@InProceedings{Sugiura2008,
  Title                    = {Motion recognition and generation by combining reference-point-dependent probabilistic models},
  Author                   = {Sugiura, K. and Iwahashi, N.},
  Booktitle                = {Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems},
  Year                     = {2008},
  Month                    = {Sept},
  Pages                    = {852-857},

  Abstract                 = {This paper presents a method to recognize and generate sequential motions for object manipulation such as placing one object on another or rotating it. Motions are learned using reference-point-dependent probabilistic models, which are then transformed to the same coordinate system and combined for motion recognition/generation. We conducted physical experiments in which a user demonstrated the manipulation of puppets and toys, and obtained a recognition accuracy of 63% for the sequential motions. Furthermore, the results of motion generation experiments performed with a robot arm are presented.},
  Doi                      = {10.1109/IROS.2008.4651169},
  Keywords                 = {image motion analysis;image recognition;learning systems;manipulators;mobile robots;probability;robot vision;coordinate system;motion learning;object manipulation;reference-point-dependent probabilistic model;sequential motion generation;sequential motion recognition;Accuracy;Hidden Markov models;Indexes;Robot kinematics;Robots;Stereo vision;Trajectory},
  Review                   = {it seems like each movement segment is trained separately, then woven together over several different HMMs. the learning and recognition is done separately. there does seem to be. uses ML to show classification works.},
  Timestamp                = {2014.12.20}
}

{"_id":"QZj66kim3vHBqQsy3","bibbaseid":"sugiura-iwahashi-motionrecognitionandgenerationbycombiningreferencepointdependentprobabilisticmodels-2008","downloads":0,"creationDate":"2017-09-14T16:34:37.089Z","title":"Motion recognition and generation by combining reference-point-dependent probabilistic models","author_short":["Sugiura, K.","Iwahashi, N."],"year":2008,"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/jfslin/jfslin.github.io/master/jf2lin.bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Motion recognition and generation by combining reference-point-dependent probabilistic models","author":[{"propositions":[],"lastnames":["Sugiura"],"firstnames":["K."],"suffixes":[]},{"propositions":[],"lastnames":["Iwahashi"],"firstnames":["N."],"suffixes":[]}],"booktitle":"Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems","year":"2008","month":"Sept","pages":"852-857","abstract":"This paper presents a method to recognize and generate sequential motions for object manipulation such as placing one object on another or rotating it. Motions are learned using reference-point-dependent probabilistic models, which are then transformed to the same coordinate system and combined for motion recognition/generation. We conducted physical experiments in which a user demonstrated the manipulation of puppets and toys, and obtained a recognition accuracy of 63% for the sequential motions. Furthermore, the results of motion generation experiments performed with a robot arm are presented.","doi":"10.1109/IROS.2008.4651169","keywords":"image motion analysis;image recognition;learning systems;manipulators;mobile robots;probability;robot vision;coordinate system;motion learning;object manipulation;reference-point-dependent probabilistic model;sequential motion generation;sequential motion recognition;Accuracy;Hidden Markov models;Indexes;Robot kinematics;Robots;Stereo vision;Trajectory","review":"it seems like each movement segment is trained separately, then woven together over several different HMMs. the learning and recognition is done separately. there does seem to be. uses ML to show classification works.","timestamp":"2014.12.20","bibtex":"@InProceedings{Sugiura2008,\n Title = {Motion recognition and generation by combining reference-point-dependent probabilistic models},\n Author = {Sugiura, K. and Iwahashi, N.},\n Booktitle = {Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems},\n Year = {2008},\n Month = {Sept},\n Pages = {852-857},\n\n Abstract = {This paper presents a method to recognize and generate sequential motions for object manipulation such as placing one object on another or rotating it. Motions are learned using reference-point-dependent probabilistic models, which are then transformed to the same coordinate system and combined for motion recognition/generation. We conducted physical experiments in which a user demonstrated the manipulation of puppets and toys, and obtained a recognition accuracy of 63% for the sequential motions. Furthermore, the results of motion generation experiments performed with a robot arm are presented.},\n Doi = {10.1109/IROS.2008.4651169},\n Keywords = {image motion analysis;image recognition;learning systems;manipulators;mobile robots;probability;robot vision;coordinate system;motion learning;object manipulation;reference-point-dependent probabilistic model;sequential motion generation;sequential motion recognition;Accuracy;Hidden Markov models;Indexes;Robot kinematics;Robots;Stereo vision;Trajectory},\n Review = {it seems like each movement segment is trained separately, then woven together over several different HMMs. the learning and recognition is done separately. there does seem to be. uses ML to show classification works.},\n Timestamp = {2014.12.20}\n}\n\n","author_short":["Sugiura, K.","Iwahashi, N."],"key":"Sugiura2008","id":"Sugiura2008","bibbaseid":"sugiura-iwahashi-motionrecognitionandgenerationbycombiningreferencepointdependentprobabilisticmodels-2008","role":"author","urls":{},"keyword":["image motion analysis;image recognition;learning systems;manipulators;mobile robots;probability;robot vision;coordinate system;motion learning;object manipulation;reference-point-dependent probabilistic model;sequential motion generation;sequential motion recognition;Accuracy;Hidden Markov models;Indexes;Robot kinematics;Robots;Stereo vision;Trajectory"],"downloads":0},"search_terms":["motion","recognition","generation","combining","reference","point","dependent","probabilistic","models","sugiura","iwahashi"],"keywords":["image motion analysis;image recognition;learning systems;manipulators;mobile robots;probability;robot vision;coordinate system;motion learning;object manipulation;reference-point-dependent probabilistic model;sequential motion generation;sequential motion recognition;accuracy;hidden markov models;indexes;robot kinematics;robots;stereo vision;trajectory"],"authorIDs":[],"dataSources":["iCsmKnycRmHPxmhBd"]}