检索结果-内蒙古大学图书馆

IEEE International Conference on Unmanned systems (ICUS)

作者： Zirui Wu Zhen Li Dong Zhu Qiuhan Liao Weiran Yao School of Astronautics Harbin Institute of Technology Harbin China Beijing Electro-Mechanical Engineering Institute Beijing China Chengdu CHG Robots & Intelligent Equipment Institute Co. Ltd Chengdu China National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Beijing China

ISBN: (数字)9798350384185

ISBN: (纸本)9798350384192

The task allocation for multiple robots is a critical component in the coordination of unmanned clusters. The existing heuristic algorithms are hard to achieve satisfactory results in large-scale problems, and reinforcement learning-based methods face challenges in ensuring the rationality of reward design. This paper introduces a model based on multi-head attention and graph neural networks to address the schedule-dependent multi-robot task allocation problem, trained using unsupervised learning techniques. This model can be trained with varying numbers of robots and tasks without necessitating changes to its structure or parameters. In the experiment of this paper, the model is trained under two different conditions, and the performance is evaluated across six different problem scales. Comparing the proposed model against greedy algorithms and genetic algorithms, the results demonstrate that the proposed model has sianiflcant advantages in overall performance.

关键词： Greedy algorithms Robot kinematics Heuristic algorithms Computational modeling Reinforcement learning Graph neural networks Resource management Unsupervised learning Faces Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Cooperative Collision Avoidance Method for Multi-UAV Based on Kalman Filter and Model Predictive control

Cooperative Collision Avoidance Method for Multi-UAV Based o...

引用

International Conference on Unmanned systems and Artificial Intelligence

作者： Hanqiao Huang Huan Zhou Meiyun Zheng Cheng Xu Xiaofeng Zhang Wei Xiong Unmanned System Research Institute Northwest Polytechnical University Xi'an China Aeronautical Engineering College Air Force Engineering University Xi'an China School of Marine Science and Technology Northwest Polytechnical University Xi'an China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China UAV Researc Center Army Aviation Institute Beijing China

ISBN: (数字)9781728158594

ISBN: (纸本)9781728158600

Collision avoidance is the primary problem to be solved in formation flight of multiple Unmanned aerial vehicles(UAVs). Firstly, a cooperative collision avoidance architecture of multiple UAVs is designed according to the requirement of autonomous collision avoidance of single UAV. Then a new cooperative collision avoidance method of multiple UAVs based on Kalman filter and model predictive control(MPC) is proposed. In this method, extended Kalman filter(EKF) is used to estimate the state of obstacles and target points in uncertain environment space, and to predict the trajectory of obstacles and target points. At the same time, relevant performance index functions and constraints are set up. On the basis of sharing environmental information, model predictive control strategy is used to guide and make cooperative collision avoidance decisions for multiple UAVs. The simulation results show that the proposed method is effective in uncertain environment perception and UAV collision avoidance, and the cooperative mechanism has obvious advantages.

关键词： UAV cooperative decision collision avoidance Kalman filter state estimation MPC Collision avoidance Kalman filters Unmanned Aerial Vehicle State estimation Maximum Allowable Concentration drone honey bees environmental perception Formation flight

来源：评论

学校读者我要写书评

暂无评论

Impact Time and Angle control Guidance Based on Cubic Bézier Curves: Theory and Experiment

SSRN

引用

SSRN 2024年

作者： Li, Heng Lv, Xiaokang Yu, Jianglong Zhang, Kun Wang, Yanyan Dong, Xiwang Institute of Artificial Intelligence Beihang University Beijing100191 China School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control Laboratory Beihang University Beijing100191 China Institute of Unmanned System Beihang University Beijing100191 China School of Astronautics Beihang University Beihang University Beijing100191 China National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Beijing100074 China

A trajectory-shaping guidance strategy with constraints on impact time, impact angle, and maximum lateral acceleration is proposed based on a cubic Bézier curve fitting method. Firstly, an optimal guidance model is formulated, in which the Bézier curves are employed to fit the guidance trajectory, ensuring compliance with the required constraints. The manipulation transforms the optimal guidance problem into an optimal Bézier guidance trajectory design problem and a trajectory tracking problem. Then, by parameterizing the Bézier curves and analyzing the trajectory constraints in detail, the optimal Bézier guidance trajectory design is transformed into optimizing the control parameters of the Bézier curves. Moreover, a multi-layer zeroth-order Adam trajectory optimization algorithm based on general and fine tuning is introduced to determine the control parameters without relying on gradient information. Subsequently, a hyperbolic tangent vector field path tracking guidance algorithm is proposed to follow the designed trajectory and fulfill the guidance missions. Finally, numerical simulations and equivalent physical experiments verify the effectiveness of the proposed guidance strategy. © 2024, The Authors. All rights reserved.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

