检索结果-内蒙古大学图书馆

EMPIRICAL STUDIES ON THE PROPERTIES OF LINEAR REGIONS IN DEEP NEURAL NETWORKS 8

学校读者我要写书评

暂无评论

EMPIRICAL STUDIES ON THE PROPERTIES OF LINEAR REGIONS IN DEE...

8th International Conference on Learning Representations, ICLR 2020

作者： Zhang, Xiao Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

A deep neural network (DNN) with piecewise linear activations can partition the input space into numerous small linear regions, where different linear functions are fitted. It is believed that the number of these regions represents the expressivity of the DNN. This paper provides a novel and meticulous perspective to look into DNNs: Instead of just counting the number of the linear regions, we study their local properties, such as the inspheres, the directions of the corresponding hyperplanes, the decision boundaries, and the relevance of the surrounding regions. We empirically observed that different optimization techniques lead to completely different linear regions, even though they result in similar classification accuracies. We hope our study can inspire the design of novel optimization techniques, and help discover and analyze the behaviors of DNNs. © 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved.

关键词： Deep neural networks

Recognizing Human-object Interactions for a Home Assistive Robot

学校读者我要写书评

暂无评论

Recognizing Human-object Interactions for a Home Assistive R...

Automation, control and Robotics Engineering (CACRE), International Conference on

作者： Liangliang Wang Guanglei Huo Xinwei Chen Chengxi Huang School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China Fujian(Quanzhou)-HIT Research Institute of Engineering and Technology Quanzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China

To enable robots to understand a specific assistive task during human-robot interactions under complex home scenes, at the center is the problem of human-object interaction (HOI) recognition. In particular, aiming at identifying efficiently, this paper proposes a graph convolutional network (GCN) by considering the similarity and proximity of human and object nodes, based on which the geometric positions and morphological relationships are explored. Also, a supplementary convolutional neural network (CNN) is fused to GCN to extract the global semantic features, which also ensures the recognition applicability for the cases where detectors fall into failure. Experiments on V-COCO demonstrate our approach, and results in real-world scenes on our assistive robot – Xiaozhi II verify its robustness.

关键词：

A localizability estimation method for mobile robots based on 3D point cloud feature

学校读者我要写书评

暂无评论

A localizability estimation method for mobile robots based o...

2021 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2021

作者： Liu, Ying Wang, Jingchuan Huang, Yi Institute of Medical Robotics Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Department of Automation Shanghai200240 China Nanjing Kingyoung Intelligent Technology CO. LTD.

ISBN: (纸本)9781665436786

This paper introduces the theoretical analysis and derivation of localizability estimation for mobile robots based on point cloud observation. Combined with the observation model, the pre-established point cloud map is firstly clustered and segmented with a newly proposed method considering multiple constraints on depth map. Then localizability is set to be equal to the strength of the constraints associated with 3D point cloud features. In addition, based on the method of using information matrix theory, this paper integrates the Fisher's information matrix and point cloud features to estimate localizability. © 2021 IEEE.

关键词： Mobile robots

A Game Theory-Reinforcement Learning Approach to Cooperation for UAVs

学校读者我要写书评

暂无评论

IEEE Transactions on Vehicular Technology 2025年

作者： Tang, Changbing Pan, Linchao Chen, Jie Liu, Yang Lai, Jingang The College of Physics and Electronic Information Engineering Zhejiang Normal University Jinhua321004 China The School of Mathematical Sciences Zhejiang Normal University Jinhua321004 China The Hangzhou School of Automation Zhejiang Normal University Hangzhou311231 China The College of Electronic Engineering National University of Defense Technology Hefei230037 China The School of Artificial Intelligence and Automation the Key Laboratory of Image Processing and Intelligent Control Education Ministry of China China Huazhong University of Science and Technology Wuhan430074 China

To execute a variety of collaborative tasks, the cooperation for unmanned aerial vehicles (UAVs) with complicated interactions under dynamic environments is a challenging and critical issue. This paper studies the cooperation issue for UAVs under dynamic environments through an approach of game theory-reinforcement learning (GT-RL) approach, which combines the advantages of both game theory and reinforcement learning. First, to cope with the complicated interactions of UAVs, the cluster of UAVs is modeled as a public goods game with asymmetrical environmental feedback. Then, reinforcement learning is adopted to optimize decision-making of UAVs under unknown and dynamic environments through comparing the dynamic behaviors of UAVs, where a novel dynamics system offers a more comprehensive understanding on cooperative behavior among UAVs. Finally, the simulation results show that the GT-RL approach can effectively promote cooperation among UAVs in completing the collaborative tasks. © 1967-2012 IEEE.

关键词： Adversarial machine learning

3D Gaussian Splatting in Robotics: A Survey

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhu, Siting Wang, Guangming Kong, Xin Kong, Dezhi Wang, Hesheng Department of Automation Shanghai Jiao Tong University Shanghai China University of Cambridge United Kingdom Imperial College London United Kingdom Shanghai Jiao Tong University Shanghai China Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University China

Dense 3D representations of the environment have been a long-term goal in the robotics field. While previous Neural Radiance Fields (NeRF) representation have been prevalent for its implicit, coordinate-based model, the recent emergence of 3D Gaussian Splatting (3DGS) has demonstrated remarkable potential in its explicit radiance field representation. By leveraging 3D Gaussian primitives for explicit scene representation and enabling differentiable rendering, 3DGS has shown significant advantages over other radiance fields in real-time rendering and photo-realistic performance, which is beneficial for robotic applications. In this survey, we provide a comprehensive understanding of 3DGS in the field of robotics. We divide our discussion of the related works into two main categories: the application of 3DGS and the advancements in 3DGS techniques. In the application section, we explore how 3DGS has been utilized in various robotics tasks from scene understanding and interaction perspectives. The advance of 3DGS section focuses on the improvements of 3DGS own properties in its adaptability and efficiency, aiming to enhance its performance in robotics. We then summarize the most commonly used datasets and evaluation metrics in robotics. Finally, we identify the challenges and limitations of current 3DGS methods and discuss the future development of 3DGS in robotics. The paper lists of our survey are available at 3D Gaussian Splatting in Robotics. Copyright © 2024, The Authors. All rights reserved.

