Learning to navigate in a virtual world using optic flow and stereo disparity signals

摘要

Navigating in a complex world is challenging in that the rich, real environment provides a very large number of sensory states that can immediately precede a collision. Biological organisms such as rodents are able to solve this problem, effortlessly navigating in closed spaces by encoding in neural representations distance toward walls or obstacles for a given direction. This paper presents a method that can be used by virtual (simulated) or robotic agents, which uses states similar to neural representations to learn collision avoidance. Unlike other approaches, our reinforcement learning approach uses a small number of states defined by discretized distances along three constant directions. These distances are estimated either from optic flow or binocular stereo information. Parameterized templates for optic flow or disparity information are compared against the input flow or input disparity to estimate these distances. Simulations in a virtual environment show learning of collision avoidance. Our results show that learning with only stereo information is superior to learning with only optic flow information. Our work motivates the usage of state descriptions for the learning of visual navigation. Future work will focus on the fusion of optic flow and stereo information, and transferring these models to robotic platforms.