检索结果-南通市图书馆

A Real-time Underwater Robotic Visual Tracking Strategy Based on Image Restoration and Kernelized Correlation Filters

在线全文

学校读者我要写书评

暂无评论

A Real-time Underwater Robotic Visual Tracking Strategy Base...

第30届中国控制与决策会议

作者： Shihan Kong Xi Fang Xingyu Chen Zhengxing Wu junzhi yu University of Chinese Academy of Sciences Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences School of Mechanical Engineering and Automation Beihang university

In this paper, a real-time underwater robotic visual tracking strategy（RUTS） based on underwater image restoration and Kernelized Correlation Filters（KCF） is developed for underwater robots. A real-time and unsupervised advancement scheme（RUAS）, which is utilized in this strategy, performs robustly in restoring underwater images. The KCF, as a high-speed and accurate tracking method on land, is employed in this strategy. To handle the conflict between tracking speed and accuracy, we propose a tracking strategy based on KCF in video sequence restored by RUAS,comparing Histogram of Oriented Gradient（HOG） descriptors and raw pixels gray（RPG） descriptors. We define an index Ac to describe the tracking accuracy and regard the number of frames per second as computing speed. Results of contrast experiments show that the RPG, a much simpler descriptor, can achieve tracking accuracy as precise as HOG,accompanied by an increase of tracking speed up to 36%. Finally, experiments of the KCF-based tracker with RPG on different underwater objects demonstrate the feasibility of the formed RUTS.

关键词： Underwater robotic vision real-time underwater tracking underwater image restoration KCF

Pruning-Based YOLOv4 Algorithm for Underwater Gabage Detection

在线全文

cnki会议

学校读者我要写书评

暂无评论

Pruning-Based YOLOv4 Algorithm for Underwater Gabage Detecti...

第40届中国控制会议

作者： Manjun Tian Xiali Li Shihan Kong Licheng wu junzhi yu School of Information Engineering Minzu University of China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Dept.Adv.Manuf.Robot. BIC-ESAT College of Engineering Peking University

To tackle the problem of aquatic environment pollution, a vision-based autonomous underwater garbage cleaning robot has been developed in our laboratory. This paper proposes a garbage detection method based on a modified YOLOv4,allowing high-speed and high-precision object detection. More specifically, the YOLOv4 algorithm is chosen as a basic neural network framework to perform object detection. With the purpose of further improvement on the detection speed, the channel pruning and layer pruning are implemented on the trained YOLOv4 model, while the fine-tuned mechanism assists the pruned model to restore accuracy. In virtue of the improved detection methods, the robot has the ability to collect garbage *** experimental results indicate that the pruned YOLOv4 detection method can still maintain the high performance even though the parameter amount is 7.062% of the original model.

关键词： Object detection aquatic environment garbage cleaning robot modified YOLOv4

Turning Control of a Tuna-Like BAUV for a Minimum Turning Radius

在线全文

cnki会议

学校读者我要写书评

暂无评论

Turning Control of a Tuna-Like BAUV for a Minimum Turning Ra...

第40届中国控制会议

作者： Sheng Du junzhi yu Zhengxing Wu Di Chen Ming Wang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Dept.Adv.Manuf.Robot. BIC-ESAT College of Engineering Peking University School of Information and Electrical Engineering Shandong Jianzhu University

In order to break the bottleneck of conventional autonomous underwater vehicles（AUVs）, biologically-inspired AUVs（BAUVs） have drawn great attention. This paper explores the turning control issue of a tuna-like BAUV with the purpose of seeking a minimum turning radius. Specifically, for better understanding of the turning motion, a dynamical model is established and the force acting on the tail fin is taken as the main source. Because of the complex nonlinear relationship and physical restrictions, it is hard to optimize the turning radius directly. To tackle with this problem, the input signals of joints are generated by sine function so as to satisfy physical constraints, and simulations under different parameter combinations are ***, a fixed tail joint method and a half-cycle flapping method are chosen and compared in an indoor pool. Finally,the experimental results verify the effectiveness of proposed methods, and a minimum turning radius of the tuna-like BAUV is achieved as small as 0.37 body lengths.