关键词： Rendering (computer graphics)

Heterogeneous Graph Convolutional Network for Visual Reinforcement Learning of Action Detection

学校读者我要写书评

暂无评论

Heterogeneous Graph Convolutional Network for Visual Reinfor...

Automation, control and Robotics Engineering (CACRE), International Conference on

作者： Liangliang Wang Chengxi Huang Xinwei Chen School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China Fujian(Quanzhou)-HIT Research Institute of Engineering and Technology Quanzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China

Existing action detection approaches do not take spatio-temporal structural relationships of action clips into account, which leads to a low applicability in real-world scenarios and can benefit detecting if exploited. To this end, this paper proposes to formulate the action detection problem as a reinforcement learning process which is rewarded by observing both the clip sampling and classification results via adjusting the detection schemes. In particular, our framework consists of a heterogeneous graph convolutional network to represent the spatio-temporal features capturing the inherent relation, a policy network which determines the probabilities of a predefined action sampling spaces, and a classification network for action clip recognition. We accomplish the network joint learning by considering the temporal intersection over union and Euclidean distance between detected clips and ground-truth. Experiments on ActivityNet v1.3 and THUMOS14 demonstrate our method.

关键词：

Unsupervised Difference Learning for Noisy Rigid image Alignment

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Yu-Xuan Feng, Dagan Shen, Hong-Bin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China School of Computer Science University of Sydney Sydney2006 Australia

Rigid image alignment is a fundamental task in computer vision, while the traditional algorithms are either too sensitive to noise or time-consuming. Recent unsupervised image alignment methods developed based on spatial transformer networks show an improved performance on clean images but will not achieve satisfactory performance on noisy images due to its heavy reliance on pixel value comparations. To handle such challenging applications, we report a new unsupervised difference learning (UDL) strategy and apply it to rigid image alignment. UDL exploits the quantitative properties of regression tasks and converts the original unsupervised problem to pseudo supervised problem. Under the new UDL-based image alignment pipeline, rotation can be accurately estimated on both clean and noisy images and translations can then be easily solved. Experimental results on both nature and cryo-EM images demonstrate the efficacy of our UDL-based unsupervised rigid image alignment method. Copyright © 2022, The Authors. All rights reserved.

关键词： image enhancement

Large, Complex, and Realistic Safety Clothing and Helmet Detection: Dataset and Method

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yu, Fusheng Li, Jiang Wang, Xiaoping Wu, Shaojin Zhang, Junjie Zeng, Zhigang The School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China The Institute of Artificial Intelligence Huazhong University of Science and Technology Wuhan430074 China The Hubei Key Laboratory of Brain-Inspired Intelligent Systems Huazhong University of Science and Technology Wuhan430074 China The Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Ministry of Education Wuhan430074 China

Detecting safety clothing and helmets is paramount for ensuring the safety of construction workers. However, the development of deep learning models in this domain has been impeded by the scarcity of high-quality datasets. In this study, we construct a large, complex, and realistic safety clothing and helmet detection (SFCHD) dataset. SFCHD is derived from two authentic chemical plants, comprising 12,373 images, 7 categories, and 50,552 annotations. We partition the SFCHD dataset into training and testing sets with a ratio of 4:1 and validate its utility by applying several classic object detection algorithms. Furthermore, drawing inspiration from spatial and channel attention mechanisms, we design a spatial and channel attention-based low-light enhancement (SCALE) module. SCALE is a plug-and-play component with a high degree of flexibility. Extensive evaluations of the SCALE module on both the ExDark and SFCHD datasets have empirically demonstrated its efficacy in enhancing the performance of detectors under low-light conditions. The dataset and code are publicly available at https://***/lijfrankopen/SFCHD-SCALE. Copyright © 2023, The Authors. All rights reserved.

关键词： Chemical plants

AnyBipe: An End-to-End Framework for Training and Deploying Bipedal Robots Guided by Large Language Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yao, Yifei He, Wentao Gu, Chenyu Du, Jiaheng Tan, Fuwei Zhu, Zhen Lu, Junguo All authors are with Machine Vision and Autonomous System Laboratory Department of Automation School of Electrical Information and Electronic Engineering Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China University of Michigan Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong University Shanghai China

Training and deploying reinforcement learning (RL) policies for robots, especially in accomplishing specific tasks, presents substantial challenges. Recent advancements have explored diverse reward function designs, training techniques, simulation-to-reality (sim-to-real) transfers, and performance analysis methodologies, yet these still require significant human intervention. This paper introduces an end-to-end framework for training and deploying RL policies, guided by Large Language Models (LLMs), and evaluates its effectiveness on bipedal robots. The framework consists of three interconnected modules: an LLM-guided reward function design module, an RL training module leveraging prior work, and a sim-to-real homomorphic evaluation module. This design significantly reduces the need for human input by utilizing only essential simulation and deployment platforms, with the option to incorporate human-engineered strategies and historical data. We detail the construction of these modules, their advantages over traditional approaches, and demonstrate the framework’s capability to autonomously develop and refine controlling strategies for bipedal robot locomotion, showcasing its potential to operate independently of human intervention. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning