Motion generation of robotic surgical tasks: Learning from expert demonstrations. Reiley, C. E., Plaku, E., & Hager, G. D. In 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology, pages 967–970, August, 2010. doi abstract bibtex Robotic surgical assistants offer the possibility of automating portions of a task that are time consuming and tedious in order to reduce the cognitive workload of a surgeon. This paper proposes using programming by demonstration to build generative models and generate smooth trajectories that capture the underlying structure of the motion data recorded from expert demonstrations. Specifically, motion data from Intuitive Surgical's da Vinci Surgical System of a panel of expert surgeons performing three surgical tasks are recorded. The trials are decomposed into subtasks or surgemes, which are then temporally aligned through dynamic time warping. Next, a Gaussian Mixture Model (GMM) encodes the experts' underlying motion structure. Gaussian Mixture Regression (GMR) is then used to extract a smooth reference trajectory to reproduce a trajectory of the task. The approach is evaluated through an automated skill assessment measurement. Results suggest that this paper presents a means to (i) important features of the task, (ii) create a metric to evaluate robot imitative performance (iii) generate smoother trajectories for reproduction of three common medical tasks.
@inproceedings{reileyMotionGenerationRobotic2010,
title = {Motion generation of robotic surgical tasks: {Learning} from expert demonstrations},
shorttitle = {Motion generation of robotic surgical tasks},
doi = {10.1109/IEMBS.2010.5627594},
abstract = {Robotic surgical assistants offer the possibility of automating portions of a task that are time consuming and tedious in order to reduce the cognitive workload of a surgeon. This paper proposes using programming by demonstration to build generative models and generate smooth trajectories that capture the underlying structure of the motion data recorded from expert demonstrations. Specifically, motion data from Intuitive Surgical's da Vinci Surgical System of a panel of expert surgeons performing three surgical tasks are recorded. The trials are decomposed into subtasks or surgemes, which are then temporally aligned through dynamic time warping. Next, a Gaussian Mixture Model (GMM) encodes the experts' underlying motion structure. Gaussian Mixture Regression (GMR) is then used to extract a smooth reference trajectory to reproduce a trajectory of the task. The approach is evaluated through an automated skill assessment measurement. Results suggest that this paper presents a means to (i) important features of the task, (ii) create a metric to evaluate robot imitative performance (iii) generate smoother trajectories for reproduction of three common medical tasks.},
booktitle = {2010 {Annual} {International} {Conference} of the {IEEE} {Engineering} in {Medicine} and {Biology}},
author = {Reiley, C. E. and Plaku, E. and Hager, G. D.},
month = aug,
year = {2010},
keywords = {Computer-Assisted, Expert Systems, Gaussian mixture model, Gaussian mixture regression, Gaussian processes, Hidden Markov models, Humans, Intuitive Surgical da Vinci Surgical System, Man-Machine Systems, Motion, Professional Competence, Robotics, Robots, Surges, Training, Trajectory, User-Computer Interface, automated skill assessment measurement, biomechanics, biomedical optical imaging, decomposition, dynamic time warping, encoding, feature extraction, generative models, image motion analysis, medical image processing, medical robotics, motion generation, programming, regression analysis, robotic surgical assistants, robotic surgical tasks, smooth reference trajectory extraction, smooth trajectories, surgery, video coding, video signal processing},
pages = {967--970},
}
Downloads: 0
{"_id":"mrjhwvxifatxXEoey","bibbaseid":"reiley-plaku-hager-motiongenerationofroboticsurgicaltaskslearningfromexpertdemonstrations-2010","author_short":["Reiley, C. E.","Plaku, E.","Hager, G. D."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Motion generation of robotic surgical tasks: Learning from expert demonstrations","shorttitle":"Motion generation of robotic surgical tasks","doi":"10.1109/IEMBS.2010.5627594","abstract":"Robotic surgical assistants offer the possibility of automating portions of a task that are time consuming and tedious in order to reduce the cognitive workload of a surgeon. This paper proposes using programming by demonstration to build generative models and generate smooth trajectories that capture the underlying structure of the motion data recorded from expert demonstrations. Specifically, motion data from Intuitive Surgical's da Vinci Surgical System of a panel of expert surgeons performing three surgical tasks are recorded. The trials are decomposed into subtasks or surgemes, which are then temporally aligned through dynamic time warping. Next, a Gaussian Mixture Model (GMM) encodes the experts' underlying motion structure. Gaussian Mixture Regression (GMR) is then used to extract a smooth reference trajectory to reproduce a trajectory of the task. The approach is evaluated through an automated skill assessment measurement. Results suggest that this paper presents a means to (i) important features of the task, (ii) create a metric to evaluate robot imitative performance (iii) generate smoother trajectories for reproduction of three common medical tasks.","booktitle":"2010 Annual International Conference of the IEEE Engineering in Medicine and