A Hierarchical Graph Search Method for Path Planning of Unmanned Ground Vehicle for Freight Transportation

A Hierarchical Graph Search Method for Path Planning of Unma...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Jianing Hu Zhen Li Sen Guo Weiran Yao School of Astronautics Harbin Institute of Technology Harbin China Beijing Electro-Mechanical Engineering Institute Beijing China CRRC Nanjing Puzhen Co. Ltd Nanjing China National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Beijing China

ISBN: (数字)9798350384185

ISBN: (纸本)9798350384192

For the problem of collision volume change when forklift unmanned vehicles work in complex storage environments, a multi-level graph search path planning method is proposed. The first level is the path planning of the Unmanned Ground Vehicle (UGV) body, which uses the grid map and the A * algorithm to plan the path of the UGV transferring in the scene; the second level is the joint path planning of the UGV and the object being carried, to avoid overcomplicating this issue, the unmanned vehicle will be limited to pushing the cargo only forwards. The third level is the path planning when the unmanned vehicle carries multiple objects, which decomposes the whole scene into multiple sub-scenes, plans the paths of the unmanned vehicle in the sub-scenes separately, and searches for the optimal combination of sub-scenes. Higher level searches will invoke lower level algorithms and provide a virtual scene and target as input. The experimental results show that this multilevel path planning method is optimal and complete in solving the forklift unmanned vehicle for handling a single object, and can give a feasible solution for handling multiple objects.

关键词： Costs Transportation Search problems Path planning Land vehicles complexity theory Autonomous vehicles

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

Event-triggered Consensus control of Heterogeneous Multi-agent systems: Model- and Data-based Analysis

arXiv

引用

arXiv 2022年

作者： Wang, Xin Sun, Jian Wang, Gang Chen, Jie The School of Automation The Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology Beijing10081 China The Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China The Department of Control Science and Engineering Tongji University Shanghai201804 China The State Key Lab of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China

This article deals with model- and data-based consensus control of heterogenous leader-following multi-agent systems (MASs) under an event-triggering transmission scheme. A dynamic periodic transmission protocol is developed to significantly alleviate the transmission frequency and computational burden, where the followers can interact locally with each other approaching the dynamics of the leader. Capitalizing on a discrete-time looped-functional, a model-based consensus condition for the closed-loop MASs is derived in form of linear matrix inequalities (LMIs), as well as a design method for obtaining the distributed controllers and event-triggering parameters. Upon collecting noise-corrupted state-input measurements during open-loop operation, a data-driven leader-following MAS representation is presented, and employed to solve the data-driven consensus control problem without requiring any knowledge of the agents' models. This result is then extended to the case of guaranteeing an H∞ performance. A simulation example is finally given to corroborate the efficacy of the proposed distributed event-triggering scheme in cutting off data transmissions and the data-driven design method. Copyright © 2022, The Authors. All rights reserved.

关键词： Linear matrix inequalities

来源：评论

学校读者我要写书评

暂无评论

Cooperative output regulation for networked multi-agent systems based on the self-tuning adaptive distributed observer

Cooperative output regulation for networked multi-agent syst...

引用

American control Conference

作者： Yi Dong Jie Chen Jie Huang Department of Automation Nanjing University of Science and Technology China The State Key Laboratory of Complex System Intelligent Control and Decision Beijing Institute of Technology China Department of Mechanical and Automation Engineering the Chinese University of Hong Kong HK

ISBN: (纸本)9781467386838

In this paper, we first propose a self-tuning adaptive distributed observer for a multi-agent system, which is capable of providing the estimation of the leader's signal to various followers without assuming all the followers know the system matrix of the leader and which avoids calculating the observer gain off-line. We then further develop an adaptive distributed control law to solve the cooperative output regulation problem for linear heterogeneous multi-agent systems. This control law offers two advantages in that it makes the least use of the information of the network and the information of the leader system, and it avoids calculating the observer gain.

关键词： Observers Multi-agent systems Communication networks Closed loop systems Nickel Decentralized control Multi-agent systems Closed loop systems decentralised control networks(communications) Output Regulation Observers Nickel Telecommunications control law Self tuning

来源：评论

学校读者我要写书评

暂无评论

Differential evolution with adaptive population size combining lifetime and extinction mechanisms

Differential evolution with adaptive population size combini...

