The conventional teaching/playback scheme is widely used for robot programming due to its reliablity and general versatility. However, it is applicable only when task conditions does not vary. In this paper, we study a method of robot programming with view-based image processing: view-based teaching/playback. It can adapt to changes of task conditions such as variations in initial pose of the object, without losing the general versatility. The method is composed of two parts: teaching phase and playback phase. In the teaching phase, a human operator commands a robot to perform a manipulation task as a demonstration. Scene images and corresponding robot motions are recorded in the demonstration. A mapping from the images to the robot motions is obtained as a neural network by learning from the demonstration data. In the playback phase, a robot motion is generated by the mapping. We applied this view-based teaching/playback to pushing tasks by an industrial robot. After multiple teaching demonstrations, pushing an object to a goal position was successfully achieved from some initial poses that are not identical to those in the demonstrations. This indicates that our view-based teaching/playback can deal with a certain range of variations in initial pose of the object without object models or camera calibrations.
{"title":"View-based teaching/playback for manipulation by industrial robots","authors":"Yukihiro Moriyama, Y. Maeda","doi":"10.1299/KIKAIC.79.3597","DOIUrl":"https://doi.org/10.1299/KIKAIC.79.3597","url":null,"abstract":"The conventional teaching/playback scheme is widely used for robot programming due to its reliablity and general versatility. However, it is applicable only when task conditions does not vary. In this paper, we study a method of robot programming with view-based image processing: view-based teaching/playback. It can adapt to changes of task conditions such as variations in initial pose of the object, without losing the general versatility. The method is composed of two parts: teaching phase and playback phase. In the teaching phase, a human operator commands a robot to perform a manipulation task as a demonstration. Scene images and corresponding robot motions are recorded in the demonstration. A mapping from the images to the robot motions is obtained as a neural network by learning from the demonstration data. In the playback phase, a robot motion is generated by the mapping. We applied this view-based teaching/playback to pushing tasks by an industrial robot. After multiple teaching demonstrations, pushing an object to a goal position was successfully achieved from some initial poses that are not identical to those in the demonstrations. This indicates that our view-based teaching/playback can deal with a certain range of variations in initial pose of the object without object models or camera calibrations.","PeriodicalId":337733,"journal":{"name":"Transactions of the Japan Society of Mechanical Engineers. C","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126110528","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}
Toru Fujimori, Shigeaki Maruyama, K. Yamazaki, T. Aoyama
Following to the previous paper reporting the motion control compensation for machine tool by 2 dimensional scale system, we hereby propose the Magnetic principle special scale for motion control compensation of machine tool. The authors investigated the compensation of the collateral movement orthogonal to the principle direction, which will affect the accuracy of the machine, by adding the orthogonal, 2-directional, short range measurement. The authors expected the improvement of compensation accuracy by continuously monitoring the relative motions between the movement of the bed and machine components with respect to the principle direction as well as to the direction of collateral movement, because the monitoring prompts re-acquisition of compensation data when the deviation from the initial compensation data becomes significant, enabling additional compensation for the dynamic motion error caused by cutting force etc. Firstly, this paper estimates the amount of motion error due to cutting force, the weight and acceleration force of the bed, using middle sized machine tool model. Then the paper presents the approximate required performance of the multi DOF scale. Finally, the paper reports the basic and elemental performance of magnetic multi DOF scales for motion error compensation, by prototyping the rotary scales.
{"title":"A study on multi DOF magnetic scale for motion control compensation of machine tool","authors":"Toru Fujimori, Shigeaki Maruyama, K. Yamazaki, T. Aoyama","doi":"10.1299/KIKAIC.79.3993","DOIUrl":"https://doi.org/10.1299/KIKAIC.79.3993","url":null,"abstract":"Following to the previous paper reporting the motion control compensation for machine tool by 2 dimensional scale system, we hereby propose the Magnetic principle special scale for motion control compensation of machine tool. The authors investigated the compensation of the collateral movement orthogonal to the principle direction, which will affect the accuracy of the machine, by adding the orthogonal, 2-directional, short range measurement. The authors expected the improvement of compensation accuracy by continuously monitoring the relative motions between the movement of the bed and machine components with respect to the principle direction as well as to the direction of collateral movement, because the monitoring prompts re-acquisition of compensation data when the deviation from the initial compensation data becomes significant, enabling additional compensation for the dynamic motion error caused by cutting force etc. Firstly, this paper estimates the amount of motion error due to cutting force, the weight and acceleration force of the bed, using middle sized machine tool model. Then the paper presents the approximate required performance of the multi DOF scale. Finally, the paper reports the basic and elemental performance of magnetic multi DOF scales for motion error compensation, by prototyping the rotary scales.","PeriodicalId":337733,"journal":{"name":"Transactions of the Japan Society of Mechanical Engineers. C","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125253033","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}
Mechanoluminescence (ML) intensity is proportional to magnitude of load and loading rate in elastic region. However, ML intensity is affected by initial excitation level, concentration of ML materials and so on, resulting in difficulties to evaluate the stress quantitatively. Controlling the initial conditions for the quantitative measurement requires a long stand-by time. In this study, we evaluated relations between increasing/decreasing stress and the response characteristics of ML. The transient ML intensity was measured by a photomultiplier tube. The rise time of ML, τup, and decay time, τdown, were proportional to maximum load and inversely proportional to loading rate. Furthermore, τup and τdown were not affected by initial excitation level, concentration of ML materials. Investigating responses to the cyclic load, τ was not affected by cycle stress. In order to confirm whether external force affects the value of τ, same loading time and various magnitude of external force were added to the sample and calculated τ. Results show τup was affected only by loading time. On the other hand, τdown was affected by loading time and rate of time variation of strain energy. Appling to two-dimensional measurement, qualitatively correct results were obtained in each area. The above results indicate τ would be a useful parameter to visualize stress field in elastic body arbitrary and sequentially.
