Human-in-the-Loop Optimization of Shared Autonomy in Assistive Robotics. Gopinath, D., Jain, S., & Argall, B. D. IEEE Robotics and Automation Letters, 2(1):247–254, January, 2017. Conference Name: IEEE Robotics and Automation Lettersdoi abstract bibtex In this paper, we propose a mathematical framework which formalizes user-driven customization of shared autonomy in assistive robotics as a nonlinear optimization problem. Our insight is to allow the end-user, rather than relying on standard optimization techniques, to perform the optimization procedure, thereby allowing us to leave the exact nature of the cost function indeterminate. We ground our formalism with an interactive optimization procedure that customizes control sharing using an assistive robotic arm. We also present a pilot study that explores interactive optimization with end-users. This study was performed with 17 subjects (4 with spinal cord injury, 13 without injury). Results show all subjects were able to converge to an assistance paradigm, suggesting the existence of optimal solutions. Notably, the amount of assistance was not always optimized for task performance. Instead, some subjects favored retaining more control during the execution over better task performance. The study supports the case for user-driven customization and provides guidance for its continued development and study.
@article{gopinath_human---loop_2017,
title = {Human-in-the-{Loop} {Optimization} of {Shared} {Autonomy} in {Assistive} {Robotics}},
volume = {2},
issn = {2377-3766},
doi = {10.1109/LRA.2016.2593928},
abstract = {In this paper, we propose a mathematical framework which formalizes user-driven customization of shared autonomy in assistive robotics as a nonlinear optimization problem. Our insight is to allow the end-user, rather than relying on standard optimization techniques, to perform the optimization procedure, thereby allowing us to leave the exact nature of the cost function indeterminate. We ground our formalism with an interactive optimization procedure that customizes control sharing using an assistive robotic arm. We also present a pilot study that explores interactive optimization with end-users. This study was performed with 17 subjects (4 with spinal cord injury, 13 without injury). Results show all subjects were able to converge to an assistance paradigm, suggesting the existence of optimal solutions. Notably, the amount of assistance was not always optimized for task performance. Instead, some subjects favored retaining more control during the execution over better task performance. The study supports the case for user-driven customization and provides guidance for its continued development and study.},
number = {1},
journal = {IEEE Robotics and Automation Letters},
author = {Gopinath, Deepak and Jain, Siddarth and Argall, Brenna D.},
month = jan,
year = {2017},
note = {Conference Name: IEEE Robotics and Automation Letters},
pages = {247--254},
}
Downloads: 0
{"_id":"k3fGHn95hLNcRu2vX","bibbaseid":"gopinath-jain-argall-humanintheloopoptimizationofsharedautonomyinassistiverobotics-2017","author_short":["Gopinath, D.","Jain, S.","Argall, B. D."],"bibdata":{"bibtype":"article","type":"article","title":"Human-in-the-Loop Optimization of Shared Autonomy in Assistive Robotics","volume":"2","issn":"2377-3766","doi":"10.1109/LRA.2016.2593928","abstract":"In this paper, we propose a mathematical framework which formalizes user-driven customization of shared autonomy in assistive robotics as a nonlinear optimization problem. Our insight is to allow the end-user, rather than relying on standard optimization techniques, to perform the optimization procedure, thereby allowing us to leave the exact nature of the cost function indeterminate. We ground our formalism with an interactive optimization procedure that customizes control sharing using an assistive robotic arm. We also present a pilot study that explores interactive optimization with end-users. This study was performed with 17 subjects (4 with spinal cord injury, 13 without injury). Results show all subjects were able to converge to an assistance paradigm, suggesting the existence of optimal solutions. Notably, the amount of assistance was not always optimized for task performance. Instead, some subjects favored retaining more control during the execution over better task performance. The study supports the case for user-driven customization and provides guidance for its continued development and study.","number":"1","journal":"IEEE Robotics and Automation Letters","author":[{"propositions":[],"lastnames":["Gopinath"],"firstnames":["Deepak"],"suffixes":[]},{"propositions":[],"lastnames":["Jain"],"firstnames":["Siddarth"],"suffixes":[]},{"propositions":[],"lastnames":["Argall"],"firstnames":["Brenna","D."],"suffixes":[]}],"month":"January","year":"2017","note":"Conference Name: IEEE Robotics and Automation Letters","pages":"247–254","bibtex":"@article{gopinath_human---loop_2017,\n\ttitle = {Human-in-the-{Loop} {Optimization} of {Shared} {Autonomy} in {Assistive} {Robotics}},\n\tvolume = {2},\n\tissn = {2377-3766},\n\tdoi = {10.1109/LRA.2016.2593928},\n\tabstract = {In this paper, we propose a mathematical framework which formalizes user-driven customization of shared autonomy in assistive robotics as a nonlinear optimization problem. Our insight is to allow the end-user, rather than relying on standard optimization techniques, to perform the optimization procedure, thereby allowing us to leave the exact nature of the cost function indeterminate. We ground our formalism with an interactive optimization procedure that customizes control sharing using an assistive robotic arm. We also present a pilot study that explores interactive optimization with end-users. This study was performed with 17 subjects (4 with spinal cord injury, 13 without injury). Results show all subjects were able to converge to an assistance paradigm, suggesting the existence of optimal solutions. Notably, the amount of assistance was not always optimized for task performance. Instead, some subjects favored retaining more control during the execution over better task performance. The study supports the case for user-driven customization and provides guidance for its continued development and study.},\n\tnumber = {1},\n\tjournal = {IEEE Robotics and Automation Letters},\n\tauthor = {Gopinath, Deepak and Jain, Siddarth and Argall, Brenna D.},\n\tmonth = jan,\n\tyear = {2017},\n\tnote = {Conference Name: IEEE Robotics and Automation Letters},\n\tpages = {247--254},\n}\n\n","author_short":["Gopinath, D.","Jain, S.","Argall, B. D."],"key":"gopinath_human---loop_2017","id":"gopinath_human---loop_2017","bibbaseid":"gopinath-jain-argall-humanintheloopoptimizationofsharedautonomyinassistiverobotics-2017","role":"author","urls":{},"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/yuuki_koyama","dataSources":["bJBFjpaYFPYMt7By9"],"keywords":[],"search_terms":["human","loop","optimization","shared","autonomy","assistive","robotics","gopinath","jain","argall"],"title":"Human-in-the-Loop Optimization of Shared Autonomy in Assistive Robotics","year":2017}