{"title":"Optimal routing control of a construction machine by deep reinforcement learning","authors":"Zeyuan Sun, Masayuki Nakatani, Y. Uchimura","doi":"10.1109/AMC.2019.8371085","DOIUrl":"https://doi.org/10.1109/AMC.2019.8371085","url":null,"abstract":"Deep reinforcement learning algorithms are rapidly growing, and expected to be applied to many industrial fields. In this paper, we proposed a method that combines a deep Q-network with batch normalization to generate an optimal route for a grading machine. The goal is to achieve autonomous operation of the grading machine. For the learning platform, a grading simulator was developed to emulate the grading work. The proposed method was evaluated with the grading simulator, and showed better route searching performance results than the conventional method.","PeriodicalId":377008,"journal":{"name":"2018 IEEE 15th International Workshop on Advanced Motion Control (AMC)","volume":"166 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131734629","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":"Time slotted channel hopping scheduling based on the energy consumption of wireless sensor networks","authors":"T. Matsui, H. Nishi","doi":"10.1109/AMC.2019.8371162","DOIUrl":"https://doi.org/10.1109/AMC.2019.8371162","url":null,"abstract":"Wireless Sensor Nnetworks (WSNs) are becoming increasingly widespread owing to the introduction of the Internet of Things (IoT) and the networks' comparatively low cost and usability. WSNs are usually battery-powered, owing to their low power consumption, which however limits their computational performance. The lifetime of a WSN strongly depends on its communication-related power consumption. Time Slotted Channel Hopping (TSCH) solves the problem of power consumption by featuring both time-division and frequency- division multiplexing in the system's Media Access Control (MAC) layer. In this paper, Pruning-based Coloring Scheduling (PRCOS) is proposed, which is an algorithm for TSCH scheduling that accounts for the power consumption to extend the system's lifetime. Using mathematical analysis, we show that the proposed algorithm decreases the transfer time and energy consumption by factors of 0.43 and 0.57, respectively, compared with existing algorithms.","PeriodicalId":377008,"journal":{"name":"2018 IEEE 15th International Workshop on Advanced Motion Control (AMC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124600486","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":"Distributed thermal conductance control for sensing and rendering thermal sensation on the palm","authors":"Yukiko Osawa, S. Katsura","doi":"10.1109/AMC.2019.8371112","DOIUrl":"https://doi.org/10.1109/AMC.2019.8371112","url":null,"abstract":"Sensing and rendering thermal sensation is important to the multimedia, communication, and medical field. For example, human health care system for monitoring and treating a body temperature distribution can be estimated by using the technique. In this research, the thermal interface using multiple heat sources for rendering thermal sensation is treated. In order to control a lot of heat sources in the thermal interface, the distributed control method is required to render spatial continuous sensation. The paper defined \"Distributed thermal conductance\" that the relationship between heat sources, and heat flow on the palm can be freely changed depending on the connectivity between heat sources. The proposed method can be controlled the desired temperature distribution on the surface of the interface.","PeriodicalId":377008,"journal":{"name":"2018 IEEE 15th International Workshop on Advanced Motion Control (AMC)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126870463","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":"Implementation of schedule management mechanism for S-TDMA switch","authors":"Shunpei Koyasu, T. Yakoh","doi":"10.1109/AMC.2019.8371157","DOIUrl":"https://doi.org/10.1109/AMC.2019.8371157","url":null,"abstract":"Recently, because of the development of industrial systems and network systems, the demands of telehaptics and telesurgery become higher. To realize these systems, a real-time communication which can guarantee deterministic delays and low jitters in a network is required. One of the real-time protocol is Synchronous-Time Division Multiple Access (S-TDMA). S-TDMA makes it possible to coexist of real-time and conventional TCP/IP communications over a multiple-hop network using Ethernet. In previous works, the schedule of real-time combinations was fixed. So this research introduces management mechanism of communication schedules by using the technology of Software Defined Networking (SDN). SDN is a notion to realize a dynamic and centralized control of network configuration by using one controller which can manage all equipments in the network. In this paper, the design and implementation of management mechanism of S-TDMA switches are discussed and performance of the implemented switches is verified. The experiment results confirm that it is possible to change time slot allocation, communication mode and paths dynamically. Results also show that the management system can control multiple switches in the network.","PeriodicalId":377008,"journal":{"name":"2018 IEEE 15th International Workshop on Advanced Motion Control (AMC)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134446571","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":"Kernel-based regression of non-causal systems for inverse model feedforward estimation","authors":"L. Blanken, Ids van den Meijdenberg, T. Oomen","doi":"10.1109/AMC.2019.8371137","DOIUrl":"https://doi.org/10.1109/AMC.2019.8371137","url":null,"abstract":"Inversion-based feedforward control enables high performance for industrial motion systems. To this end, accurate knowledge of the inverse system is required, and non-causal control actions must be enabled. The aim of this paper is to accurately identify non-causal inverse models in view of high feedforward control performance. The developed method employs kernel-based regularization to minimize the mean squared error of the estimate. The performance benefits of the presented approach are demonstrated on an industrial printing system, including non-causal feedforward control actions.","PeriodicalId":377008,"journal":{"name":"2018 IEEE 15th International Workshop on Advanced Motion Control (AMC)","volume":"409 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122803789","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":"An approach to power assist hand exoskeleton for patients with paralysis","authors":"Hidekatsu Uchida, T. Murakami","doi":"10.1109/AMC.2019.8371172","DOIUrl":"https://doi.org/10.1109/AMC.2019.8371172","url":null,"abstract":"The