{"title":"Evaluation method of loading condition based on the time response of Mechanoluminescence","authors":"K. Ishii, S. Someya, Masayuki Saeki, T. Munakata","doi":"10.1299/KIKAIC.79.3721","DOIUrl":"https://doi.org/10.1299/KIKAIC.79.3721","url":null,"abstract":"Mechanoluminescence (ML) intensity is proportional to magnitude of load and loading rate in elastic region. However, ML intensity is affected by initial excitation level, concentration of ML materials and so on, resulting in difficulties to evaluate the stress quantitatively. Controlling the initial conditions for the quantitative measurement requires a long stand-by time. In this study, we evaluated relations between increasing/decreasing stress and the response characteristics of ML. The transient ML intensity was measured by a photomultiplier tube. The rise time of ML, τup, and decay time, τdown, were proportional to maximum load and inversely proportional to loading rate. Furthermore, τup and τdown were not affected by initial excitation level, concentration of ML materials. Investigating responses to the cyclic load, τ was not affected by cycle stress. In order to confirm whether external force affects the value of τ, same loading time and various magnitude of external force were added to the sample and calculated τ. Results show τup was affected only by loading time. On the other hand, τdown was affected by loading time and rate of time variation of strain energy. Appling to two-dimensional measurement, qualitatively correct results were obtained in each area. The above results indicate τ would be a useful parameter to visualize stress field in elastic body arbitrary and sequentially.","PeriodicalId":337733,"journal":{"name":"Transactions of the Japan Society of Mechanical Engineers. C","volume":"291 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116306195","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}
In this paper, we propose a new method that uses multiple SOMs for estimating values lacking in data analysis. Recently, development of information technology grows the importance of data analysis. In actual data, however, some values will be sometimes missing, and then dealing with such insufficient data has become one of the important subjects in data analysis. Estimating and completing the empty values are required to applying various data analysis techniques. Such an estimation method is also applicable to data prediction problems. In the former methods that use SOM, many empty values would have caused the lack of data for learning process. Our system can achieve effective learning by using multiple SOMs even for data that includes many missing values. Moreover, the system is still available for nonlinear data because of using SOMs. We performed some numerical simulation using the proposed and other methods. By the simulation results, we showed the advantages of our method over some traditional techniques including a technique that uses single SOM.
{"title":"An estimating method for missing data by using multiple self-organizing maps","authors":"Y. Kikuchi, N. Okada, Y. Tsuji, K. Kiguchi","doi":"10.1299/KIKAIC.79.3465","DOIUrl":"https://doi.org/10.1299/KIKAIC.79.3465","url":null,"abstract":"In this paper, we propose a new method that uses multiple SOMs for estimating values lacking in data analysis. Recently, development of information technology grows the importance of data analysis. In actual data, however, some values will be sometimes missing, and then dealing with such insufficient data has become one of the important subjects in data analysis. Estimating and completing the empty values are required to applying various data analysis techniques. Such an estimation method is also applicable to data prediction problems. In the former methods that use SOM, many empty values would have caused the lack of data for learning process. Our system can achieve effective learning by using multiple SOMs even for data that includes many missing values. Moreover, the system is still available for nonlinear data because of using SOMs. We performed some numerical simulation using the proposed and other methods. By the simulation results, we showed the advantages of our method over some traditional techniques including a technique that uses single SOM.","PeriodicalId":337733,"journal":{"name":"Transactions of the Japan Society of Mechanical Engineers. C","volume":"132 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131404883","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}
Y. Maruno, A. T. Zengin, Hiroshi Okajima, N. Matsunaga, N. Nakamura
Electric-powered personal vehicles have been used as a convenient transportation device. A front-drive-type personal vehicle STAVi, that is easy for elderly but also disabled persons, to climb on from a bed has been focused on. However, front-drive-type personal vehicles are difficult to operate because their over-steering characteristic is strong owing to free casters. If the vehicle can be driven by an easy joy-stick operation, it will be a comfortable function for all users. In previous studies, we proposed a simple modeling error compensator which achieves a desired driving characteristics using a simple reference model, and the effectiveness was evaluated by simulations. In this paper, we propose a control system for STAVi using a modeling error compensator with a non-linear reference model to realize a comfortable under-steering characteristics. At first, the advantage of proposed controller is summarized. The STAVi’s over-steering characteristic is modified to be under-steering one by proposed controller. As an experimental result, the additional assistance is necessary for a beginner. The phase-lead compensator for beginners is designed to adjust the maneuverability depending on the skill level. The maneuverability is evaluated by driving experiments on the slope.
