Velazquez Espitia Victor Miguel, Gonzalez Gonzalez Jose Angel, Mat Omar, Ponce Pedro, Molina G. Arturo
{"title":"Deep Q-learning for Control: Technique and Implementation Considerations on a Physical System: Active Automotive Rear Spoiler Case","authors":"Velazquez Espitia Victor Miguel, Gonzalez Gonzalez Jose Angel, Mat Omar, Ponce Pedro, Molina G. Arturo","doi":"10.1109/ICMA52036.2021.9512669","DOIUrl":"https://doi.org/10.1109/ICMA52036.2021.9512669","url":null,"abstract":"Deep Q-learning is the combination of artificial neural networks advantages (ANNs) with Q-learning. ANNs have expanded the possibilities on a variety of algorithms by enhancing their capabilities and surpassing their limitations. This is the case of reinforcement learning. Nowadays, Deep Q-learning is used in a variety of applications in different fields, including the development of intelligent algorithms to control physical systems. Deep Q-learning has demonstrated the possibility of achieving effective results by solving specific tasks that are highly complex to model through classical approaches. An important drawback is that these models require an elaborated implementation process, and several design decisions must be taken in order to achieve reliable results. Often, developers might find the design process mostly experimental rather than ruled-based. Addressing this problem, the present work describes in detail the implementation process of Deep Q-learning to control a physical system, proposes considerations and analysis parameters for each of the main steps. Demonstrated in the development of the “Active automotive rear spoiler”, the results present a methodology that successfully guides towards a proper implementation of Deep Q-learning. The knowledge of this paper should not be taken as a recipe, but rather as an evaluation reference to equip the reinforcement learning developers with tools for the development of projects.","PeriodicalId":339025,"journal":{"name":"2021 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129378945","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}
{"title":"Energy Conserving Path when Chasing an Intruder by Autonomous Guards","authors":"D. Nussbaum","doi":"10.1109/ICMA52036.2021.9512628","DOIUrl":"https://doi.org/10.1109/ICMA52036.2021.9512628","url":null,"abstract":"The rapid deployment of autonomous mobile guards require the guards to smartly use their energy in order to patrol and chase intruders where applicable. This paper provides solutions and strategies for conserving energy when a guard robot is chasing a mobile robot intruder while having limited information about the intruder's location. In this paper we look at energy conservation of the Moving Target Search with Snapshots problem where a mobile guard Ah is chasing a mobile intruder At in R2. Here, Ah can obtain At's location either by requesting a snapshot or by sensing At if Ah is close enough to At. The objective is to reduce the amount of energy that the guard robot is spending, where the total energy consists of the energy spent to roam around and the energy for taking/receiving a snapshot. In this paper we present 1) Solution for computing the minimum amount of energy required to catch the intruder in the worst case. 2) Algorithmic solutions for conserving energy used by Ah when using a limited number of snapshots computing the path, the locations and the time that Ah should take the snapshots.","PeriodicalId":339025,"journal":{"name":"2021 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129630620","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}
{"title":"Design and Development of a Bladder Volume Determination Device Based on A-mode Ultrasound","authors":"Qiang Gao, Yunfei Gao, Zemin Mao, Chunping Liu, Yu Song, Haobo Zhang, Zixuan Zhang","doi":"10.1109/ICMA52036.2021.9512651","DOIUrl":"https://doi.org/10.1109/ICMA52036.2021.9512651","url":null,"abstract":"Many older adults with Alzheimer's disease and patients with conditions such as spinal nerve injuries have symptoms of urinary incontinence. In order to improve their quality of life, B-mode ultrasound and drainage tubes are often used to measure the urine accumulation in the human bladder. In this paper, an ultrasonic urine system based on A-mode ultrasound is developed for measuring the urine accumulation in the human bladder. The ultrasound urine system contains three parts: the collection device, the mobile terminal, and the upper data processing software. In the collection device, the STM32 microcontroller sends out a pulse signal with a rate of 2.5MHz to excite the ultrasonic transducer through the ultrasonic transmitter circuit. Ultrasonic transducer receives the echo signals by the ultrasonic receiving circuit processing into digital signals, STM32 microcontroller transmits them to the mobile terminal. The mobile terminal transmits the digital signals to the upper data processing software for processing and receives the calculation results for display. We conducted tests on a bladder simulator. We conducted three sets of experiments and measured the transducer to baffle distance of 30mm, 40mm, and 50mm. The accuracy of the system measurements in three sets of experiments were 99.8%, 99.65%, and 99.52%. Experimental results verify the effectiveness of the system.","PeriodicalId":339025,"journal":{"name":"2021 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132902507","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}