关键词： Turning control biologically-inspired autonomous underwater vehicles tuna-like robot

Online Optimization of Normalized CPGs for a Multi-Joint Robotic Fish

在线全文

cnki会议

学校读者我要写书评

暂无评论

Online Optimization of Normalized CPGs for a Multi-Joint Rob...

第40届中国控制会议

作者： Ru Tong Zhengxing Wu Jian Wang Min Tan junzhi yu School of Artificial Intelligence University of Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences Dept.Adv.Manuf.Robot. BIC-ESATCollege of EngineeringPeking University

As a popular control rhythm of the multi-joint robotic fish,Center Pattern Generators（CPGs） plays an important role for motion ***,its optimal parameters are tough to seek through traditional *** order to address this problem,we propose an online optimization method for CPG parameters,including a novel normalized CPGs（N-CPGs）and a learning-based optimization *** N-CPGs,the network parameters can be fully decoupled,which provides a great convenience for model parameter *** particular,by applying the established dynamic model of the robotic fish,we use the deep Q network（DQN） to optimize the N-CPGs,aiming at improving the speed ***,extensive simulation results verify the effectiveness of proposed method,laying a solid foundation for real-time online control optimization of versatile motion modes in complex application scenarios.

关键词： Biomimetic robotic fish motion optimization Central Pattern Generator(CPG) online optimization

Model Predictive Control Based Path Following of an Amphibious Robot

在线全文

cnki会议

学校读者我要写书评

暂无评论

Model Predictive Control Based Path Following of an Amphibio...

第40届中国控制会议

作者： Dongyue Li Jie Pan Jincun Liu Ming Wang junzhi yu Department of Adv.Manuf.Robot. College of Engineering Peking University College of Information and Electrical Engineering China Agricultural University School of Information and Electrical Engineering Shandong Jianzhu University

The path following of the amphibious robot is rarely investigated. This paper deals with the following control issue of a fish-inspired amphibious robot. Firstly, land and underwater kinematic models of the robot are established. Based on the kinematic model, we formulate a nonlinear model predictive control method. Then, a gradual switching strategy of the robot’s terrestrial and aquatic motion modes is proposed. By combining the model predictive control method and the gradual switching strategy, the robot is able to follow the path across land and water. Simulation results of following circle and sine-like paths verify the effectiveness of the presented control method. Moreover, the gradual switching strategy is able to maintain stable following when the path switches between land and water.

关键词： Path following model predictive control amphibious robot switching strategy

基于A^(*)和TEB融合的行人感知无碰跟随方法

在线全文

cnki会议

学校读者我要写书评

暂无评论

航空学报 2021年第4期42卷 495-504页

作者：庞磊曹志强喻俊志中国科学院自动化研究所复杂系统管理与控制国家重点实验室北京100190 中国科学院大学人工智能学院北京100049 北京大学工学院先进制造与机器人系北京100871

移动机器人通过跟随一个指定行人实现导航是一种便捷的方式。针对行人跟随中的机器人跟随和避障问题,提出了一种基于路径规划的无碰跟随方法。该方法结合激光点云分割提供的非行人障碍信息生成静态障碍代价地图,并根据3D行人定位结果,... 详细信息

移动机器人通过跟随一个指定行人实现导航是一种便捷的方式。针对行人跟随中的机器人跟随和避障问题,提出了一种基于路径规划的无碰跟随方法。该方法结合激光点云分割提供的非行人障碍信息生成静态障碍代价地图,并根据3D行人定位结果,利用基于无迹卡尔曼滤波器(Unscented Kalman Filter,UKF)和最近邻联合概率数据关联(Nearest Near Joint Probabilistic Data Association,NN-JPDA)的多行人跟踪器估计干扰行人运动状态,进而生成动态行人代价地图。在此基础上,基于A^(*)的全局规划器结合静态障碍代价地图输出指向目标行人的全局路径,而基于时间弹性带(TEB)算法的局部规划器也将动态行人代价地图纳入考虑范围以规划优化的局部路径,这能够帮助机器人实现行人感知的避障且跟随全局路径。通过低频全局规划与高频局部规划结合的方式实现对目标行人安全无碰的跟随。实验验证了所提方法的有效性。

