Pub Date : 1991-11-03DOI: 10.1109/IROS.1991.174456
S. Pagliano, V. Sanguineti, P. Morasso
A computational model is proposed for trajectory planning of redundant robots starting from studies about synergy generation in human motor system. Based on the passive motion paradigm (PMP), i.e., on an analogic mechanism, the model shows a good representational power and is able to manage several robot motor planning problems. Such a connectionist model shows analogies with several neural network paradigms, in particular relaxation, and can be expressed in terms of neuron-like processing elements.<>
{"title":"A neural framework for robot motor planning","authors":"S. Pagliano, V. Sanguineti, P. Morasso","doi":"10.1109/IROS.1991.174456","DOIUrl":"https://doi.org/10.1109/IROS.1991.174456","url":null,"abstract":"A computational model is proposed for trajectory planning of redundant robots starting from studies about synergy generation in human motor system. Based on the passive motion paradigm (PMP), i.e., on an analogic mechanism, the model shows a good representational power and is able to manage several robot motor planning problems. Such a connectionist model shows analogies with several neural network paradigms, in particular relaxation, and can be expressed in terms of neuron-like processing elements.<<ETX>>","PeriodicalId":388962,"journal":{"name":"Proceedings IROS '91:IEEE/RSJ International Workshop on Intelligent Robots and Systems '91","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129334165","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}
Pub Date : 1991-11-03DOI: 10.1109/IROS.1991.174550
T. Manabe, F. Miyazaki
Discusses a new type of learning control scheme for a class of discrete-time nonlinear system. The algorithm of the proposed learning control utilizes a local linearization technique by using a discrete Fourier transform (DFT) to design a learning operator and the numerical function iterative techniques. The secant method is used, which can find the best learning operator by itself at each learning step, in other words, at each calculation step of iteration. This proposed learning algorithm has been extensively tested by simulation on the computer.<>
{"title":"Learning control based on local linearization by using DFT","authors":"T. Manabe, F. Miyazaki","doi":"10.1109/IROS.1991.174550","DOIUrl":"https://doi.org/10.1109/IROS.1991.174550","url":null,"abstract":"Discusses a new type of learning control scheme for a class of discrete-time nonlinear system. The algorithm of the proposed learning control utilizes a local linearization technique by using a discrete Fourier transform (DFT) to design a learning operator and the numerical function iterative techniques. The secant method is used, which can find the best learning operator by itself at each learning step, in other words, at each calculation step of iteration. This proposed learning algorithm has been extensively tested by simulation on the computer.<<ETX>>","PeriodicalId":388962,"journal":{"name":"Proceedings IROS '91:IEEE/RSJ International Workshop on Intelligent Robots and Systems '91","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128647944","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}
Pub Date : 1991-11-03DOI: 10.1109/IROS.1991.174483
J. Miura, Y. Shirai
The authors propose a framework of unified planning of vision and motion with uncertainty. They use a probabilistic model to represent uncertainty and use statistical decision theory to make a unified plan of vision and motion. They describe a method of predicting the information acquired by a sensing operation and formulate the planning problem in a recurrence formula. They analyze vision-motion planning problem in a simple example and conclude that the combination of dynamic programming and hill-climbing is useful. Simulation results show the validity of the approach.<>
{"title":"Planning of vision and motion for a mobile robot using a probabilistic model of uncertainty","authors":"J. Miura, Y. Shirai","doi":"10.1109/IROS.1991.174483","DOIUrl":"https://doi.org/10.1109/IROS.1991.174483","url":null,"abstract":"The authors propose a framework of unified planning of vision and motion with uncertainty. They use a probabilistic model to represent uncertainty and use statistical decision theory to make a unified plan of vision and motion. They describe a method of predicting the information acquired by a sensing operation and formulate the planning problem in a recurrence formula. They analyze vision-motion planning problem in a simple example and conclude that the combination of dynamic programming and hill-climbing is useful. Simulation results show the validity of the approach.<<ETX>>","PeriodicalId":388962,"journal":{"name":"Proceedings IROS '91:IEEE/RSJ International Workshop on Intelligent Robots and Systems '91","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130065219","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}
