Navigation and Exploration with Active Inference: from Biology to Industry

TL;DR

This paper introduces a biologically inspired robotic navigation system based on Active Inference Framework, capable of real-time map building, localization, and planning in complex environments without prior training.

Contribution

It presents a novel real-time navigation method that constructs topological maps and plans actions using active inference, applicable to both 2D and 3D environments, integrated into ROS2.

Findings

Demonstrates competitive performance with traditional exploration methods

Validates adaptability in simulated and real-world environments

Offers a biologically inspired approach to robotic navigation

Abstract

By building and updating internal cognitive maps, animals exhibit extraordinary navigation abilities in complex, dynamic environments. Inspired by these biological mechanisms, we present a real time robotic navigation system grounded in the Active Inference Framework (AIF). Our model incrementally constructs a topological map, infers the agent's location, and plans actions by minimising expected uncertainty and fulfilling perceptual goals without any prior training. Integrated into the ROS2 ecosystem, we validate its adaptability and efficiency across both 2D and 3D environments (simulated and real world), demonstrating competitive performance with traditional and state of the art exploration approaches while offering a biologically inspired navigation approach.