检索结果-南通市图书馆

Off-policy correction algorithm for double Q network based on deep reinforcement learning

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IET Cyber-Systems and Robotics 2023年第4期5卷 16-26页

作者： Qingbo Zhang manlu liu Heng Wang Weimin Qian Xinglang Zhang School of Information Engineering Southwest University of Science and TechnologyMianyangChina Robot Technology Used for Special Environment Key Laboratory of Sichuan Province MianyangChina Tianfu Institute of Research and Innovation Southwest University of Science and TechnologyChengduChina

A deep reinforcement learning(DRL)method based on the deep deterministic policy gradient(DDPG)algorithm is proposed to address the problems of a mismatch between the needed training samples and the actual training samples during the training of in-telligence,the overestimation and underestimation of the existence of Q-values,and the insufficient dynamism of the intelligence policy *** method introduces the Actor-Critic Off-Policy Correction(AC-Off-POC)reinforcement learning framework and an improved double Q-value learning method,which enables the value function network in the target task to provide a more accurate evaluation of the policy network and converge to the optimal policy more quickly and stably to obtain higher value *** method is applied to multiple MuJoCo tasks on the Open AI Gym simulation *** experimental results show that it is better than the DDPG algorithm based solely on the different policy correction framework(AC-Off-POC)and the conventional DRL *** value of returns and stability of the double-Q-network off-policy correction algorithm for the deep deterministic policy gradient(DCAOP-DDPG)pro-posed by the authors are significantly higher than those of other DRL algorithms.

关键词： neural network Q-learning reinforcement learning

Fault-Tolerant Control Method of Robotic Arm Based on Machine Vision

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Fault-Tolerant Control Method of Robotic Arm Based on Machin...

第30届中国控制与决策会议

作者： Xinmao Li manlu liu Wei Wang Yingxing Li Minghao Li Southwest University of Science and Technology Datang Shandong Yantai Power Development co.LTD

We proposed a fault-tolerant control method based on machine vision to enhance the reliability of the robotic arm in the radiation ***,we introduced the joint angle visual detection method as an angle detection backup solution,which was used to timely detect the joint angle of the robotic arm in case of encoder ***,we introduced an encoder fault diagnosis mechanism,and the difference between the machine visual feedback value and corresponding encoder feedback values was used as the basis of encoder *** the encoder failed,it could be switched to the joint angle visual detection in real *** the Canny edge detection and the Probabilistic Hough transform,the method could extract the identification tag of robotic arm joint image from the front-end camera,and hence the joint angle value was ***,in the fault-tolerance experiment,the proposed approach found the encoder failure and switched detection method,and the scheduled task continued to the *** error about the angle detection based on the machine vision would not exceed ± 0.008.

关键词： Machine vision fault-tolerant control robotic arm Hough transform

Research On Fault Tolerant Control Strategy of Multi-Degree-of-Freedom Manipulator with Single Joint Faults

在线全文

cnki会议

学校读者我要写书评

暂无评论

Research On Fault Tolerant Control Strategy of Multi-Degree-...

第37届中国控制会议

作者： Qijie Zhou manlu liu Wei Wang Liang Xu Tianxiang Ao Hua Zhang Special Environment Robot Technology Key Laboratory of Sichuan Province Southwest University of Science and Technology Datang Shandong Yantai Power Development co.LTD

While performing the typical task of point-to-point motion of redundant manipulator,single joint faults suddenly *** the effect of the configuration on the manipulator’s task,here we propose an improved genetic algorithm based on the measurement of manipulator end-to-target position error and the manipulability measure,which makes the end of the manipulator arrive at the target position with less error *** addition,it also makes the machine has a greater operable arm configuration upon *** is used for modeling and simulating with a three-link planar arm as an *** groups of simulation experiments are carried out to compare the improved genetic algorithm with the traditional genetic algorithm based on position error,and the simulation results are analyzed and ***,the physical robot proves the validity and reliability of this method.

关键词： Redundant Manipulator Manipulability Measure Position Error Genetic Algorithm

Manipulator Control Method Based on Deep Reinforcement Learning

在线全文

cnki会议

学校读者我要写书评

暂无评论

Manipulator Control Method Based on Deep Reinforcement Learn...

