CaltechAUTHORS
  A Caltech Library Service

Human motion analysis in medical robotics via high-dimensional inverse reinforcement learning

Li, Kun and Burdick, Joel W. (2020) Human motion analysis in medical robotics via high-dimensional inverse reinforcement learning. International Journal of Robotics Research, 39 (5). pp. 568-585. ISSN 0278-3649. https://resolver.caltech.edu/CaltechAUTHORS:20200213-073405888

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200213-073405888

Abstract

This work develops a novel high-dimensional inverse reinforcement learning (IRL) algorithm for human motion analysis in medical, clinical, and robotics applications. The method is based on the assumption that a surgical robot operators’ skill or a patient’s motor skill is encoded into the innate reward function during motion planning and recovered by an IRL algorithm from motion demonstrations. This class of applications is characterized by high-dimensional sensory data, which is computationally prohibitive for most existing IRL algorithms. We propose a novel function approximation framework and reformulate the Bellman optimality equation to handle high-dimensional state spaces efficiently. We compare different function approximators in simulated environments, and adopt a deep neural network as the function approximator. The technique is applied to evaluating human patients with spinal cord injuries under spinal stimulation, and the skill levels of surgical robot operators. The results demonstrate the efficiency and effectiveness of the proposed method.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1177/0278364920903104DOIArticle
ORCID:
AuthorORCID
Li, Kun0000-0002-5927-4749
Additional Information:© 2020 by SAGE Publications. Article first published online: January 29, 2020; Issue published: April 1, 2020.
Funders:
Funding AgencyGrant Number
NIHUNSPECIFIED
Subject Keywords:Human motion analysis, inverse reinforcement learning, medical data analysis
Issue or Number:5
Record Number:CaltechAUTHORS:20200213-073405888
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20200213-073405888
Official Citation:Li, K., & Burdick, J. W. (2020). Human motion analysis in medical robotics via high-dimensional inverse reinforcement learning. The International Journal of Robotics Research, 39(5), 568–585. https://doi.org/10.1177/0278364920903104
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:101260
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:13 Feb 2020 15:48
Last Modified:25 Mar 2020 15:30

Repository Staff Only: item control page