Pub Date : 1991-11-03DOI: 10.1109/IROS.1991.174642
Y. Shoji, M. Inaba, T. Fukuda
A methodology using the Lyapunov direct method is proposed to analyze the stability of an n-D.O.F. linear manipulator system which is positioned on a flexible wall with collision phenomenon. A methodology to determine the control law of the manipulator which guarantees the system stability is also discussed. As collision is a phenomenon with energy dissipation, it is used in the field of industry for such purposes that suppress vibrations. On the other hand, in the field of robotics, the phenomenon is considered to be avoided, because the controllability of the system becomes poorer at contact. But in the case that the demands for fast tasks against environment increases, collision becomes the problem which should be solved. In previous reports, some approaches using the Lyapunov method were discussed. This report expands the manipulator complexity to n-DOF and proves the stability of the system even including collision. Some numerical simulations were also executed to show the transient behavior of the system and to compare with the result of the theoretical analysis.<>
{"title":"Stable contact control of multi-degrees-of-freedom linear manipulator with collision phenomena","authors":"Y. Shoji, M. Inaba, T. Fukuda","doi":"10.1109/IROS.1991.174642","DOIUrl":"https://doi.org/10.1109/IROS.1991.174642","url":null,"abstract":"A methodology using the Lyapunov direct method is proposed to analyze the stability of an n-D.O.F. linear manipulator system which is positioned on a flexible wall with collision phenomenon. A methodology to determine the control law of the manipulator which guarantees the system stability is also discussed. As collision is a phenomenon with energy dissipation, it is used in the field of industry for such purposes that suppress vibrations. On the other hand, in the field of robotics, the phenomenon is considered to be avoided, because the controllability of the system becomes poorer at contact. But in the case that the demands for fast tasks against environment increases, collision becomes the problem which should be solved. In previous reports, some approaches using the Lyapunov method were discussed. This report expands the manipulator complexity to n-DOF and proves the stability of the system even including collision. Some numerical simulations were also executed to show the transient behavior of the system and to compare with the result of the theoretical analysis.<<ETX>>","PeriodicalId":388962,"journal":{"name":"Proceedings IROS '91:IEEE/RSJ International Workshop on Intelligent Robots and Systems '91","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130199447","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}
Pub Date : 1991-11-03DOI: 10.1109/IROS.1991.174729
Junmin Pan, Junshi Cheng
Presents an experimental study of climbing and walking down a slope by the JTUWM-II quadruped robot. A scheme by which the walking robot detects the slope and measures the gradient of the slope with tactile sensors is proposed. An algorithm for the body to turn parallel with the sloping surface is developed. In the transition area gait adjustment is made for stable walking. Also the maximum gradient of the slope for the robot and the optimum body height are given.<>
{"title":"Study of quadruped walking robot climbing and walking down slope","authors":"Junmin Pan, Junshi Cheng","doi":"10.1109/IROS.1991.174729","DOIUrl":"https://doi.org/10.1109/IROS.1991.174729","url":null,"abstract":"Presents an experimental study of climbing and walking down a slope by the JTUWM-II quadruped robot. A scheme by which the walking robot detects the slope and measures the gradient of the slope with tactile sensors is proposed. An algorithm for the body to turn parallel with the sloping surface is developed. In the transition area gait adjustment is made for stable walking. Also the maximum gradient of the slope for the robot and the optimum body height are given.<<ETX>>","PeriodicalId":388962,"journal":{"name":"Proceedings IROS '91:IEEE/RSJ International Workshop on Intelligent Robots and Systems '91","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121281949","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}
Pub Date : 1991-11-03DOI: 10.1109/IROS.1991.174526
S. Hirai, Tadataka Asakawa
Proposes a method to estimate hand-to-object transformation for a hand-eye system. The method estimates hand-to-object transformation by achieving rotation about a fixed point on the object. The primary feature of the method is that the obtained estimation is almost free from visual measurement error. Several experimental results are also included.<>
