Approximate Inverse Reinforcement Learning from Vision-based Imitation Learning

Keuntaek Lee, Bogdan Vlahov, Jason Gibson, James M. Rehg, Evangelos A. Theodorou

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this work, we present a method for obtaining an implicit objective function for vision-based navigation. The proposed methodology relies on Imitation Learning, Model Predictive Control (MPC), and an interpretation technique used in Deep Neural Networks. We use Imitation Learning as a means to do Inverse Reinforcement Learning in order to create an approximate cost function generator for a visual navigation challenge. The resulting cost function, the costmap, is used in conjunction with MPC for real-time control and outperforms other state-of-the-art costmap generators in novel environments. The proposed process allows for simple training and robustness to out-of-sample data. We apply our method to the task of vision-based autonomous driving in multiple real and simulated environments and show its generalizability. Supplementary video: https://youtu.be/WyJfT5lc0aQ.

Original languageEnglish (US)
Title of host publication2021 IEEE International Conference on Robotics and Automation, ICRA 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages10793-10799
Number of pages7
ISBN (Electronic)9781728190778
DOIs
StatePublished - 2021
Externally publishedYes
Event2021 IEEE International Conference on Robotics and Automation, ICRA 2021 - Xi'an, China
Duration: May 30 2021Jun 5 2021

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
Volume2021-May
ISSN (Print)1050-4729

Conference

Conference2021 IEEE International Conference on Robotics and Automation, ICRA 2021
Country/TerritoryChina
CityXi'an
Period5/30/216/5/21

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Approximate Inverse Reinforcement Learning from Vision-based Imitation Learning'. Together they form a unique fingerprint.

Cite this