Home Run: Finding Your Way Home by Imagining Trajectories

TL;DR

This paper introduces a method for navigation planning that allows agents to imagine and incorporate unvisited paths using a hierarchical generative model, improving pathfinding beyond previously explored routes.

Contribution

It extends hierarchical active inference models by enabling the prediction of new paths through generative imagination, demonstrated in a pixel-based grid-world environment.

Findings

Agents can predict shorter, unvisited paths to start points.

Generative models enable imagining potential routes.

Improves navigation planning beyond known trajectories.

Abstract

When studying unconstrained behaviour and allowing mice to leave their cage to navigate a complex labyrinth, the mice exhibit foraging behaviour 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.