27卷 3034-3044页

作者： Li, Yizhe Zhou, Sanping Qin, Zheng Wang, Le National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Shaanxi Xi'an710049 China

Referring Multi-Object Tracking (RMOT) aims to dynamically track an arbitrary number of referred targets in a video sequence according to the language expression. Previous methods mainly focus on cross-modal fusion at the feature level with designed structures. However, the insufficient visual-linguistic alignment is prone to causing visual-linguistic mismatches, leading to some targets being tracked but not correctly referred especially when facing the language expression with complex semantics or motion descriptions. To this end, we propose to conduct visual-linguistic alignment with semantic and kinematic guidance to effectively align the visual features with more diverse language expressions. In this paper, we put forward a novel end-to-end RMOT framework SKTrack, which follows the transformer-based architecture with a Language-Guided Decoder (LGD) and a Motion-Aware Aggregator (MAA). In particular, the LGD performs deep semantic interaction layer-by-layer in a single frame to enhance the alignment ability of the model, while the MAA conducts temporal feature fusion and alignment across multiple frames to enable the alignment between visual targets and language expression with motion descriptions. Extensive experiments on the Refer-KITTI and Refer-KITTI-v2 demonstrate that SKTrack achieves state-of-the-art performance and verify the effectiveness of our framework and its components. © 1999-2012 IEEE.

关键词： Semantics

STVO: Spatial-Temporal Constrained Velocity Obstacle for Safe Navigation among Pedestrians

学校读者我要写书评

暂无评论

IEEE Transactions on Vehicular Technology 2025年

作者： Song, Yichen Wang, Runhua Bi, Qingchen Pan, Zhangchao Gao, Haiming Zhang, Xuebo Nankai University College of Artificial Intelligence Institute of Robotics and Automatic Information System The Tianjin Key Laboratory of Intelligent Robotics Tianjin300350 China

This paper presents a novel motion planning method that safely navigates the unmanned ground vehicle (UGV) among pedestrian-rich environments by constructing the spatial-temporal constrained velocity obstacle (STVO) region. Compared with existing velocity obstacle (VO) type-based methods, the novelty of this work is twofold: 1) An innovative temporal constraint is introduced into the velocity space, also playing the role as an adaptive collision time constraint to dynamically adjust the velocity obstacle region according to real-time perceived pedestrian density;2) The spatial constraint is proposed to foresee and evade potential entrapments for the UGV, by carefully considering the position relationship between the UGV and the VO region. Additionally, a velocity resampling mechanism is further designed to prevent the UGV from being trapped. Above techniques augments the navigation flexibility and safety of the UGV, thereby significantly improves the success rate of practical navigation in dynamic and challenging pedestrian environments. Extensive simulations and real-world experiments have been conducted, especially the experiment in pedestrian-rich school cafeteria demonstrating satisfactory practicality of our approach. (Supplementary video link: https://***/xt4KosuPMYs). © 1967-2012 IEEE.

关键词： Pedestrian safety

Global Convergence of Continual Learning on Non-IID Data

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhu, Fei Liu, Yujing Liu, Wenzhuo Zhang, Zhaoxiang Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation CAS Hong Kong Key Laboratory of Systems and Control Academy of Mathematics and Systems Science CAS China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation CAS China School of Artificial Intelligence University of Chinese Academy of Sciences China

Continual learning, which aims to learn multiple tasks sequentially, has gained extensive attention. However, most existing work focuses on empirical studies, and the theoretical aspect remains under-explored. Recently, a few investigations have considered the theory of continual learning only for linear regressions, establishes the results based on the strict independent and identically distributed (i.i.d.) assumption and the persistent excitation on the feature data that may be difficult to verify or guarantee in practice. To overcome this fundamental limitation, in this paper, we provide a general and comprehensive theoretical analysis for continual learning of regression models. By utilizing the stochastic Lyapunov function and martingale estimation techniques, we establish the almost sure convergence results of continual learning under a general data condition for the first time. Additionally, without any excitation condition imposed on the data, the convergence rates for the forgetting and regret metrics are provided. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

Modeling of AUV Dynamics with Limited Resources: Efficient Online Learning Using Uncertainty

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Tešnar, Michal Wehbe, Bilal Valdenegro-Toro, Matias Department of AI Bernoulli Institute University of Groningen Netherlands Robotics Innovation Center German Research Center for Artificial Intelligence Bremen Germany

Machine learning proves effective in constructing dynamics models from data, especially for underwater vehicles. Continuous refinement of these models using incoming data streams, however, often requires storage of an overwhelming amount of redundant data. This work investigates the use of uncertainty in the selection of data points to rehearse in online learning when storage capacity is constrained. The models are learned using an ensemble of multilayer perceptrons as they perform well at predicting epistemic uncertainty. We present three novel approaches: the Threshold method, which excludes samples with uncertainty below a specified threshold, the Greedy method, designed to maximize uncertainty among the stored points, and Threshold-Greedy, which combines the previous two approaches. The methods are assessed on data collected by an underwater vehicle Dagon. Comparison with baselines reveals that the Threshold exhibits enhanced stability throughout the learning process and also yields a model with the least cumulative testing loss. We also conducted detailed analyses on the impact of model parameters and storage size on the performance of the models, as well as a comparison of three different uncertainty estimation methods. © 2025, CC0.

关键词：