2020 6th International Conference on Control, Automation and Robotics (ICCAR)最新文献_第8页

Heterogeneous Siamese Tracking System Based on PYNQ Framework 基于PYNQ框架的异构连体跟踪系统

2020 6th International Conference on Control, Automation and Robotics (ICCAR) Pub Date : 2020-04-01 DOI: 10.1109/ICCAR49639.2020.9108096

Zhoujuan Cui, Junshe An

{"title":"Heterogeneous Siamese Tracking System Based on PYNQ Framework","authors":"Zhoujuan Cui, Junshe An","doi":"10.1109/ICCAR49639.2020.9108096","DOIUrl":"https://doi.org/10.1109/ICCAR49639.2020.9108096","url":null,"abstract":"Deep neural network models have been gradually applied to the field of visual tracking due to their excellent feature expression capabilities. However, the model is large, which is expressed in the calculation of model parameters. As a result, the implementation platforms of visual tracking algorithm are usually limited by computing power, power consumption, portability, etc. In this paper, we propose a Siamese network tracking scheme based on PYNQ framework, which is deployed on ZYNQ platform. By optimizing the calculation process, Siamese Network accelerated IP core and Region Proposal Network accelerated IP core are designed. The double buffer structure is adopted to effectively call different feature map calculations and reduce off-chip memory access. Python is used to call the accelerated IP core at the top level as the hardware coprocessor to realize the data interaction from the bottom level to the top level and update the system running results asynchronously in Jupyter notebook. We achieve an average 36.7FPS on Xilinx ZCU104 platform, which illustrates that our method has the important practical benefit of allowing lightweight architectures to achieve good performance at high framerates.","PeriodicalId":412255,"journal":{"name":"2020 6th International Conference on Control, Automation and Robotics (ICCAR)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133607522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Adaptive Fuzzy Terminal Sliding Mode Synchronization of Uncertain Newton-Leipnik Chaotic System 不确定Newton-Leipnik混沌系统的自适应模糊终端滑模同步

2020 6th International Conference on Control, Automation and Robotics (ICCAR) Pub Date : 2020-04-01 DOI: 10.1109/ICCAR49639.2020.9107996

Xiaomeng Cui, Xiaoshan Zhao, Yongfeng Guo, Xiang Li, Pengyu Hou

引用次数: 2

Computatational Assessment of Protective Capabilities of Vehicle Floor, Seat and Occupant Response under Shock Loads 冲击荷载作用下汽车地板、座椅和乘员响应防护能力的计算评估

2020 6th International Conference on Control, Automation and Robotics (ICCAR) Pub Date : 2020-04-01 DOI: 10.1109/ICCAR49639.2020.9108009

Basa Jsk kalyan Subrahmanyam, V. Balasubramanian, Lakshmana Rao

引用次数: 0

Kalman Filter Embedded MPC for Stochastic Systems 随机系统的嵌入MPC卡尔曼滤波

2020 6th International Conference on Control, Automation and Robotics (ICCAR) Pub Date : 2020-04-01 DOI: 10.1109/ICCAR49639.2020.9108027

K. Chacko, S. Janardhanan, I. Kar

引用次数: 0

Development of a Neural Network Based PV Power Output Prediction Application Using Reduced Features and Tansig Activation Function 利用约简特征和Tansig激活函数开发基于神经网络的光伏输出预测应用

2020 6th International Conference on Control, Automation and Robotics (ICCAR) Pub Date : 2020-04-01 DOI: 10.1109/ICCAR49639.2020.9108101

Jordan N. Velasco, C. Ostia

引用次数: 5

Range Measurements Based UAV Navigation for Intercepting Ground Targets 基于距离测量的无人机导航拦截地面目标

2020 6th International Conference on Control, Automation and Robotics (ICCAR) Pub Date : 2020-04-01 DOI: 10.1109/ICCAR49639.2020.9108013

Manaram Gnanasekera, A. Savkin, J. Katupitiya

引用次数: 1

Sample-Based Motion Planning for Multi-Robot Systems 基于样本的多机器人系统运动规划

2020 6th International Conference on Control, Automation and Robotics (ICCAR) Pub Date : 2020-04-01 DOI: 10.1109/ICCAR49639.2020.9108020

M. Muradi, R. Wanka

引用次数: 4

Study on Stress Characteristics of Plantar Walking and Rehabilitation Strategy 足底行走的应力特征及康复策略研究

2020 6th International Conference on Control, Automation and Robotics (ICCAR) Pub Date : 2020-04-01 DOI: 10.1109/ICCAR49639.2020.9108097