Liran Sun, Ming Zhu, Xiao Guo, Jiace Yuan, Huabei Gou
{"title":"Error-constrained Moving Path-Following Control for a Stratospheric Airship","authors":"Liran Sun, Ming Zhu, Xiao Guo, Jiace Yuan, Huabei Gou","doi":"10.1109/ICMA52036.2021.9512644","DOIUrl":"https://doi.org/10.1109/ICMA52036.2021.9512644","url":null,"abstract":"This article investigates the problem of error-constrained moving path following (EMPF) for a stratospheric airship. An airship is required to converge to and follow a time-varying desired geometric path attached to a moving frame under external disturbances without violating the tracking error constraints. A representative application of the EMPF problem is the challenging mission scenario where an airship is tasked to track tropical cyclones or ground moving targets. An EMPF controller is proposed for stratospheric airships with external disturbances based on the adaptive backstepping technique combined with barrier Lyapunov function (BLF) and line-of-sight (LOS) guidance law. Simulation results are provided to illustrate the effectiveness of the proposed EMPF control method.","PeriodicalId":339025,"journal":{"name":"2021 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131726504","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}
{"title":"Modeling and Control Strategy Simulation of Dual Active Bridge DC-DC Converter","authors":"Youjie Ma, H.-T. Wen, X. Zhou, Jie Yin","doi":"10.1109/ICMA52036.2021.9512593","DOIUrl":"https://doi.org/10.1109/ICMA52036.2021.9512593","url":null,"abstract":"In order to improve the dynamic response of isolated dual active bridge (DAB) DC-DC converter under input voltage disturbance and load disturbance, in this paper, an Active Disturbance Rejection Virtual Power Control (ADR-VPC) strategy is proposed with direct power control. First the small signal model of DAB converter is established and the design process of ADR-VPC controller is deduced in detail. Finally, the control simulation model of DAB converter is built in Matlab & Simulink simulation software, and the simulation is compared with the traditional DPC control strategy. The simulation results show that the system can obtain better dynamic response and keep the output voltage basically unchanged when the input voltage and load change.","PeriodicalId":339025,"journal":{"name":"2021 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126896872","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}
{"title":"Classification and detection method of Blood lancet based on VGG16 network","authors":"Feng Zhao, Baofeng Zhang, Zhili Zhang, Xinghui Zhang, Chunyu Wei","doi":"10.1109/ICMA52036.2021.9512686","DOIUrl":"https://doi.org/10.1109/ICMA52036.2021.9512686","url":null,"abstract":"Detection method based on convolutional neural network aims to classify and detect blood lancet after production. The Canny detection algorithm is used to multi-target detection on blood lancet images. The Canny algorithm extracts the blood lancet target, expands the blood lancet data set through image augmentation technology, and solves sample imbalance. The pre-trained VGG16 model is used for blood lancet classification training and fine-tuning of parameters, and the adjusted network model is used for lancet classification and detection. The comparative experiments of the VGG16 network and the two classification networks of GoogLeNet and ResNet show that the average recognition rate of the VGG16 model for blood lancet classification reaches 98.12%, and the classification and detection ability is better than the comparison algorithm. It proves that the network can complete the classification and recognition of blood lancet, and provide technical support for the intelligent classification of blood lancet after production.","PeriodicalId":339025,"journal":{"name":"2021 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123374042","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}
