检索结果-内蒙古大学图书馆

Optimal Path Search for robot Manipulator using Deep Reinforcement Learning

学校读者我要写书评

暂无评论

IEIE Transactions on smart Processing and Computing 2021年第5期10卷 424-430页

作者： Sunwoo, Yungmin Lee, Won Chang Department of Smart Robot Convergence and Application Engineering Pukyong National University Busan Korea Republic of Department of Electronic Engineering Pukyong National University Busan Korea Republic of

Much research using deep reinforcement learning has been conducted to make robot manipulators perform certain tasks with little prior knowledge of the work environment. However, due to the high-dimension continuous action-state spaces that a robot manipulator must work in, it is difficult for deep reinforcement learning agents to find or even learn optimal policies. In this paper, we present a method for generating optimal paths for the end effector of a robot manipulator to move through. This is achieved by using images of the workspace that allow us to avoid the problems of high dimensionality while the system learns pick-and-place tasks using deep reinforcement learning. The robot simulator Webots was used to implement the robot model in a virtual work environment. Simulations confirmed that the robot manipulator is able to successfully move target objects from their starting points to their destinations while avoiding moving obstacles in real time, even if the size, position, and number of obstacles are varied. © 2021 Institute of Electronics and Information Engineers. All rights reserved.

关键词： Reinforcement learning

An Anti-disturbance backstepping control for a two-axis gimbal system with euler angle feedback and delayed inputs

学校读者我要写书评

暂无评论

An Anti-disturbance backstepping control for a two-axis gimb...

2021 International Conference on System Science and Engineering, ICSSE 2021

作者： Huynh, Thinh Tran, Minh Thien Bok Kim, Young Pukyong National University Department of Smart Robot Convergence and Application Engineering Busan Korea Republic of

ISBN: (纸本)9781665448482

Maintaining the position of a camera by a gimbal system in surveillance applications has never been an easy task since the system is carried on a mobile vehicle. In this study, the design of a stabilization control for the gimbal system is presented to deal with this problem. Firstly, the system kinematics and dynamics are derived in mathematical models, where influences of disturbances, system nonlinearities, and hardware parameterizations are taken into consideration. Secondly, an observer is proposed to estimate the unmeasured disturbances. Then, a full state feedback controller is designed based on the backstepping procedure to ensure the performance of the system. The system stability is preserved in the sense of Lyapunov theory, and the effectiveness is validated by simulation studies. Although the effects of delay time cannot be rejected completely, performances of the proposed control are better than those of previous related studies. © 2021 IEEE.

关键词： Sliding mode control

Design of Low-Power Variable Gain Amplifier

学校读者我要写书评

暂无评论

Journal of Institute of Control, robotics and Systems 2022年第1期28卷 1-5页

作者： Choi, Ye-Ji Ryu, Jee-Youl Department of Smart Robot Convergence and Application Engineering Pukyong National University Korea Republic of Department of Information and Communications Engineering Pukyong National University Korea Republic of

This paper presents a low-power variable gain amplifier (VGA) for the automotive radar. The proposed VGA comprises a gain control stage and an amplifier stage with active inductors. The gain control stage on the circuit is designed to be adjustable in 5 steps from 0 dB to 20 dB. The chip area can be reduced using an active inductor. This circuit also has a lower power dissipation, which reduces slow vibrations. The VGA is fabricated by TSMC 0.13 μm CMOS process. In comparison to conventional research results, the proposed VGA showed a lower power consumption of 17.88 mW, a low noise figure of less than 3.424 dB, and a relatively low active area of 0.034 mm2. © ICROS 2022.

关键词： Variable gain amplifiers

A Study on Robust Fault-tolerant Control for a Low-cost Target Tracking System 21

学校读者我要写书评

暂无评论

A Study on Robust Fault-tolerant Control for a Low-cost Targ...

21st International Conference on Control, Automation and Systems, ICCAS 2021

作者： Huynh, Thinh Tran, Minh-Thien Lee, Dong-Hun Kim, Young-Bok Pukyong National University Department of Smart Robot Convergence and Application Engineering Busan48513 Korea Republic of Pukyong National University Department of Mechanical System Engineering Busan48513 Korea Republic of

ISBN: (纸本)9788993215212

This paper presents a robust control system for a low-cost tracking system. As the controlled apparatus, a 2-axis gimbal is involved in a networked control system and an unreliable gyro sensor is used. Besides, external disturbances heavily affect the system performance. Thus, an unknown input observer is proposed to identify the sensor fault accurately even in the presence of the disturbances and time-varying delay of the networked system. Their influences are estimated subsequently. Then, a fault-tolerant controller is designed, using the observed fault and disturbances. The continuous control law is obtained based on the super-twisting algorithm, backstepping procedure, and integral sliding mode control technique. Finally, a simulation in a worst-case scenario validates the efficiency of the proposed control method. Compared to other control systems, the proposed controller has shown its superiority and reliability. © 2021 ICROS.

关键词： Controllers

Deep learning based resource assignment for wireless networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kim, Minseok Lee, Hoon Lee, Hongju Lee, Inkyu School of Electrical Engineering Korea University Seoul Korea Republic of Department of Smart Robot Convergence and Application Engineering Department of Information and Communications Engineering Pukyong National University Busan48513 Korea Republic of

This paper studies a deep learning approach for binary assignment problems in wireless networks, which identifies binary variables for permutation matrices. This poses challenges in designing a structure of a neural network and its training strategies for generating feasible assignment solutions. To this end, this paper develop a new Sinkhorn neural network which learns a non-convex projection task onto a set of permutation matrices. An unsupervised training algorithm is proposed where the Sinkhorn neural network can be applied to network assignment problems. Numerical results demonstrate the effectiveness of the proposed method in various network scenarios. Copyright © 2021, The Authors. All rights reserved.