Zhao Lingyan, Zhang Shi, Yu Lingtao, Guan Zhiguang

{"title":"Study on Stress Characteristics of Plantar Walking and Rehabilitation Strategy","authors":"Zhao Lingyan, Zhang Shi, Yu Lingtao, Guan Zhiguang","doi":"10.1109/ICCAR49639.2020.9108097","DOIUrl":"https://doi.org/10.1109/ICCAR49639.2020.9108097","url":null,"abstract":"With the rapid development of science and technology, plantar pressure analysis provides an important reference for medical examination, sports training and exoskeleton robot developing. In order to study the characteristics of plantar stress and its effect on the change of velocity during flat walking, this paper collected data of plantar pressure of 20 healthy young men during flat walking and extracted characteristic values for analysis. The results showed that the stress of human body during walking on the ground was concentrated on the front foot and the back foot, and the stress of the front foot increased significantly with the increase of walking speed. Because of the arch of the foot, the change of the arch area and the bone area of the foot resulting from the changing walking speed is not obvious. And thus the plantar is well protected. During the single support phase, the support leg adjusts to maintain the balance of the body so that the friction force is less affected by the speed. Combined with the analysis, this paper provides a simple rehabilitation training strategy to prevent secondary injury to the injured part of the foot in the process of rehabilitation. The above conclusions have certain scientific significance in the fields of rehabilitation medicine and sports science.","PeriodicalId":412255,"journal":{"name":"2020 6th International Conference on Control, Automation and Robotics (ICCAR)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127118404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Decentralized Communication-less Multi-Agent Task Assignment with Cooperative Monte-Carlo Tree Search 基于蒙特卡罗树搜索的分散无通信多智能体任务分配

2020 6th International Conference on Control, Automation and Robotics (ICCAR) Pub Date : 2020-04-01 DOI: 10.1109/ICCAR49639.2020.9108073

Mohammadreza Daneshvaramoli, M. Kiarostami, Saleh Khalaj Monfared, Helia Karisani, Keivan Dehghannayeri, Dara Rahmati, S. Gorgin

{"title":"Decentralized Communication-less Multi-Agent Task Assignment with Cooperative Monte-Carlo Tree Search","authors":"Mohammadreza Daneshvaramoli, M. Kiarostami, Saleh Khalaj Monfared, Helia Karisani, Keivan Dehghannayeri, Dara Rahmati, S. Gorgin","doi":"10.1109/ICCAR49639.2020.9108073","DOIUrl":"https://doi.org/10.1109/ICCAR49639.2020.9108073","url":null,"abstract":"Cooperative task assignment is an important subject in multi-agent systems with a wide range of applications. These systems are usually designed with massive communication among the agents to minimize the error in pursuit of the general goal of the entire system. The problem is often formulated as finding the best routing configuration to capture $N_{A}$ goals by $N_{A}$ agents in an $Ntimes N$ 2-Dim grid with no collision. In this work, we propose an approach for Decentralized Cooperative Communication-less Multi-Agent Task Assignment employing Monte-Carlo Tree Search (MCTS). We design a Multi-Agent MCTS with a high success rate where each agent is moving toward the collective goal effectively by knowing the current location of other agents, with no additional communication overhead. We show that by employing separated MCTS on each agent armed with a collective reward value, the total accuracy could be maximized compared to the solutions where a single MCTS executed for all the agents. As an evaluation and comparison, in the proposed MA-MCTS, agents accomplish a high success-rate by capturing all 20 random positioned goals, in a 20 by 20 2-D grid in 9.9s process-time.","PeriodicalId":412255,"journal":{"name":"2020 6th International Conference on Control, Automation and Robotics (ICCAR)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126355644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Dual-Arm Upper Limb Rehabilitation Robot: Mechanism Design and Preliminary Experiments 双臂上肢康复机器人:机构设计与初步实验

2020 6th International Conference on Control, Automation and Robotics (ICCAR) Pub Date : 2020-04-01 DOI: 10.1109/ICCAR49639.2020.9108019

Siqi Cai, Weifeng Wu, Longhan Xie

{"title":"Dual-Arm Upper Limb Rehabilitation Robot: Mechanism Design and Preliminary Experiments","authors":"Siqi Cai, Weifeng Wu, Longhan Xie","doi":"10.1109/ICCAR49639.2020.9108019","DOIUrl":"https://doi.org/10.1109/ICCAR49639.2020.9108019","url":null,"abstract":"Stroke affects thousands of people worldwide and nearly half of stroke survivors suffer from upper limb deficits affecting their daily activities. Task-oriented, repetitive and intensive physiotherapy can enhance upper limb rehabilitation for stroke patients. Rehabilitation robots, with the advantages of delivering high-dosage and high-intensity training over long time, have gained high popularity in physiotherapy. In this work, the Dual-Arm Rehabilitation Robot (DARR), an end-effector system with collaborative manipulators assisting the upper and lower arms of a stroke patient respectively, was proposed. Each manipulator of the DARR, with three active degrees of freedom (DOF) for positioning and three passive DOF for orientation, can provide rehabilitation training to the affected arm in a three-dimensional workspace and permit stroke patients to freely orient his/her hand as needed to grasp an object. The DARR prototype was built and conducted experiments to validate its feasibility and effectiveness, including mechanical structure and control system. Both simulation and experimental results showed that the DARR could satisfy the demands of upper limb rehabilitation for stroke patients.","PeriodicalId":412255,"journal":{"name":"2020 6th International Conference on Control, Automation and Robotics (ICCAR)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126393611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0