TY - JOUR
T1 - A Robustness Analysis of Inverse Optimal Control of Bipedal Walking
AU - Rebula, John R.
AU - Schaal, Stefan
AU - Finley, James
AU - Righetti, Ludovic
N1 - Funding Information:
This work was supported in part by theNewYork University, in part by the Max-Planck Society, in part by the European Union's Horizon 2020
Funding Information:
Manuscript received February 24, 2019; accepted July 20, 2019. Date of publication August 7, 2019; date of current version October 24, 2019. This letter was recommended for publication by Associate Editor J. Kim and Editor N. Tsagarakis upon evaluation of the reviewers’ comments. This work was supported in part by the New York University, in part by the Max-Planck Society, in part by the European Union’s Horizon 2020 research and innovation program under Grant 780684, in part by European Research Council under Grant 637935, in part by the National Science Foundation under Grant CMMI-1825993, in part by National Institutes of Health National Institute of Child Health and Human Development Award Number R01HD091184, in part by National Science Foundation under Grants IIS-1205249, IIS-1017134, and EECS-0926052, in part by the Office of Naval Research, and in part by the Okawa Foundation. (Corresponding author: John Rebula.) J. R. Rebula is with the Max Planck Institute for Intelligent Systems of Tuebingen, Tuebingen 72076, Germany (e-mail: jrebula@umich.edu).
Publisher Copyright:
© 2016 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - Cost functions have the potential to provide compact and understandable generalizations of motion. The goal of inverse optimal control (IOC) is to analyze an observed behavior which is assumed to be optimal with respect to an unknown cost function, and infer this cost function. Here we develop a method for characterizing cost functions of legged locomotion, with the goal of representing complex humanoid behavior with simple models. To test this methodology we simulate walking gaits of a simple 5 link planar walking model which optimize known cost functions, and assess the ability of our IOC method to recover them. In particular, the IOC method uses an iterative trajectory optimization process to infer cost function weightings consistent with those used to generate a single demonstrated optimal trial. We also explore sensitivity of the IOC to sensor noise in the observed trajectory, imperfect knowledge of the model or task, as well as uncertainty in the components of the cost function used. With appropriate modeling, these methods may help infer cost functions from human data, yielding a compact and generalizable representation of human-like motion for use in humanoid robot controllers, as well as providing a new tool for experimentally exploring human preferences.
AB - Cost functions have the potential to provide compact and understandable generalizations of motion. The goal of inverse optimal control (IOC) is to analyze an observed behavior which is assumed to be optimal with respect to an unknown cost function, and infer this cost function. Here we develop a method for characterizing cost functions of legged locomotion, with the goal of representing complex humanoid behavior with simple models. To test this methodology we simulate walking gaits of a simple 5 link planar walking model which optimize known cost functions, and assess the ability of our IOC method to recover them. In particular, the IOC method uses an iterative trajectory optimization process to infer cost function weightings consistent with those used to generate a single demonstrated optimal trial. We also explore sensitivity of the IOC to sensor noise in the observed trajectory, imperfect knowledge of the model or task, as well as uncertainty in the components of the cost function used. With appropriate modeling, these methods may help infer cost functions from human data, yielding a compact and generalizable representation of human-like motion for use in humanoid robot controllers, as well as providing a new tool for experimentally exploring human preferences.
KW - Humanoid robots
KW - optimization and optimal control
KW - underactuated robots
UR - http://www.scopus.com/inward/record.url?scp=85077491103&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077491103&partnerID=8YFLogxK
U2 - 10.1109/LRA.2019.2933766
DO - 10.1109/LRA.2019.2933766
M3 - Article
AN - SCOPUS:85077491103
SN - 2377-3766
VL - 4
SP - 4531
EP - 4538
JO - IEEE Robotics and Automation Letters
JF - IEEE Robotics and Automation Letters
IS - 4
M1 - 8790816
ER -