检索结果-内蒙古大学图书馆

Mixed Motivation Driven Social Multi-Agent Reinforcement Learning for Autonomous Driving

IEEE/CAA Journal of Automatica Sinica 2025年第6期12卷 1272-1282页

作者： Long Chen Peng Deng Lingxi Li Xuemin Hu State Key Laboratory of Multimodal Artificial Intelligence Systems and the State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing WAYTOUS Inc. Beijing Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China School of Computer Science and Information Engineering Hubei University Wuhan China Purdue School of Engineering and Technology Indiana University-Purdue University Indianapolis Indianapolis IN USA School of Artificial Intelligence Hubei University Wuhan Key Laboratory of Intelligent Sensing System and Security (Hubei University) Ministry of Education Wuhan China

Despite great achievement has been made in autonomous driving technologies, autonomous vehicles (AVs) still exhibit limitations in intelligence and lack social coordination, which is primarily attributed to their reliance on single-agent technologies, neglecting inter-AV interactions. Current research on multi-agent autonomous driving (MAAD) predominantly focuses on either distributed individual learning or centralized cooperative learning, ignoring the mixed-motive nature of MAAD systems, where each agent is not only self-interested in reaching its own destination but also needs to coordinate with other traffic participants to enhance efficiency and safety. Inspired by the mixed motivation of human driving behavior and their learning process, we propose a novel mixed motivation driven social multi-agent reinforcement learning method for autonomous driving. In our method, a multi-agent reinforcement learning (MARL) algorithm, called Social Learning Policy Optimization (SoLPO), which takes advantage of both the individual and social learning paradigms, is proposed to empower agents to rapidly acquire self-interested policies and effectively learn socially coordinated behavior. Based on the proposed SoLPO, we further develop a mixed-motive MARL method for autonomous driving combined with a social reward integration module that can model the mixed-motive nature of MAAD systems by integrating individual and neighbor rewards into a social learning objective for improved learning speed and effectiveness. Experiments conducted on the MetaDrive simulator show that our proposed method outperforms existing state-of-the-art MARL approaches in metrics including the success rate, safety, and efficiency. More-over, the AVs trained by our method form coordinated social norms and exhibit human-like driving behavior, demonstrating a high degree of social coordination.

关键词： Measurement Reinforcement learning Safety Driver behavior Autonomous vehicles Optimization

来源：评论

学校读者我要写书评

暂无评论

Zero-shot learning based on semantic embedding for ship detection 3

Zero-shot learning based on semantic embedding for ship dete...

引用

3rd International Conference on Unmanned systems, ICUS 2020

作者： Zhang, Zihan Zhoa, Jiajia Liang, Xinkai Northwestern Polytechnical University School of Electronics and Information Shaanxi Xi'an China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Bejing China

ISBN: (纸本)9781728180250

Zero-shot detection (ZSD) is a hot topic, which can detect unseen object without training on it. This new approach rises several challenges, e.g., the imbalance between positive and negative data, ambiguity between background and unseen classes, and how to align visual feature and semantic concept. In this paper, we apply an end-to-end zero-shot network to fulfil ZSD, where polarity loss is utilized to train detection model. polarity loss puts more importance on difficult data to reduce class imbalance and can maximize the difference between positive and negative predictions. Then, we use a semantic embedding method that use word vectors in both classification and regression subnets to better align visual features and semantic features. Finally, we use MS-COCO dataset as seen classes to train detection model, then we transfer the model for our own to detect warship object. Our model performs good on unseen classes and test accuracy of using polarity loss is apparently higher than that of using focal loss. © 2020 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

MPC-based intelligent car for tobacco warehouse inspection

MPC-based intelligent car for tobacco warehouse inspection

引用

第40届中国控制会议

作者： Chao Ji Tian-Tian Luan Zhao-Jun Tang Ming-Xiao Sun Da-Xiu Cao School of Automation Harbin University of Science and Technology Heilongjiang Provincial Key Laboratory of Complex Intelligent System and Integration Harbin University of Science and Technology Key Laboratory of Advanced Manufacturing and Intelligent Technology Ministry of Education Harbin University of Science and Technology

In order to complete the inspection of tobacco storage warehouses economically and accurately, This article proposes a method of using a smart car to monitor temperature and humidity for 24 hours. The car with STM32 microcontroller as the main control chip, equipped with linear CCD sensor, ultrasonic obstacle avoidance module, as well as multiple detection sensors,UWB system, Wi Fi module, which can track and avoid obstacles automatically based on MPC, detect important parameter values in the tobacco storage warehouse for 24 hours and transmit date to the PC. It also has the function of real-time alarm and positioning using TDOA technology. After testing in a simulated environment, the car has been proven to accurately and reliably complete the detection of important parameters that affect tobacco mildew. Compared with traditional detection methods, this method is effective in tracing, comprehensive, easy to use and cost-effective. It can also be applied to other monitoring scenarios and has a wide range of application prospects.

