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

Abstract

Multisensory polices are known to enhance both state estimation and target tracking. However, in the space of end-to-end sensorimotor control, this multi-sensor outlook has received limited attention. Moreover, systematic ways to make policies robust to partial sensor failure are not well explored. In this work, we propose a specific customization of Dropout, called \textit{Sensor Dropout}, to improve multisensory policy robustness and handle partial failure in the sensor-set. We also introduce an additional auxiliary loss on the policy network in order to reduce variance in the band of potential multi- and uni-sensory policies to reduce jerks during policy switching triggered by an abrupt sensor failure or deactivation/activation. Finally, through the visualization of gradients, we show that the learned policies are conditioned on the same latent states representation despite having diverse observations spaces - a hallmark of true sensor-fusion. Simulation results of the multisensory policy, as visualized in TORCS racing game, can be seen here: https://youtu.be/QAK2lcXjNZc.

arXiv commentto be published in Conference on Robot Learning (CoRL), 2017

References in corpus (8)

• Continuous control with deep reinforcement learning
• Playing Atari with Deep Reinforcement Learning
• End to End Learning for Self-Driving Cars
• Dueling Network Architectures for Deep Reinforcement Learning
• Learning to Navigate in Complex Environments
• Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations
• Composing Meta-Policies for Autonomous Driving Using Hierarchical Deep Reinforcement Learning
• Sensor Fusion for Robot Control through Deep Reinforcement Learning

Cited by in corpus (7)

• Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges
• Mapless Navigation among Dynamics with Social-safety-awareness: a reinforcement learning approach from 2D laser scans
• Deep Reinforcement Learning with Population-Coded Spiking Neural Network for Continuous Control
• Intervention Aided Reinforcement Learning for Safe and Practical Policy Optimization in Navigation
• Deep Robotic Prediction with hierarchical RGB-D Fusion
• Multi-modal Experts Network for Autonomous Driving
• Touch-based Curiosity for Sparse-Reward Tasks