Home Run: Finding Your Way Home by Imagining Trajectories

Abstract

When studying unconstrained behavior and allowing mice to leave their cage to navigate a complex labyrinth, the mice exhibit foraging behavior in the labyrinth searching for rewards, returning to their home cage now and then, e.g. to drink. Surprisingly, when executing such a "home run", the mice do not follow the exact reverse path, in fact, the entry path and home path have very little overlap. Recent work proposed a hierarchical active inference model for navigation, where the low level model makes inferences about hidden states and poses that explain sensory inputs, whereas the high level model makes inferences about moving between locations, effectively building a map of the environment. However, using this "map" for planning, only allows the agent to find trajectories that it previously explored, far from the observed mice's behaviour. In this paper, we explore ways of incorporating before-unvisited paths in the planning algorithm, by using the low level generative model to imagine potential, yet undiscovered paths. We demonstrate a proof of concept in a grid-world environment, showing how an agent can accurately predict a new, shorter path in the map leading to its starting point, using a generative model learnt from pixel-based observations.

Spatial and Temporal Hierarchy for Autonomous Navigation Using Active Inference in Minigrid Environment

“…The model’s adaptation to new environments could be optimised, and methods for handling changes in familiar environments can be explored further. Additionally, exploration and goal-seeking tasks could be improved by adding a layer of comprehension to our cognitive map by integrating possible unexplored rooms when planning, in the form of potential places to visit [ 63 ]. Finally, the scalability and flexibility of our hierarchical structure could be extended to more complex, dynamic or realist scenarios such as Memory maze [ 64 ] or Habitat [ 65 ] to step toward real applications.…”