关键词： Combinatorial optimization

Deep Learning for Multi-User MIMO Systems: Joint Design of Pilot, Limited Feedback, and Precoding

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jang, Jeonghyeon Lee, Hoon Kim, Il-Min Lee, Inkyu School of Electrical Engineering Korea University Seoul02841 Korea Republic of Department of Smart Robot Convergence and Application Engineering Department of Information and Communications Engineering Pukyong National University Busan48513 Korea Republic of Department of Electrical and Computer Engineering Queen’s University KingstonONK7L 3N6 Canada

In conventional multi-user multiple-input multiple-output (MU-MIMO) systems with frequency division duplexing (FDD), channel acquisition and precoder optimization processes have been designed separately although they are highly coupled. This paper studies an end-to-end design of downlink MU-MIMO systems which include pilot sequences, limited feedback, and precoding. To address this problem, we propose a novel deep learning (DL) framework which jointly optimizes the feedback information generation at users and the precoder design at a base station (BS). Each procedure in the MU-MIMO systems is replaced by intelligently designed multiple deep neural networks (DNN) units. At the BS, a neural network generates pilot sequences and helps the users obtain accurate channel state information. At each user, the channel feedback operation is carried out in a distributed manner by an individual user DNN. Then, another BS DNN collects feedback information from the users and determines the MIMO precoding matrices. A joint training algorithm is proposed to optimize all DNN units in an end-to-end manner. In addition, a training strategy which can avoid retraining for different network sizes for a scalable design is proposed. Numerical results demonstrate the effectiveness of the proposed DL framework compared to classical optimization techniques and other conventional DNN schemes. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

Learning robust beamforming for MISO downlink systems

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kim, Junbeom Lee, Hoon Park, Seok-Hwan The Division of Electronic Engineering Jeonbuk National University Jeonju54896 Korea Republic of The Department of Smart Robot Convergence and Application Engineering The Department of Information and Communications Engineering Pukyong National University Busan48513 Korea Republic of

This paper investigates a learning solution for robust beamforming optimization in downlink multi-user systems. A base station (BS) identifies efficient multi-antenna transmission strategies only with imperfect channel state information (CSI) and its stochastic features. To this end, we propose a robust training algorithm where a deep neural network (DNN), which only accepts estimates and statistical knowledge of the perfect CSI, is optimized to fit to real-world propagation environment. Consequently, the trained DNN can provide efficient robust beamforming solutions based only on imperfect observations of the actual CSI. Numerical results validate the advantages of the proposed learning approach compared to conventional schemes. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

Learning optimal fronthauling and decentralized edge computation in fog radio access networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lee, Hoon Kim, Junbeom Park, Seok-Hwan Department of Smart Robot Convergence and Application Engineering Department of Information and Communications Engineering Pukyong National University Busan48513 Korea Republic of Division of Electronic Engineering Jeonbuk National University Jeonju54896 Korea Republic of

Fog radio access networks (F-RANs), which consist of a cloud and multiple edge nodes (ENs) connected via fronthaul links, have been regarded as promising network architectures. The F-RAN entails a joint optimization of cloud and edge computing as well as fronthaul interactions, which is challenging for traditional optimization techniques. This paper proposes a Cloud-Enabled Cooperation-Inspired Learning (CECIL) framework, a structural deep learning mechanism for handling a generic F-RAN optimization problem. The proposed solution mimics cloud-aided cooperative optimization policies by including centralized computing at the cloud, distributed decision at the ENs, and their uplink-downlink fronthaul interactions. A group of deep neural networks (DNNs) are employed for characterizing computations of the cloud and ENs. The forwardpass of the DNNs is carefully designed such that the impacts of the practical fronthaul links, such as channel noise and signling overheads, can be included in a training step. As a result, operations of the cloud and ENs can be jointly trained in an end-to-end manner, whereas their real-time inferences are carried out in a decentralized manner by means of the fronthaul coordination. To facilitate fronthaul cooperation among multiple ENs, the optimal fronthaul multiple access schemes are designed. Training algorithms robust to practical fronthaul impairments are also presented. Numerical results validate the effectiveness of the proposed approaches. Copyright © 2021, The Authors. All rights reserved.

关键词： Radio access networks

Learning autonomy in management of wireless random networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lee, Hoon Lee, Sang Hyun Quek, Tony Q.S. The Department of Smart Robot Convergence and Application Engineering The Department of Information and Communications Engineering Pukyong National University Busan48513 Korea Republic of The School of Electrical Engineering Korea University Seoul02841 Korea Republic of The Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore487372 Singapore

This paper presents a machine learning strategy that tackles a distributed optimization task in a wireless network with an arbitrary number of randomly interconnected nodes. Individual nodes decide their optimal states with distributed coordination among other nodes through randomly varying backhaul links. This poses a technical challenge in distributed universal optimization policy robust to a random topology of the wireless network, which has not been properly addressed by conventional deep neural networks (DNNs) with rigid structural configurations. We develop a flexible DNN formalism termed distributed message-passing neural network (DMPNN) with forward and backward computations independent of the network topology. A key enabler of this approach is an iterative message-sharing strategy through arbitrarily connected backhaul links. The DMPNN provides a convergent solution for iterative coordination by learning numerous random backhaul interactions. The DMPNN is investigated for various configurations of the power control in wireless networks, and intensive numerical results prove its universality and viability over conventional optimization and DNN approaches. Copyright © 2021, The Authors. All rights reserved.

关键词： Message passing