Biology","author":[{"propositions":[],"lastnames":["Reiley"],"firstnames":["C.","E."],"suffixes":[]},{"propositions":[],"lastnames":["Plaku"],"firstnames":["E."],"suffixes":[]},{"propositions":[],"lastnames":["Hager"],"firstnames":["G.","D."],"suffixes":[]}],"month":"August","year":"2010","keywords":"Computer-Assisted, Expert Systems, Gaussian mixture model, Gaussian mixture regression, Gaussian processes, Hidden Markov models, Humans, Intuitive Surgical da Vinci Surgical System, Man-Machine Systems, Motion, Professional Competence, Robotics, Robots, Surges, Training, Trajectory, User-Computer Interface, automated skill assessment measurement, biomechanics, biomedical optical imaging, decomposition, dynamic time warping, encoding, feature extraction, generative models, image motion analysis, medical image processing, medical robotics, motion generation, programming, regression analysis, robotic surgical assistants, robotic surgical tasks, smooth reference trajectory extraction, smooth trajectories, surgery, video coding, video signal processing","pages":"967–970","bibtex":"@inproceedings{reileyMotionGenerationRobotic2010,\n\ttitle = {Motion generation of robotic surgical tasks: {Learning} from expert demonstrations},\n\tshorttitle = {Motion generation of robotic surgical tasks},\n\tdoi = {10.1109/IEMBS.2010.5627594},\n\tabstract = {Robotic surgical assistants offer the possibility of automating portions of a task that are time consuming and tedious in order to reduce the cognitive workload of a surgeon. This paper proposes using programming by demonstration to build generative models and generate smooth trajectories that capture the underlying structure of the motion data recorded from expert demonstrations. Specifically, motion data from Intuitive Surgical's da Vinci Surgical System of a panel of expert surgeons performing three surgical tasks are recorded. The trials are decomposed into subtasks or surgemes, which are then temporally aligned through dynamic time warping. Next, a Gaussian Mixture Model (GMM) encodes the experts' underlying motion structure. Gaussian Mixture Regression (GMR) is then used to extract a smooth reference trajectory to reproduce a trajectory of the task. The approach is evaluated through an automated skill assessment measurement. Results suggest that this paper presents a means to (i) important features of the task, (ii) create a metric to evaluate robot imitative performance (iii) generate smoother trajectories for reproduction of three common medical tasks.},\n\tbooktitle = {2010 {Annual} {International} {Conference} of the {IEEE} {Engineering} in {Medicine} and {Biology}},\n\tauthor = {Reiley, C. E. and Plaku, E. and Hager, G. D.},\n\tmonth = aug,\n\tyear = {2010},\n\tkeywords = {Computer-Assisted, Expert Systems, Gaussian mixture model, Gaussian mixture regression, Gaussian processes, Hidden Markov models, Humans, Intuitive Surgical da Vinci Surgical System, Man-Machine Systems, Motion, Professional Competence, Robotics, Robots, Surges, Training, Trajectory, User-Computer Interface, automated skill assessment measurement, biomechanics, biomedical optical imaging, decomposition, dynamic time warping, encoding, feature extraction, generative models, image motion analysis, medical image processing, medical robotics, motion generation, programming, regression analysis, robotic surgical assistants, robotic surgical tasks, smooth reference trajectory extraction, smooth trajectories, surgery, video coding, video signal processing},\n\tpages = {967--970},\n}\n\n\n\n","author_short":["Reiley, C. E.","Plaku, E.","Hager, G. D."],"key":"reileyMotionGenerationRobotic2010","id":"reileyMotionGenerationRobotic2010","bibbaseid":"reiley-plaku-hager-motiongenerationofroboticsurgicaltaskslearningfromexpertdemonstrations-2010","role":"author","urls":{},"keyword":["Computer-Assisted","Expert Systems","Gaussian mixture model","Gaussian mixture regression","Gaussian processes","Hidden Markov models","Humans","Intuitive Surgical da Vinci Surgical System","Man-Machine Systems","Motion","Professional Competence","Robotics","Robots","Surges","Training","Trajectory","User-Computer Interface","automated skill assessment measurement","biomechanics","biomedical optical imaging","decomposition","dynamic time warping","encoding","feature extraction","generative models","image motion analysis","medical image processing","medical robotics","motion generation","programming","regression analysis","robotic surgical assistants","robotic surgical tasks","smooth reference trajectory extraction","smooth trajectories","surgery","video coding","video signal processing"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/Lurkereer","dataSources":["nt89PQYq5ax2S5mNx","WjABoCEgfQvLxRxoH"],"keywords":["computer-assisted","expert systems","gaussian mixture model","gaussian mixture regression","gaussian processes","hidden markov models","humans","intuitive surgical da vinci surgical system","man-machine systems","motion","professional competence","robotics","robots","surges","training","trajectory","user-computer interface","automated skill assessment measurement","biomechanics","biomedical optical imaging","decomposition","dynamic time warping","encoding","feature extraction","generative models","image motion analysis","medical image processing","medical robotics","motion generation","programming","regression analysis","robotic surgical assistants","robotic surgical tasks","smooth reference trajectory extraction","smooth trajectories","surgery","video coding","video signal processing"],"search_terms":["motion","generation","robotic","surgical","tasks","learning","expert","demonstrations","reiley","plaku","hager"],"title":"Motion generation of robotic surgical tasks: Learning from expert demonstrations","year":2010}