Training a simulated bat: Modeling sonar-based obstacle avoidance using deep-reinforcement learning

Abstract

Recent evidence suggests that sonar provides bats only with limited information about the environment. Nevertheless, they can fly swiftly through dense environments while avoiding obstacles. Previously, we proposed a sonar-based obstacle avoidance model that only relied on the interaural level difference of the onset of the echoes. In this paper, we extend this previous model. In particular, we present a model that (1) is equipped with a short term memory of the three most recent echo trains, and (2) uses the full echo train. Because handcrafting a controller to use more sonar data is challenging, we resort to machine learning to train a robotic model. We find that both extensions substantially increase performance and conclude that these could be used to enhance our existing models of bat sonar behavior. We discuss the implications or our method and findings for both biology and bio-inspired engineering.