Learning End-to-end Multimodal Sensor Policies for Autonomous Navigation - Robotics Institute Carnegie Mellon University

Learning End-to-end Multimodal Sensor Policies for Autonomous Navigation

G. H. Liu, A. Siravuru, S. Prabhakar, M. Veloso, and G. Kantor
Conference Paper, Proceedings of (CoRL) Conference on Robot Learning, Vol. 78, pp. 249 - 261, November, 2017

Abstract

We proposed a multimodal end-to-end policy based on deep reinforcement learning (DRL) that leverages sensor fusion to reduced performance drops in noisy environment from 50% to 10% compared with the baseline and makes the policy functional even in the face of partial sensor failure by using a novel stochastic technique called Sensor Dropout to reduce sensitivity to any sensor subset, and a new auxiliary loss on policy network along with standard DRL loss that reduces the action variations.

BibTeX

@conference{Liu-2017-119999,
author = {G. H. Liu and A. Siravuru and S. Prabhakar and M. Veloso and G. Kantor},
title = {Learning End-to-end Multimodal Sensor Policies for Autonomous Navigation},
booktitle = {Proceedings of (CoRL) Conference on Robot Learning},
year = {2017},
month = {November},
volume = {78},
pages = {249 - 261},
}