Deep Reinforcement Learning to Acquire Navigation Skills for Wheel-Legged Robots in Complex Environments

Abstract

Mobile robot navigation in complex and dynamic environments is a challenging but important problem. Reinforcement learning approaches fail to solve these tasks efficiently due to reward sparsities, temporal complexities and high-dimensionality of sensorimotor spaces which are inherent in such problems. We present a novel approach to train action policies to acquire navigation skills for wheel-legged robots using deep reinforcement learning. The policy maps height-map image observations to motor commands to navigate to a target position while avoiding obstacles. We propose to acquire the multifaceted navigation skill by learning and exploiting a number of manageable navigation behaviors. We also introduce a domain randomization technique to improve the versatility of the training samples. We demonstrate experimentally a significant improvement in terms of data-efficiency, success rate, robustness against irrelevant sensory data, and also the quality of the maneuver skills.

Submitted to IROS 2018

References in corpus (9)

• Continuous control with deep reinforcement learning
• High-Dimensional Continuous Control Using Generalized Advantage Estimation
• Emergence of Locomotion Behaviours in Rich Environments
• Learning Continuous Control Policies by Stochastic Value Gradients
• Hindsight Experience Replay
• Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World
• Learning and Transfer of Modulated Locomotor Controllers
• Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigation
• Deep Predictive Policy Training using Reinforcement Learning

Cited by in corpus (2)

• Spatial Action Maps for Mobile Manipulation
• Inner Attention Supported Adaptive Cooperation for Heterogeneous Multi Robots Teaming based on Multi-agent Reinforcement Learning