检索结果-内蒙古大学图书馆

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Yuan Zhao Hanmin Sheng Jinliang Shao Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China University of Electronic Science and Technology of China Chengdu China Laboratory of Electromagnetic Space Cognition and Intelligent Control Beijing China

Direct position determination (DPD) technique has been shown its appealing to emitter localization thanks to high estimation accuracy. Motivated by the practical applications, this paper proposed a computational efficient DPD approach using the multiple signal classification (MUSIC) formulation. Whereas, the proposed approach calculates the signal and the noise subspace using the multi-stage Wiener filter (MSWF) without employing the hardware-consuming eigen-decomposition. Hence, the proposed MSWF-DPD can be cheap equipment friendly. And we verify the performance loss is small through the simulations in the end of this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High-Speed Trajectory Tracking control for Quadrotors via Deep Reinforcement Learning

High-Speed Trajectory Tracking Control for Quadrotors via De...

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Hean Hua Hang Zhong Hui Zhang Yongchun Fang Yaonan Wang College of Electrical and Information Engineering Hunan University Changsha China National Engineering Research Center for Robot Visual Perception and Control Technology Changsha China School of Robotics Hunan University Changsha China Institute of Robotics and Automatic Information System College of Artificial Intelligence Nankai University Tianjin Key Laboratory of Intelligent Robotics Nankai University Tianjin China

ISBN: (数字)9798350379228

ISBN: (纸本)9798350390780

This paper presents a learning-based high-speed trajectory tracking control strategy for quadrotors, which achieves efficient learning and strong reliability by the collaboration of deep reinforcement learning (RL) and self-tuning mechanism. Different from existing methods, the proposed strategy is designed to explore optimal control performance by taking advantage of model-based self-tuning mechanism and deep reinforcement learning. Specifically, the self-tuning guided deep RL scheme is put forward for quadrotors, with superior learning efficiency and strong adaptability. Firstly, a novel self-tuning mechanism is constructed and some auxiliary variables are introduced to enhance the tracking performance. Then, based on the model-driven self-tuning design, the deep RL is proposed to achieve model-guided learning, where the tuning actions are adopted in the evaluation process during training, aiming at removing the bad explorations by the carefully designed parallel evaluation. Finally, the convergence is analyzed based on the proposed learning framework, which indicates the efficient cooperation of exploration and self-tuning mechanism. To verify the effectiveness of the proposed controller, the guided training and hardware experiments are implemented to show efficient cooperation and satisfactory high-speed trajectory tracking control of the proposed method.

关键词： Training Adaptation models Trajectory tracking Heuristic algorithms Optimal control Deep reinforcement learning Hardware

来源：评论

学校读者我要写书评

暂无评论

Intention-Aware Planner for Robust and Safe Aerial Tracking

Intention-Aware Planner for Robust and Safe Aerial Tracking

引用

IEEE/RSJ International Conference on intelligent Robots and Systems (IROS)

作者： Qiuyu Ren Huan Yu Jiajun Dai Zhi Zheng Jun Meng Li Xu Chao Xu Fei Gao Yanjun Cao The State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China The Robotics Institute of Zhejiang University Yuyao China Huzhou Institute Zhejiang University Huzhou China Huzhou Laboratory of Autonomous Intelligent Systems Huzhou China College of Electrical Engineering Zhejiang University Hangzhou China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Autonomous target tracking with quadrotors has wide applications in many scenarios, such as cinematographic follow-up shooting or suspect chasing. Target motion prediction is necessary when designing the tracking planner. However, the widely used constant velocity or constant rotation assumption can not fully capture the dynamics of the target. The tracker may fail when the target happens to move aggressively, such as sudden turn or deceleration. In this paper, we propose an intention-aware planner by additionally considering the intention of the target to enhance safety and robustness in aerial tracking applications. Firstly, a designated intention prediction method is proposed, which combines a user-defined potential assessment function and a state observation function. A reachable region is generated to speci cally evaluate the turning intentions. Then we design an intention-driven hybrid A* method to predict the future possible positions for the target. Finally, an intention-aware optimization approach is designed to generate a spatial-temporal optimal trajectory, allowing the tracker to perceive unexpected situations from the target. Benchmark comparisons and real-world experiments are conducted to validate the performance of our method.

关键词： Target tracking Semantics Prediction methods Turning Prediction algorithms Robustness Safety Planning Trajectory optimization Quadrotors

来源：评论

学校读者我要写书评

暂无评论

Image Feature Matching Based on Spatial Constraints and Inertial Assistance for AGV Navigation in Digital Workshops 12

Image Feature Matching Based on Spatial Constraints and Iner...