引用

Asian control Conference

作者： Chunmei Zhang Jie Chen Bin Xin Tao Cai Chen Chen School of Electronic Information Engineering Taiyuan University of Science and Technology Shanxi China Key Laboratory of Complex System Intelligent Control and Decision Ministry of Education Beijing China School of Automation Beijing Institute of Technology Beijing China

ISBN: (纸本)9781612844879

Differential Evolution (DE) is a simple and efficient numerical optimization method. Most DE variants in the literature adopt fixed population size. This paper incorporates into DE the mechanisms of lifetime and extinction which regulate DE's population size in an adaptive manner. The population size is adjusted according to the online progress of fitness improvement. Two schemes of inserting new individuals are proposed to match different mechanisms respectively. The performance of these innovations is examined through the optimization of benchmark problems. The results show that the proposed adaptive population sizing strategy is efficient for improving the convergence and efficiency of the DE.

关键词： Convergence Optimization Benchmark testing Cloning Automation Evolutionary computation Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Development of an anthropomorphic flute robot for the application in science and technology museum

Development of an anthropomorphic flute robot for the applic...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Gao Huang Weimin Zhang Fei Meng Ye Tian Qing Shi Klaus Petersen Atsuo Takanishi Qiang Huang Key Laboratory of Biomimetic Robots and Systems Ministry of Education China Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institute of Technology Beijing China Faculty of Science and Engineering Waseda University Tokyo Japan Key Laboratory of Intelligent Control and Decision of Complex System China

ISBN: (纸本)9781479973989

To resemble the appearance of human beings, humanoid robots should be designed with many DOFs, however, it increases the complexity of the mechanical design and the real-time control, which will make a high cost and have a poor reliability and will not fit for the application in museums or human's daily lives. In this paper, to enable the low cost and high reliability robot to interact with humans naturally and sever humans more friendly, we imported advanced technology of the Waseda's flute robot and retained the most important mechanical parts, such as the lip, lungs and the fingers for the flute playing, on this basis, some other mechanical structures were redesigned; particularly, the robot's appearance was carefully designed; in addition, we also redesigned the hardware structure using our own joint controllers and software system based on CAN bus communication for the cost saving and high reliability. The redesigned robot had just 16 DOFs. Preliminary performance test results showed that this new redesigned robot achieved in producing high quality of flute sound and high sound conversion efficiency, and the period of communication was about 4ms.

关键词： Robot kinematics Robot sensing systems Lungs Joints Legged locomotion control systems

来源：评论

学校读者我要写书评

暂无评论

Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison

arXiv

引用

arXiv 2022年

作者： Liu, Tianying Zhang, Lu Wang, Yang Guan, Jihong Fu, Yanwei Zhao, Jiajia Zhou, Shuigeng Department of Computer Science and Technology Tongji University Shanghai201804 China The Project Management Office of China National Scientific Seafloor Observatory Tongji University Shanghai200092 China Shanghai Key Lab of Intelligent Information Processing The School of Computer Science Fudan University Shanghai200438 China Shanghai Key Lab of Intelligent Information Processing The School of Data Science Fudan University Shanghai200433 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

The generic object detection (GOD) task has been successfully tackled by recent deep neural networks, trained by an avalanche of annotated training samples from some common classes. However, it is still non-trivial to generalize these object detectors to the novel long-tailed object classes, which have only few labeled training samples. To this end, the Few-Shot Object Detection (FSOD) has been topical recently, as it mimics the humans' ability of learning to learn, and intelligently transfers the learned generic object knowledge from the common heavy-tailed, to the novel long-tailed object classes. Especially, the research in this emerging field has been flourishing in recent years with various benchmarks, backbones, and methodologies proposed. To review these FSOD works, there are several insightful FSOD survey articles [58, 59, 74, 78] that systematically study and compare them as the groups of fine-tuning/transfer learning, and meta-learning methods. In contrast, we review the existing FSOD algorithms from a new perspective under a new taxonomy based on their contributions, i.e., data-oriented, model-oriented, and algorithm-oriented. Thus, a comprehensive survey with performance comparison is conducted on recent achievements of FSOD. Furthermore, we also analyze the technical challenges, the merits and demerits of these methods, and envision the future directions of FSOD. Specifically, we give an overview of FSOD, including the problem definition, common datasets, and evaluation protocols. The taxonomy is then proposed that groups FSOD methods into three types. Following this taxonomy, we provide a systematic review of the advances in FSOD. Finally, further discussions on performance, challenges, and future directions are presented. Copyright © 2022, 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

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：