{"title":"An active method for estimating the pose of an object grasped by a robot","authors":"S. Hirai, Tadataka Asakawa","doi":"10.1109/IROS.1991.174526","DOIUrl":"https://doi.org/10.1109/IROS.1991.174526","url":null,"abstract":"Proposes a method to estimate hand-to-object transformation for a hand-eye system. The method estimates hand-to-object transformation by achieving rotation about a fixed point on the object. The primary feature of the method is that the obtained estimation is almost free from visual measurement error. Several experimental results are also included.<<ETX>>","PeriodicalId":388962,"journal":{"name":"Proceedings IROS '91:IEEE/RSJ International Workshop on Intelligent Robots and Systems '91","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126060973","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}
Pub Date : 1991-11-03DOI: 10.1109/IROS.1991.174437
T. Sobh, R. Bajcsy
The authors address the problem of observing a moving agent. In particular, they propose a system for observing a manipulation process, where a robot hand manipulates an object. A discrete event dynamic system framework is developed for the hand/object interaction over time and a stabilizing observer is constructed. Low-level modules are developed for recognizing the 'events' that cause state transitions within the dynamic manipulation system. The work examines closely the possibilities for errors, mistakes and uncertainties in the manipulation system, observer construction process and event identification mechanisms. The system utilizes different tracking techniques in order to observe and recognize the task in an active, adaptive and goal-directed manner.<>
{"title":"A model for observing a moving agent","authors":"T. Sobh, R. Bajcsy","doi":"10.1109/IROS.1991.174437","DOIUrl":"https://doi.org/10.1109/IROS.1991.174437","url":null,"abstract":"The authors address the problem of observing a moving agent. In particular, they propose a system for observing a manipulation process, where a robot hand manipulates an object. A discrete event dynamic system framework is developed for the hand/object interaction over time and a stabilizing observer is constructed. Low-level modules are developed for recognizing the 'events' that cause state transitions within the dynamic manipulation system. The work examines closely the possibilities for errors, mistakes and uncertainties in the manipulation system, observer construction process and event identification mechanisms. The system utilizes different tracking techniques in order to observe and recognize the task in an active, adaptive and goal-directed manner.<<ETX>>","PeriodicalId":388962,"journal":{"name":"Proceedings IROS '91:IEEE/RSJ International Workshop on Intelligent Robots and Systems '91","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124124418","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}
Pub Date : 1991-11-03DOI: 10.1109/IROS.1991.174426
H. Terasaki, T. Hasegawa, Hironobu Takahashi, T. Arakawa
This paper describes a method of planning grasps for parallel two-fingered grippers in order to pick up user-specified objects and place them at user-specified configurations. By characterizing local space around gripping positions, the method can plan grasps where the hand can move as freely as possible and then easily plan a path. It can plan regrasping where the grasps themselves and the regrasping placements are computed flexibly according to the environment. It can plan minimal sequences of regraspings for objects that have rotational symmetries.<>
{"title":"Automatic grasping and regrasping by space characterization for pick-and-place operations","authors":"H. Terasaki, T. Hasegawa, Hironobu Takahashi, T. Arakawa","doi":"10.1109/IROS.1991.174426","DOIUrl":"https://doi.org/10.1109/IROS.1991.174426","url":null,"abstract":"This paper describes a method of planning grasps for parallel two-fingered grippers in order to pick up user-specified objects and place them at user-specified configurations. By characterizing local space around gripping positions, the method can plan grasps where the hand can move as freely as possible and then easily plan a path. It can plan regrasping where the grasps themselves and the regrasping placements are computed flexibly according to the environment. It can plan minimal sequences of regraspings for objects that have rotational symmetries.<<ETX>>","PeriodicalId":388962,"journal":{"name":"Proceedings IROS '91:IEEE/RSJ International Workshop on Intelligent Robots and Systems '91","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127516149","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}
Pub Date : 1991-11-03DOI: 10.1109/IROS.1991.174590
M. Terauchi, Koji Ito, T. Joko, T. Tsuji