关键词： MPC STM32 microcomputer Tobacco leaf mold detection Industrial intelligence

来源：评论

学校读者我要写书评

暂无评论

Phase Unwrapping Based on CFAR Detection for Multi-baseline InISAR

Phase Unwrapping Based on CFAR Detection for Multi-baseline ...

引用

IEEE International Conference on Radar

作者： Meng Ma Guangzhou Qu Shuaishuai Liu Yanjiao Yang Hucheng Pei Qingxi Chi Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China Beijing Electro-Mechanical Engineering Institute Beijing China

ISBN: (纸本)9781665468893

A phase unwrapping method based on constant false alarm rate (CF AR) detection is proposed for multi-baseline interferometric inverse synthetic aperture radar (InISAR). Aiming at the problem of ambiguity number estimation error under the condition of phase noise, Chinese remainder theorem (CRT) and cluster analysis are utilized to acquire the probability distribution of phase noise. By introducing CFAR detection, the novel method reduced the error probability of ambiguity number estimation. Through simulation, it is verified that the novel method can effectively suppress phase noise and obtain accurate phase unwrapping results.

关键词： Phase noise Phase measurement Radar measurements Radar Radar scattering Radar imaging Cathode ray tubes

来源：评论

学校读者我要写书评

暂无评论

Fast Vision Decoder: A Robust Automatic Target Recognition Model for Sar Images

SSRN

引用

SSRN 2022年

作者： Ayodeji, Abiodun Wang, Wenhai Su, Jianzhong Yuan, Jianquan Liu, Xinggao State Key Laboratory of Industrial Control Technology Control Department Zhejiang University Hangzhou310027 China Tianjin Jinhang Technical Physics Institute Tianjin300192 China Science and Technology on Complex System Control and Intelligent Agent Cooperative Laboratory Beijing100074 China

The synthetic aperture radar (SAR) is the recent all-weather technology used to monitor areas with low to moderate penetration. However, the scarcity of SAR imagery, and the high-level noise in the images makes it difficult for real-time image interpretation. This work presents a novel fast vision decoder (FViD), a target recognition model with a frozen backbone and stack dilated autoencoder. The autoencoder architecture is introduced to learn the compressed latent representation. Moreover, a robust backbone selection method is introduced to select a task-specific optimal backbone. The proposed FViD is extensively evaluated using the Chinese TerraSAR-X ship images, and the US MSTAR datasets. Evaluation results show that the proposed method has significant improvement over the conventional models. The speed and accuracy of the proposed FViD are further compared with five state of the art models previously used for SAR target recognition tasks, and the comparison result shows that the FViD performs better. Moreover, an ablation study is performed to provide insights into the contribution of FViD architecture. The results of the ablation study as well as the performance improvement of FViD are discussed in this paper. © 2022, The Authors. All rights reserved.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Rapid and Accurate Regional Star-Map Simulated Method

Rapid and Accurate Regional Star-Map Simulated Method

引用

Computer, Control and Robotics (ICCCR), International Conference on

作者： Jian Han Jiahui Tong Cheng Tang Beijing Electro-Mechanical Engineering Institute Beijing China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

The following topics are dealt with: mobile robots; feature extraction; learning (artificial intelligence); motion control; neural nets; path planning; optimisation; object detection; fault diagnosis; design engineering.

ISBN: (数字)9781728190358

ISBN: (纸本)9781728190365

关键词： Strips Gray-scale Reconstruction algorithms Position measurement Image reconstruction Robots Next generation networking

来源：评论

学校读者我要写书评

暂无评论

A Novel Agricultural Data Sharing Mode Based on Rice Disease Identification

引用

Plant Diseases and Pests 2024年第2期15卷 9-16页

作者： Mengmeng ZHANG Xiujuan WANG Mengzhen KANG Jing HUA Haoyu WANG Feiyue WANG State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of AutomationChinese Academy of SciencesBeijing 100190China Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China State Key Laboratory for Management and Control of Complex System Institute of AutomationChinese Academy of SciencesBeijing 100190China

In this paper,a variety of classical convolutional neural networks are trained on two different datasets using transfer learning *** demonstrated that the training dataset has a significant impact on the training results,in addition to the optimization achieved through the model ***,the lack of open-source agricultural data,combined with the absence of a comprehensive open-source data sharing platform,remains a substantial *** issue is closely related to the difficulty and high cost of obtaining high-quality agricultural data,the low level of education of most employees,underdeveloped distributed training systems and unsecured data *** address these challenges,this paper proposes a novel idea of constructing an agricultural data sharing platform based on a federated learning(FL)framework,aiming to overcome the deficiency of high-quality data in agricultural field training.