关键词：导航行人跟随路径规划避障运动状态估计无碰跟随

在线全文

学校读者我要写书评

暂无评论

老年用户使用移动医疗意愿的影响因素元分析

图书馆论坛 2024年第2期44卷 153-160,F0003页

作者：贾君枝张贵香施雨中国人民大学信息资源管理学院南京农业大学信息管理学院

信息和通信技术进步为移动医疗的实施提供了便利,但老年人口移动医疗服务使用率偏低。文章针对移动医疗老年用户使用意愿影响因素实证研究之间结果不一致的问题,对相关文献进行综合梳理和再分析。基于近十年30篇移动医疗使用意愿相关实... 详细信息

信息和通信技术进步为移动医疗的实施提供了便利,但老年人口移动医疗服务使用率偏低。文章针对移动医疗老年用户使用意愿影响因素实证研究之间结果不一致的问题,对相关文献进行综合梳理和再分析。基于近十年30篇移动医疗使用意愿相关实证研究文献,采用元分析方法,利用CMA软件检验变量关系异质性、文献发表偏倚并计算各变量关系的合并效果量,并以国家或地区的经济发展水平作为调节变量进行次群体分析。研究表明:老年用户使用移动医疗的行为意愿通常直接受到7个因素的影响:努力期望、绩效期望、态度、价值价格、感知信任、便利条件以及社会影响;其中,技术焦虑与努力期望高度负相关,努力期望正向影响绩效期望,绩效期望显著影响老年用户使用移动医疗态度,经济发展水平对相关变量关系的调节作用明显。

关键词：移动医疗老年用户影响因素元分析

维普期刊数据库博看期刊

具有嵌入式视觉的仿生机器鱼头部的平稳性控制

在线全文

学校读者我要写书评

暂无评论

机器人 2015年第2期37卷 188-195,203页

作者：孙飞虎喻俊志徐德中国科学院自动化研究所复杂系统管理与控制国家重点实验室北京100190 中国科学院自动化研究所精密感知与控制研究中心北京100190

具有嵌入式视觉的仿生机器鱼的摄像头往往安装在头部,为了获取稳定的图像数据,研究了游动过程中头部的平稳性控制问题.首先,基于牛顿-欧拉方法对仿生机器鱼的水动力学进行建模.然后,基于动力学模型,比较了两种鱼体波模型下的机器鱼头部... 详细信息

具有嵌入式视觉的仿生机器鱼的摄像头往往安装在头部,为了获取稳定的图像数据,研究了游动过程中头部的平稳性控制问题.首先,基于牛顿-欧拉方法对仿生机器鱼的水动力学进行建模.然后,基于动力学模型,比较了两种鱼体波模型下的机器鱼头部摆动情况.进一步地采用遗传算法对输入到运动关节的参数进行优化,实现机器鱼头部的最小摆动.最后,在自主设计的具有嵌入式视觉的仿生机器鱼上进行了实验.结果表明,在平稳性控制后,头部的摆动幅度明显减小,采集到的图像的稳定性与连续性有较大改进,但游动速度有所降低.该方法为基于嵌入式视觉的运动控制与任务执行提供了有效保障.

关键词：平稳性控制水动力学建模遗传算法机器鱼

基于可变关节数的模块化两栖仿生机器人转弯控制

在线全文

学校读者我要写书评

暂无评论

机器人 2010年第4期32卷 491-498页

作者：丁锐喻俊志杨清海谭民中国科学院自动化研究所复杂系统与智能科学重点实验室北京100190

概述了一种具有模块化结构的两栖仿生机器人设计,结合其关节数可变和主从轮式驱动的特点,给出了任意关节数偏转转弯的地面转弯控制方法,并推导了其最小转弯半径.针对多关节两栖机器人的转弯推进方式,利用ADAMS下的运动学模型进行了仿真... 详细信息

概述了一种具有模块化结构的两栖仿生机器人设计,结合其关节数可变和主从轮式驱动的特点,给出了任意关节数偏转转弯的地面转弯控制方法,并推导了其最小转弯半径.针对多关节两栖机器人的转弯推进方式,利用ADAMS下的运动学模型进行了仿真验证,给出了相应的仿真结果.同时,平衡性分析进一步表明了关节转弯推进方式在当前两栖机器人样机上的适用性.实验结果表明了该转弯方法的有效性,它能够满足机器人的地面运动需求.

关键词：两栖仿生机器人变关节数模块化结构转弯控制