Proposes a new conventional method to reconstruct 3D motion of rigid polyhedral objects from a sequence of monocular images. In general the problem is ill-posed, therefore additional information is required to recover depth. The authors utilize line correspondence between sequential images and existence of parallel line segments in the scene. The relation between the coordinates of points can be described only by a rotation matrix, if it is formulated relatively. Then if there exists a pair of parallel line segments, the matrix can be solved by using linear equations. After that the translation vector is computed. It is necessary that there exists at least one pair of parallel line segments in the scene in order to obtain motion parameters. They also propose the method to extract pairs of parallel line segments in the image. Finally some experimental results for simulated data are demonstrated.<>
{"title":"Motion estimation of a block-shaped rigid object for robot vision","authors":"M. Terauchi, Koji Ito, T. Joko, T. Tsuji","doi":"10.1109/IROS.1991.174590","DOIUrl":"https://doi.org/10.1109/IROS.1991.174590","url":null,"abstract":"Proposes a new conventional method to reconstruct 3D motion of rigid polyhedral objects from a sequence of monocular images. In general the problem is ill-posed, therefore additional information is required to recover depth. The authors utilize line correspondence between sequential images and existence of parallel line segments in the scene. The relation between the coordinates of points can be described only by a rotation matrix, if it is formulated relatively. Then if there exists a pair of parallel line segments, the matrix can be solved by using linear equations. After that the translation vector is computed. It is necessary that there exists at least one pair of parallel line segments in the scene in order to obtain motion parameters. They also propose the method to extract pairs of parallel line segments in the image. Finally some experimental results for simulated data are demonstrated.<<ETX>>","PeriodicalId":388962,"journal":{"name":"Proceedings IROS '91:IEEE/RSJ International Workshop on Intelligent Robots and Systems '91","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133556029","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}
Pub Date : 1991-11-03DOI: 10.1109/IROS.1991.174594
T. Echigo
Proposes a new approach in which a 3D scene is segmented into free areas and object surfaces using: (1) sparse data which are obtained from trinocular stereo; and (2) occluded edges which can not be seen from at least one of the three cameras. Trinocular stereo is employed not only because it is more reliable for finding correspondences than binocular stereo, but also because it clearly classifies edge segments into 3D edge segments which can be seen from all three cameras and ones which can not be seen from at least one of the three cameras. The approach proposed consists of three steps: (1) to obtain free areas by using 3D edge segments which can be seen from all three cameras; (2) the free areas can be expanded by using edges occluded from at least one of the three cameras; and (3) to determine object surfaces. It is necessary to determine whether the 3D edge segments are occluding boundaries by using occluded edges which can not be seen from one of the cameras. One side of an occluding boundary can be taken to be an object surface. Therefore, object surfaces can be inferred using the occluded edges in trinocular stereo.<>
{"title":"Segmentation of a 3D scene into free areas and object surfaces by using occluded edges of trinocular stereo","authors":"T. Echigo","doi":"10.1109/IROS.1991.174594","DOIUrl":"https://doi.org/10.1109/IROS.1991.174594","url":null,"abstract":"Proposes a new approach in which a 3D scene is segmented into free areas and object surfaces using: (1) sparse data which are obtained from trinocular stereo; and (2) occluded edges which can not be seen from at least one of the three cameras. Trinocular stereo is employed not only because it is more reliable for finding correspondences than binocular stereo, but also because it clearly classifies edge segments into 3D edge segments which can be seen from all three cameras and ones which can not be seen from at least one of the three cameras. The approach proposed consists of three steps: (1) to obtain free areas by using 3D edge segments which can be seen from all three cameras; (2) the free areas can be expanded by using edges occluded from at least one of the three cameras; and (3) to determine object surfaces. It is necessary to determine whether the 3D edge segments are occluding boundaries by using occluded edges which can not be seen from one of the cameras. One side of an occluding boundary can be taken to be an object surface. Therefore, object surfaces can be inferred using the occluded edges in trinocular stereo.<<ETX>>","PeriodicalId":388962,"journal":{"name":"Proceedings IROS '91:IEEE/RSJ International Workshop on Intelligent Robots and Systems '91","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126989023","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：