第32届中国控制与决策会议

作者： Rui Zeng manlu liu Junjun Zhang Xinmao Li Qijie Zhou Yuanchen Jiang Special Environment Robot Technology Key Laboratory of Sichuan Province Southwest University of Science and Technology

Robotic arm have transformed the manufacturing industry and have been used for scientific exploration in human inaccessible environments. The existing manipulator control methods based on deep reinforcement learning usually discretize the action space or consider the planar manipulator, which results in great limitations of the tasks that the manipulator can accomplish complete. In this paper, we propose a control method based on the Deep Deterministic Policy Gradient（DDPG） algorithm for the 6 degree-of-freedom manipulator that reach the object position in three-dimensional space. This paper designs two types of reward functions, and introduces the manipulability index into the algorithm. The manipulability index evaluates the flexibility of the robotic arm in the work space, which is referenced by the algorithm to optimize the joint pose of the robotic arm to reach the object position. By building a simulation platform to compare the algorithms based on two reward functions, the effectiveness of the DDPG algorithm is verified, and the 6 degree-of-freedom manipulator can reach the object position with more flexible posture based on the DDPG algorithm with manipulability index.

关键词： Deep reinforcement learning Manipulator Reward function Joint pose

Research on UWB/IMU location fusion algorithm based on GA-BP neural network

在线全文

cnki会议

学校读者我要写书评

暂无评论

Research on UWB/IMU location fusion algorithm based on GA-BP...

第40届中国控制会议

作者： Kang Yang manlu liu Yu Xie Xinglang Zhang Weidong Wang Songlin Gou Haoxiang Su Special Environment Robot Technology Key Laboratory of Sichuan Province Southwest University of Science and Technology

In order to solve the problem of large errors in single positioning technology in complex indoor environments, a positioning fusion method based on GA-BP neural network is proposed. The internal calibration of the IMU is used to reduce or eliminate the coordinate axis deviation and fixed error of the IMU, and the obtained acceleration, angular velocity, attitude Angle information and the PDR positioning mechanism are used to carry out inertial navigation. UWB positioning technology uses an improved TWR ranging algorithm for ranging, and uses the trilateral ranging method to obtain the corresponding *** BP neural network is used to fuse the data of the two positioning technologies, and the genetic algorithm（GA） is used to optimize the initial weights and thresholds of the BP neural network to improve the performance and prediction accuracy of the network. The experimental results show that the GA-BP neural network integrates the two positioning data and calculates the positioning results. The average positioning error of the GA-BP neural network is 9.6cm, which is about 80% higher than the positioning accuracy of the single positioning method and 43.9% higher than the prediction error of the BP neural network.

关键词： GA-BP neural network IMU UWB

高校视觉传达设计专业《印刷工艺学》课程教学改革探索

在线全文

cnki会议

学校读者我要写书评

暂无评论

鞋类工艺与设计 2022年第11期2卷 77-79页

作者：刘曼鹭南京航空航天大学金城学院江苏南京210000

印刷工艺学是一门综合艺术、材料、机械的专业基础课,对视觉传达设计专业的学生来说十分重要。本文分析归纳了印刷工艺学课程的特点,对现有的印刷工艺学课程进行了改革探究。教师应突出学生的主体地位,培养学生自主学习的内在动力,提高... 详细信息

印刷工艺学是一门综合艺术、材料、机械的专业基础课,对视觉传达设计专业的学生来说十分重要。本文分析归纳了印刷工艺学课程的特点,对现有的印刷工艺学课程进行了改革探究。教师应突出学生的主体地位,培养学生自主学习的内在动力,提高学生的动手能力。课程安排上应增加实验实习课时,开展实验室教学,重视理论教学与实践教学相结合。应用创新型的教学方法和手段,改善考核方式,不断改进教学效果,以促进学生全面发展,成为社会所需要的高素质应用型人才。