aim of this paper is to propose a novel robotic hand exoskeleton which can assist disabled people with grasping objects. Existing exoskeletons cannot measure force during contact motion, and this makes it difficult to achieve accurate grasp assistance. In the proposed system the exoskeletal finger is attached to the index and middle fingers, and the robotic finger is place on the palm side, which functions as a substitute of a thumb. The upper exoskeletal finger exerts assistive force on operator's fingers, and the lower robotic finger works as a force sensor by the use of Reaction Torque Observer. Thus, human grasping force is measured during grasping, and the environmental and human forces are estimated from measured torque. The proposed system realizes power assist control without using additive sensors like force sensors or EMG sensors. The effectiveness of the proposed method is demonstrated through simulation and experiment.","PeriodicalId":377008,"journal":{"name":"2018 IEEE 15th International Workshop on Advanced Motion Control (AMC)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126609164","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":"An EEG-based robot arm control to express human emotions","authors":"Mikito Ogino, Y. Mitsukura","doi":"10.1109/AMC.2019.8371111","DOIUrl":"https://doi.org/10.1109/AMC.2019.8371111","url":null,"abstract":"Prosthetic limbs are designed to move naturally like human limbs. To reduce the feeling of abnormality when moving prosthetic limbs, previous studies have altered the appearance of robotic limbs along with the speed of the motors inside these limbs. The use of the wearer's emotions to control prosthetic limbs would allow robotic arms and legs to move more naturally. Recently, electroencephalograms (EEGs) have been used to estimate human emotions. In this study, we developed an emotion analyzer and applied it in a robotic arm system that changes its movement based on the user's emotions. In the proposed system, EEG data are measured by a simplified EEG headset and transferred to an iPad. An iPad application then transforms the signal to a value of \"wakuwaku\" feeling using the band-pass filtering, fast Fourier transform, and support vector machine methods. The accuracy of the algorithm estimating the wakuwaku feeling was 75.10%, and the robot arm moved accurately based on the user emotion estimated from the EEG data. Our findings are expected to lead to a new field of study focused on controlling robot arms using human emotions.","PeriodicalId":377008,"journal":{"name":"2018 IEEE 15th International Workshop on Advanced Motion Control (AMC)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126892897","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":"Quantification of pain degree by frequency features of single-chanelled EEG","authors":"Junichiro Kagita, Y. Mitsukura","doi":"10.1109/AMC.2019.8371118","DOIUrl":"https://doi.org/10.1109/AMC.2019.8371118","url":null,"abstract":"The final aim of this paper is to classify pain degree by only using Electroencephalogram (EEG) measured with single-channel. In clinical care, pain degree is needed for choosing and evaluating treatments, and it is important for clinicians to quantify pain degree as objectively as possible. Pain rating scales such as the Visual Analogue Scales (VAS) are usually used to quantify pain degree, which is only capable of subjective values due to self-report. From that, a method to quantify pain degree objectively has great importance. In this paper, we propose the possibility of quantifying pain degree by only using EEG measured with single-channel. 28 Subjects' EEG is measured while in 2 states; pain-free (VAS score of 0) and pain (VAS score of 3-4). By extracting frequency features from the measured EEG, and classifying using Support Vector Machine (SVM), the subjects in 2 states were classified with the accuracy of 100%. The results show reliability and validity of classifying pain degree using EEG measured with single-channel.","PeriodicalId":377008,"journal":{"name":"2018 IEEE 15th International Workshop on Advanced Motion Control (AMC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132965977","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 performance tradeoffs in MIMO disturbance feedforward control","authors":"M. A. Beijen, Bo Cong, M. Heertjes","doi":"10.1109/AMC.2019.8371134","DOIUrl":"https://doi.org/10.1109/AMC.2019.8371134","url":null,"abstract":"Disturbance feedforward control (DFC) can be used to reject external disturbances that are a priori unknown. This paper addresses the design and performance tradeoffs due to the causal nature of DFC in Multi-Input Multi-Output (MIMO) systems. Performance tradeoffs in optimization over both frequencies and the disturbance directions are expressed in terms of MIMO feedforward sensitivity functions. Design interpretations and disturbance decorrelation are presented to optimize the disturbance rejection properties for systems subject to these fundamental limitations. Simulation studies of a 2- DOF motion stage are included, showing significant performance benefits using disturbance decorrelation.","PeriodicalId":377008,"journal":{"name":"2018 IEEE 15th International Workshop on Advanced Motion Control (AMC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126443626","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":"Non-verbal communication-based emotion incitation robot","authors":"S. Shimizu, Kai Shimada, Rei Murakami","doi":"10.1109/AMC.2019.8371114","DOIUrl":"https://doi.org/10.1109/AMC.2019.8371114","url":null,"abstract":"This paper introduces a robot system by which emotions are incited based on non-verbal communication, i.e., a series of motion such as eye movement. The designed and developed robot system comprises mainly three parts of an eyeball robot, an eyeball robot controller, and an emotion recognizer one based on image processing technique. The system configuration is described paying attention to \"emotion\" as a keyword to communicate between the robot and the human. The proposed system implements non-verbal communication by humorous eye movements from the robot to the human and emotion expression recognition by image processing from the human to the robot, respectively. In this paper, the authors focus on smile as a target of the emotion recognizer. We implemented some smile incitation experiments and their results were discussed.","PeriodicalId":377008,"journal":{"name":"2018 IEEE 15th International Workshop on Advanced Motion Control (AMC)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134246304","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}