TY - GEN
T1 - Approximate Inverse Reinforcement Learning from Vision-based Imitation Learning
AU - Lee, Keuntaek
AU - Vlahov, Bogdan
AU - Gibson, Jason
AU - Rehg, James M.
AU - Theodorou, Evangelos A.
N1 - Funding Information:
*This work was supported by Amazon Web Services (AWS) and NASA Langley Research Center Grant 80NSSC19M0211. The authors are with the Georgia Institute of Technology, Atlanta, GA, USA. Correspondence to: [email protected]
Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85124793511&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85124793511&partnerID=8YFLogxK
U2 - 10.1109/ICRA48506.2021.9560916
DO - 10.1109/ICRA48506.2021.9560916
M3 - Conference contribution
AN - SCOPUS:85124793511
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 10793
EP - 10799
BT - 2021 IEEE International Conference on Robotics and Automation, ICRA 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE International Conference on Robotics and Automation, ICRA 2021
Y2 - 30 May 2021 through 5 June 2021
ER -