关键词：高校印刷工艺学视觉传达设计

在线全文

学校读者我要写书评

暂无评论

浅谈数字插画艺术在海报设计中的应用

鞋类工艺与设计 2022年第10期2卷 74-76页

作者：刘曼鹭南京航空航天大学金城学院江苏南京210000

随着社会的进步、设计行业的不断发展,插画艺术作为一种重要的视觉传达形式被应用于人们生活的方方面面。时至今日,新技术不断被应用到插画设计中,手绘插画逐渐演变成采用电脑、平板等工具创作插图,传统的颜料、画笔等工具也逐渐被各类... 详细信息

随着社会的进步、设计行业的不断发展,插画艺术作为一种重要的视觉传达形式被应用于人们生活的方方面面。时至今日,新技术不断被应用到插画设计中,手绘插画逐渐演变成采用电脑、平板等工具创作插图,传统的颜料、画笔等工具也逐渐被各类软件、设备取代。数字插画与时俱进,在平面设计中发挥着越来越重要的作用,被广泛应用各类海报设计的领域。本文首先分析了数字插画的概念和发展,再从数字插画艺术在海报设计中的应用问题入手,具体分析它在海报设计中的意义。

关键词：数字插画艺术海报设计应用意义

结合旋量和代数方法的工业机械臂逆运动学解法

在线全文

学校读者我要写书评

暂无评论

机械科学与技术 2017年第8期36卷 1224-1229页

作者：敖天翔刘满禄张华赵皓西南科技大学特殊环境机器人技术四川省重点实验室四川绵阳621000

针对工业机械臂逆运动学解算的问题,提出一种结合旋量方法和代数方法的逆运动学新解法。通过旋量的方法将工业机械臂整体逆运动学问题进行分解,利用Paden-kahan逆运动学子问题求解。并在该基础上利用工业机械臂的结构特点,利用代数方法... 详细信息

针对工业机械臂逆运动学解算的问题,提出一种结合旋量方法和代数方法的逆运动学新解法。通过旋量的方法将工业机械臂整体逆运动学问题进行分解,利用Paden-kahan逆运动学子问题求解。并在该基础上利用工业机械臂的结构特点,利用代数方法进一步简化末端腕部三个关节的问题求解。以安川公司MH6六自由度工业机械人为例,验证算法正确性。实验表明:该方法可以获得正确的八组逆解并在旋量解逆运动学的基础上有效减少了中间计算步骤,降低了时间复杂度和空间复杂度。

关键词：工业机器人指数基建模(POEs) 逆运动学旋量理论

在线全文

学校读者我要写书评

暂无评论

基于引导采样的Kinect深度图修补算法

计算机应用研究 2018年第8期35卷 2532-2534页

作者：杨厚易刘满禄张华西南科技大学信息工程学院特殊环境机器人技术四川省重点实验室四川绵阳621010 中国科学技术大学信息科学技术学院合肥230026

针对Kinect采集到带有大量的结构性缺失的深度图,提出了一种基于引导采样的深度图空洞噪声修补算法。算法首先将深度图所对应的彩色图片转换为灰度图,然后用K-means算法将彩色图转换而来的灰度图进行聚类处理,将生成的聚类图作为引导图... 详细信息

针对Kinect采集到带有大量的结构性缺失的深度图,提出了一种基于引导采样的深度图空洞噪声修补算法。算法首先将深度图所对应的彩色图片转换为灰度图,然后用K-means算法将彩色图转换而来的灰度图进行聚类处理,将生成的聚类图作为引导图。联合引导图对深度图空洞噪声边缘深度值采样,采集多个深度值并计算深度均值,最后使用深度均值来作为空洞的深度估计值。通过与基于蒙特卡罗不确定度评价的深度图修补算法(MC-UE)相比较,由于有引导图的矫正作用,边缘细节更加清晰准确。对于处理较小面积的空洞噪声,处理结果相较于MC-UE算法,均方误差降低4%左右。对于处理较大面积的空洞噪声,均方误差较MC-UE算法降低了9.65%~14.32%。实验证明引导采样算法在处理较大面积空洞噪声时相较于MC-UE算法有更低的均方误差。

关键词：深度图空洞噪声聚类噪声修补均方误差