引用

12th International Conference on CYBER Technology in Automation, control, and intelligent Systems, CYBER 2022

作者： Sun, Shijie Chen, Li Liang, Wei An, Haibo Zhang, Yinlong School of Artificial Intelligence Shenyang University of Technology Shenyang110020 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China Science and Technology on Information Systems Engineering Laboratory The 28th Research Institute of Cetc Jiangsu Nanjing210007 China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

VSLAM shows promising potential for AGV navigation in digital workshops, thanks to its merits in low cost, easy configuration, high flexibility, and high accuracy. However, the AGV visual perception system could be easily affected by lighting changes, and body abrupt motions. The state-of-the-art visual feature matching methods may fail to fulfill the navigation tasks in presence of these challenging issues. In order to solve these problems, we propose a feature matching method based on feature space constraints and inertial assistance. In order to reduce the computational time, the spatial constraints are designed to delete the obvious false matches. Besides, the Inertia Assistance Visual Sample Consensus (IAVSAC) is proposed to reduce the computational time in discriminating the wrong feature matches. In order to ensure the reliability of the inertial data, the analysis of IMU noise has been performed. The best IMU configuration with the smallest noises is designed. Our proposed method has been evaluated on the developed AGV navigation platform. The results show that the feature matching accuracy rate and computational time of ours are more favorable than those of RANSAC and MSAC. © 2022 IEEE.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Obstacle-Avoidance Motion Planning Method of Manipulator Based on Deep Reinforcement Learning

引用

Unmanned Systems 2025年

作者： Liu, Yiyang Wu, Defan Fu, Yukai Bai, Hongfei Deng, Chao State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210023 China

In recent years, driven by the rapid advancement of industrial automation and intelligent manufacturing, the demand for manipulators to perform tasks in complex environments has significantly increased. Traditional motion planning methods face challenges of computational complexity and lack of adaptability when handling robots with redundant degrees of freedom. To address these issues, this paper proposes a novel obstacle avoidance motion planning method for manipulators based on deep reinforcement learning (DRL), which is especially important when unmanned systems operate in a GPS-free environment. The primary contributions are twofold: (i) we propose an innovative algorithm, termed PPO-HER, which incorporates hindsight experience replay (HER) into proximal policy optimization (PPO) during training, effectively leveraging failed experiences to enhance policy learning efficiency;(ii) an adaptive action exploration strategy is designed to accelerate training convergence and avoid local optima. Experimental results demonstrate that the PPO-HER algorithm and the adaptive action exploration strategy perform exceptionally well across three environments of varying difficulty, significantly improving network training speed and success rates, shortening planned paths, and enhancing autonomous obstacle avoidance capabilities. These findings provide new ideas for target location and tracking of unmanned systems, and lay the foundation for future learning and data-driven approaches in complex environments. © World Scientific Publishing Company.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A New Recursive Composite Adaptive controller for Robot Manipulators

引用

Space(Science & Technology) 2021年第1期2021卷 77-83页

作者： Jianfei Li Yaobing Wang Zhiyong Liu Xin Jing Chengwei Hu The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Beijing Key Laboratory of Intelligent Space Robotic System Technology and Applications Beijing Institute of Spacecraft System EngineeringBeijing 100094China State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China

In this paper,a new recursive implementation of composite adaptive control for robot manipulators is *** investigate the recursive composite adaptive algorithm and prove the stability directly based on the Newton-Euler equations in matrix form,which,to our knowledge,is the first result on this point in the *** proposed algorithm has an amount of computation O(n),which is less than any existing similar algorithms and can satisfy the computation need of the complicated multidegree *** manipulator of the Chinese Space Station is employed as a simulation example,and the results verify the effectiveness of this proposed recursive algorithm.

关键词： Robot manipulators robot

来源：评论

学校读者我要写书评

暂无评论

Robot-CT Scanning Oriented Synchronous Trajectory Planning of a Dual-Manipulator System

Robot-CT Scanning Oriented Synchronous Trajectory Planning o...

引用

Chinese control Conference (CCC)

作者： Shuaikang Zhang Mingxing Yuan Xuebo Zhang Tianjin Key Laboratory of Intelligent Robotics Institute of Robotics and Automatic Information System College of Artificial Intelligence Nankai University Tianjin P. R. China Key Laboratory of Industrial Internet of Things & Networked Control Ministry of Education Chongqing P. R. China

At present, most CT scanning systems adopt the traditional horizontal O-frame, suspension or C-arm structures, which can not balance the flexibility and functionality. With the development of robot technology, CT scanning systems based on manipulators have gradually emerged. However, limited by the motion accuracy of the manipulator, most researchers sacrifice the flexibility or increase the mass to improve the accuracy. To overcome this limitation, a new master-slave teaching-based scanning method is proposed to improve the scanning accuracy of the dual-manipulator Robot-CT system with the auxiliary function of rigid links. First, a rigid link is employed to connect the end effectors of the two manipulators. Next, the sampled trajectory of each joint of the slave-manipulator is recorded while the master-manipulator pulls the slave-manipulator to perform a circular motion. Finally, when carrying out the scanning, the dual-manilupator system reproduces the recorded joint trajectory without the rigid element, thereby improving the accuracy of the dual-manipulator CT scanning system to achieve a high-accuracy spatiotemporal synchronization and alignment of pose. To this end, a fifth-order spline interpolation is used to interpolate the sampled trajectory of each joint of the slave-manipulator, which allows it to perfectly reproduce the joint trajectory recorded during the teaching process and ensures the smoothness of the angular velocity and acceleration curves. Simulations are investigated and the corresponding results confirm the effectiveness of the trajectory planning method of the slave-manipulator.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MDANet: Multi-scale Vague Boundary Augmented Dual Attention Network for Semantic Segmentation of Outdoor Plants

MDANet: Multi-scale Vague Boundary Augmented Dual Attention ...

