An Efficient Insect-inspired Approach for Visual Point-goal Navigation

TL;DR

This paper introduces a novel insect-inspired model for visual point-goal navigation that mimics insect brain functions, achieving comparable performance to state-of-the-art methods with significantly less computational cost.

Contribution

The work presents a new insect-inspired model combining associative learning and path integration for efficient visual navigation.

Findings

Model performs comparably to recent state-of-the-art methods.

Approach is robust to environmental perturbations.

Achieves similar results with much lower computational cost.

Abstract

In this work we develop a novel insect-inspired model for visual point-goal navigation. This combines abstracted models of two insect brain structures that have been implicated, respectively, in associative learning and path integration. We draw an analogy between the formal benchmark of the Habitat point-goal navigation task and the ability of insects to discover, learn, and refine visually guided paths around obstacles between a discovered food location and their nest. We demonstrate that the simple insect-inspired model exhibits performance comparable to recent state-of-the-art models at many orders of magnitude less computational cost. Testing in a more realistic simulated environment shows the approach is robust to perturbations.