{"title":"Maneuverability improvement of front-drive personal welfare vehicle STAVi using a model error compensator","authors":"Y. Maruno, A. T. Zengin, Hiroshi Okajima, N. Matsunaga, N. Nakamura","doi":"10.1299/KIKAIC.79.4721","DOIUrl":"https://doi.org/10.1299/KIKAIC.79.4721","url":null,"abstract":"Electric-powered personal vehicles have been used as a convenient transportation device. A front-drive-type personal vehicle STAVi, that is easy for elderly but also disabled persons, to climb on from a bed has been focused on. However, front-drive-type personal vehicles are difficult to operate because their over-steering characteristic is strong owing to free casters. If the vehicle can be driven by an easy joy-stick operation, it will be a comfortable function for all users. In previous studies, we proposed a simple modeling error compensator which achieves a desired driving characteristics using a simple reference model, and the effectiveness was evaluated by simulations. In this paper, we propose a control system for STAVi using a modeling error compensator with a non-linear reference model to realize a comfortable under-steering characteristics. At first, the advantage of proposed controller is summarized. The STAVi’s over-steering characteristic is modified to be under-steering one by proposed controller. As an experimental result, the additional assistance is necessary for a beginner. The phase-lead compensator for beginners is designed to adjust the maneuverability depending on the skill level. The maneuverability is evaluated by driving experiments on the slope.","PeriodicalId":337733,"journal":{"name":"Transactions of the Japan Society of Mechanical Engineers. C","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127071312","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":"高精度画像処理アルゴリズムによる「いぶき」太陽電池パネル挙動計測","authors":"悟史 鈴木, 俊之 中村, 正広 吉井, 正勝 中島, 洋喜 中西, 瑛彦 本田, 光茂 小田","doi":"10.1299/KIKAIC.79.4233","DOIUrl":"https://doi.org/10.1299/KIKAIC.79.4233","url":null,"abstract":"","PeriodicalId":337733,"journal":{"name":"Transactions of the Japan Society of Mechanical Engineers. C","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116419237","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":"Reduction in the Amplitude of the Primary Resonance Combined with the Parametrically Excited Horizontal Oscillation in a High-Tc Superconducting Levitation System","authors":"R. Sakaguchi, T. Sugiura","doi":"10.1299/KIKAIC.79.2714","DOIUrl":"https://doi.org/10.1299/KIKAIC.79.2714","url":null,"abstract":"高温超電導磁気浮上系には,磁石が非接触,低減衰で安定浮上する特徴がある (1).そのため,非制御の機械シ ステム支援機構やエネルギー損失が極めて少ない機構への応用が期待され,例として高温超電導磁気浮上列車,電 力貯蔵用フライホイールなどが挙げられる (2)−(5).しかしながら,実際に支持機構として利用する際,低減衰系と なることから,系のダイナミクスが支持力である電磁力の非線形性に影響され得る.また,低減衰ゆえに共振振 幅が増大しやすいという問題がある.当研究室では,電磁力の非線形の影響による多自由度連成の問題に関して, 支持力の非線形性を考慮に入れた非線形動力学的な立場からの連続体の研究 (6),超電導磁気軸受で支持された回 転体における非線形現象に関する研究 (7) などを行ってきた.特に,田中ら (8) は高温超電導磁気浮上系における 剛体の並進・回転運動の非線形相互作用を数値計算,実験にて確認した.以上のように高温超電導磁気浮上系で 発生する非線形連成現象,振動特性を明らかにすることで,応用上,問題になり得る現象を予想することが可能 となる.また,高温超電導磁気浮上系の共振振幅の低減に関する研究も行われている.田口ら (9)はオートパラメ トリック動吸振器を用いることで,共振点の数を増やすことなく主系の共振が低減され得ることを数値的、解析 的に確認した. 本研究では,浮上体自身の多自由度の非線形相互作用を利用して,動吸振器を新たに付加することなく浮上体","PeriodicalId":337733,"journal":{"name":"Transactions of the Japan Society of Mechanical Engineers. C","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122230084","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":"Analysis of pulse wave in blood vessel by concentrated mass model","authors":"S. Ishikawa, T. Kondou, K. Matsuzaki","doi":"10.1299/KIKAIC.79.2731","DOIUrl":"https://doi.org/10.1299/KIKAIC.79.2731","url":null,"abstract":"","PeriodicalId":337733,"journal":{"name":"Transactions of the Japan Society of Mechanical Engineers. C","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130415293","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：