A computational model of mapping in echolocating bats

Abstract

Echolocating bats can navigate to salient places relying solely on their sonar system. Currently, much about the mechanism underlying sonar-based navigation in bats remains unknown, and no computational models of this ability have been proposed. In this paper, we propose a computational model of sonar-based navigation in bats. In particular, we advance a model explaining how bats could assemble a cognitive map from their environment using only their sonar readings. The model consists of two loops. The first loop performs low-level obstacle avoidance. This gives rise to stable and environment-derived flight corridors (i.e. preferred pathways for bats flying through the environment). The second high-level loop runs on top of the low-level loop and performs mapping. Mapping is done by combining local view information extracted from echo signals with local self-motion information to recognize previously visited places and memorize their spatial relationships. Using this model, we simulate a bat exploring unstructured environments while constructing a cognitive map using a biologically plausible algorithm. The model we propose allows the simulated bat to construct a global map of its flight paths through the environment without the bat ever reconstructing the three-dimensional layout of the local environment from any of its received echo signals. Indeed, neither the obstacle avoidance strategy that guides the bat through space nor the mapping algorithm requires the three-dimensional geometric structure of the environment to be accessible to the bat.