引用

IEEE International Conference on Real-time Computing and robotics (RCAR)

作者： Pengfei Yuan Hongmin Wu Zhihan Zhu Shixin Mao Xuefeng Zhou Haifei Zhu Biomimetic and Intelligent Robotics Lab (BIRL) Guangdong University of Technology Guangzhou China Guangdong Key Laboratory of Modern Control Technology Institute of Intelligent Manufacturing Guangdong Academy of Sciences Guangzhou China Jiutian Innovation (Guangdong) Intelligent Technology Co. Ltd Foshan Guangdong China

Outdoor plant spraying is an important means of controlling mosquitoes and insects. Currently, outdoor plant spraying operations are mainly done by manual spraying. However, manual sprayings have some problems, such as waste of chemical solution and potential harm to the operator’s body. Therefore, robotic spraying will become the future development trend. In this paper, we propose a multi-scale vague boundary augmented dual attention network (MDANet) to help robots achieve outdoor plant recognition. This network introduces a multi-scale attention module in high-dimensional branches to distinguish between oversized and undersized plants and a vague boundary augmented attention module in low-dimensional branches to enhance the ability to judge different categories of plants near the vague boundary. Finally, they are fused to improve the effect of plant segmentation of similar categories in complex environments at the roadside. Experiments exhibited that the proposed network model outperformed existing semantic segmentation models such as FCN, PSANet, CCNet, and DANet with the least number of parameters and achieved the mIoU and mPA of 83.74% and 90.17%, respectively, in the complex natural roadside environment. The proposed network model demonstrated its ability to distinguish similar plants, such as trees, bushes, flowering shrubs and lawns, which is conducive to implementing mobile robot spraying operations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A History Information-Based A* Algorithm for the Path Planning with Multiple Alternative Destinations

A History Information-Based A* Algorithm for the Path Planni...

引用

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Ke Wang Wei Liang Huaguang Shi Jialin Zhang Qi Wang State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China School of Artificial Intelligence Henan University Zhengzhou China

ISBN: (数字)9798350394085

ISBN: (纸本)9798350394092

As a cornerstone technology in automation, path planning plays a crucial role across various domains, including logistics, autonomous vehicles, and robotics. A novel path planning challenge, focusing on routes with multiple alternative destinations, has emerged as a focal point in industrial settings. Traditional approaches such as breadth-first and heuristic searches lack specific optimizations for this challenge, resulting in suboptimal efficiency. This paper introduces a new approach to the path planning problem with multiple alternative destinations that utilizes historical data. It features three heuristic strategies: leveraging historical information for search acceleration, pruning based on the length of the current shortest path, and searching in ascending order of the Manhattan distance. These strategies enhance the search efficiency by leveraging historical information for faster searches and pruning based on real-time search outcomes. Simulation results show that the proposed algorithm outperforms the existing works in terms of the computational cost.

关键词： Service robots Navigation Simulation Focusing Path planning Real-time systems Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Dimension Reduction for Dynamic Analysis of Gene Expression Data Using Variational Autoencoder

Dimension Reduction for Dynamic Analysis of Gene Expression ...

引用

IEEE International Conference on Cyber Technology in Automation, control, and intelligent Systems

作者： Shuai Yuan Shipeng Chen Yongliang Yang School of Electrical and Control Engineering Shenyang Jianzhu University Shenyang Liaoning China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang Liaoning China

Single-cell RNA sequencing technology captures gene expression at the whole-genome scale and single-cell level in many cells. Thus, the cellular states during a physiological process would be captured in detail. These data provide new opportunities and challenges for systems biology. Previously, the models in systems biology dealt with the dynamics of specific signaling pathways. However, it is almost impossible to directly model the dynamics of the whole genome due to the ultrahigh dimensionality of the data. Here, to model its gene regulatory dynamics, the dimensionality of the whole genome was reduced significantly using the latent space of a variational autoencoder, a generative deep learning model. In the low-dimensional latent space, an ordinary differentiation equation (ODE) system has been established to analyze the dynamic characteristics of the whole genome system. To demonstrate the effectiveness of this method, we generated a low-dimensional representation of a systems biology model we previously developed. The variational autoencoder reduced the dimension from 13 to 2 in latent space. An ODE model was developed to analyze the dynamics of this two-dimensional system. The results indicated that the 2-dimensional model captured the essence of the original systems biology model.

关键词：

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：