关键词： Rice disease and pest identification Convolutional neural networks Distributed training Federated learning(FL) Open-source data sharing platform

来源：评论

学校读者我要写书评

暂无评论

Motion-Guided Spatial Perception for Enhanced Multi-Object Tracking: A Hierarchical Framework

SSRN

引用

SSRN 2023年

作者： Zheng, Yujin Qi, Hang Li, Lei Li, Shan Huang, Yan He, Chu Wang, Dingwen School of Computer Science Wuhan University Hubei Wuhan430000 China The Beijing Electro-Mechanical Engineering Institute Beijing100074 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China Zmvision Technology Hubei Wuhan430000 China School of Electronic Information Wuhan University Hubei Wuhan430000 China

Multi-object tracking (MOT) aims to associate objects of interest across sequences, which has rapidly progressed with the development of object detection and optimal matching techniques. However, spatio-temporal modeling complex variations, such as camera motion and occlusion in crowded scenes, have been relatively underexplored in recent years. In this work, a temporal concern through motion-guided feature aggregation module is proposed to capture multi-frame variations for instances. Additionally,an occlusion-aware head and hierarchical spatial association are proposed to handle the challenges of occlusion through spatial perception. The above approach, namely MSPNet addresses the challenges posed by occlusion effectively, resulting in improved tracking performance. Evaluation on benchmark datasets shows that MSPNet achieves the state-of-the-art performance. Specifically, MSPNet achieves 75.4% MOTA, and 72.4% IDF1 on the test set of MOT16, 74.6% MOTA, and 71.9% IDF1 on MOT17, 75.9% MOTA, and 74.4% IDF1 on MOT20, respectively. © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Hexapod robot motion planning investigation under the influence of multi-dimensional terrain features

引用

Frontiers in neurorobotics 2025年 19卷 1605938页

作者： Chen Chen Junbo Lin Bo You Jiayu Li Biao Gao The Key Laboratory of Intelligent Technology for Cutting and Manufacturing Ministry of Education Harbin University of Science and Technology Harbin China. The Heilongjiang Provincial Key Laboratory of Complex Intelligent System and Integration Harbin University of Science and Technology Harbin China.

To address the challenges arising from the coupled interactions between multi-dimensional terrain features-encompassing both geometric and physical properties of complex field environments-and the locomotion stability of hexapod robots, this paper presents a comprehensive motion planning framework incorporating multi-dimensional terrain information. The proposed methodology systematically extracts multi-dimensional geometric and physical terrain features from a multi-layered environmental map. Based on these features, a traversal cost map is synthesized, and an enhanced A* algorithm is developed that incorporates terrain traversal metrics to optimize path planning safety across complex field environments. Furthermore, the framework introduces a foothold cost map derived from multi-dimensional terrain data, coupled with a fault-tolerant free gait planning algorithm based on foothold cost evaluation. This approach enables dynamic gait modulation to enhance overall locomotion stability while maintaining safe trajectory planning. The efficacy of the proposed framework is validated through both simulation studies and physical experiments on a hexapod robotic platform. Experimental results demonstrate that, compared to conventional hexapod motion planning approaches, the proposed multi-dimensional terrain-aware planning framework significantly enhances both locomotion safety and stability across complex field environments.

关键词： free gait planning hexapod robot locomotion stability multi-dimensional terrain features path planning

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition Empowered Human-Computer Interaction with Domain Adaptation Network

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Xu, Xu Fu, Chong Chen, Junxin Northeastern University School of Computer Science and Engineering Shenyang110004 China Dalian University of Technology China The School of Software Dalian116621 China Northeastern University School of Computer Science and Engineering Shenyang110004 China Northeastern University Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Shenyang110819 China Ministry of Education Engineering Research Center of Security Technology of Complex Network System Shenyang110004 China Dalian University of Technology School of Software Dalian116621 China

Multi-modal emotion recognition plays a vital role in the human-computer interaction (HCI) for consumer electronics. Nowadays, many studies have developed multi-modal fusion algorithms for this ***, two challenging issues remain unsolved, i.e., inefficient multi-modal feature fusion and unclear distance in feature *** this end, we develop a novel framework, namely LAFDA-Net, for cross-subject emotion recognition using EEG and eye movement *** is based on low-rank fusion and domain adaptation *** specifically, the multi-modal signals are input into the feature extraction branch in parallel to generate ***, these features are fused by the low-rank fusion branch, reducing complexity and avoiding ***, the fused features are flattened and sent to the classification branch to determine the emotion *** training, these features are input into the domain adaptive branch to bridge the gap between the source domain and target *** benchmark datasets, i.e., SEED, SEED-IV, and SEED-V, are employed for performance *** results demonstrate that the proposed LAFDA-Net is robust, effective, and has advantages over peer methods. © 1975-2011 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：