{"title":"Evaluation of a Clamping Mechanism for Vascular Interventional Surgery Robotic System","authors":"Chaochao Shi, Shuxiang Guo","doi":"10.1109/ICMA52036.2021.9512694","DOIUrl":"https://doi.org/10.1109/ICMA52036.2021.9512694","url":null,"abstract":"At present, the vascular interventional surgery has attracted more attention. Because it has the advantages of smaller trauma, lower pain, and quicker recovery after the operation. As for the design of the clamping mechanism, fast and lossless clamping of the catheter has always been a hot and difficult point in the current research. In this paper, a novel slave manipulator is introduced (contains coordinate system). It simulates the twisting of human fingers for the catheter during the actual vascular interventional surgery. Moreover, we evaluated its clamping form. Simulation results show that: From the angle of total deformation, strain, and stress, it is analyzed that there is no damage to the catheter; From the point of view of the clamping force analysis, it is obtained that the clamping force is enough to guarantee the forward and backward of the catheter; From the perspective of conflict protection, the size of the clamping force can be changed by adjusting the clamping depth. In this way, the tip of the catheter can be avoided puncturing the vessel wall, thus increasing the actual clinical safety performance.","PeriodicalId":339025,"journal":{"name":"2021 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126041731","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}
Zhe Wang, Yixiang Liu, Qing Bi, Bin Yang, Rui Song
{"title":"A Bio-Inspired Quadruped Robot with Foldable Torso Capable of Omnidirectional Motion","authors":"Zhe Wang, Yixiang Liu, Qing Bi, Bin Yang, Rui Song","doi":"10.1109/ICMA52036.2021.9512600","DOIUrl":"https://doi.org/10.1109/ICMA52036.2021.9512600","url":null,"abstract":"Many quadrupeds have a flexible torso and can achieve pivot steering, which makes them have good flexibility and mobility. But the torso is usually simplified to a rigid body for most quadruped robots. This paper proposes a novel bioinspired quadruped robot with foldable torso that is capable of omnidirectional motion. First of all, a flodable torso with a fully symmetrical mechanism is designed to realize variable configurations of the torso. The obstacle surmounting ability of the quadruped robot can be improved by changing the distance between legs and the height of the torso from the ground. Then, a parallel actuated leg capable of omnidirectional swing is designed, enabling the quadruped robot to realize omnidirectional motion including in-situ turning and backward walking. The foldable torso and omnidirectional mobility allow the quadruped robot to be more adaptable to complex environment. Effectiveness of the proposed quadruped robot is verified by simulations and experiments on the prototype.","PeriodicalId":339025,"journal":{"name":"2021 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"30 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114103768","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}
Zhiheng Zheng, Jirong Xie, Tao Su, Xinguang Li, Yu Ni
{"title":"A Novel Remote Control Method Oriented to Underwater Maninulators","authors":"Zhiheng Zheng, Jirong Xie, Tao Su, Xinguang Li, Yu Ni","doi":"10.1109/ICMA52036.2021.9512585","DOIUrl":"https://doi.org/10.1109/ICMA52036.2021.9512585","url":null,"abstract":"In order to pursue the objective of intuitive operation, a new remote control method oriented to multi-DOF underwater manipulators based on vision is presented in this paper. A rod with distinct color balls fixed at both ends is adopted as the remote control device in this technique. The operator can hold the rod and adjust its position and attitude in a certain area to control the underwater manipulator. Positioning system composed of multiple cameras are deployed around the operating space to detect and get the position of the color balls. Then the position of one ball and the relative position of two balls could be used to control the slave arm. Experiments are carried out in order to investigate the performance of the approach and the feasibility of the method is verified.","PeriodicalId":339025,"journal":{"name":"2021 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116114210","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}
{"title":"Structural Synthesis of Nested Hyper-redundant Mechanisms Inspired by the Mackerel Fishes","authors":"Weiwei Chen, Hongzhou Jiang","doi":"10.1109/ICMA52036.2021.9512629","DOIUrl":"https://doi.org/10.1109/ICMA52036.2021.9512629","url":null,"abstract":"The tradition structure of hyper-redundant mechanisms is that every module connected to each other in series sequence. But the nested hyper-redundant mechanisms inspired by the mackerel fishes do not follow this principle. The modules of the nested system vary from each other. Thus, a structural synthesis of this complex system is needed to identify non-isomorphic mechanisms. Using the code-based approach, this article comes up with a simplified characteristic code for different kind of nested hyper-redundant mechanisms.","PeriodicalId":339025,"journal":{"name":"2021 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"5 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120969835","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}