Deep Active Inference with Diffusion Policy and Multiple Timescale World Model for Real-World Exploration and Navigation

TL;DR

This paper introduces a deep active inference framework for robotic navigation that combines a diffusion policy and a multi-timescale world model, enabling effective exploration and goal achievement in real environments.

Contribution

It presents a novel deep active inference approach integrating diffusion policies and a multi-timescale world model for real-world robotic navigation.

Findings

Higher success rates in navigation tasks

Fewer collisions compared to baselines

Effective exploration in complex environments

Abstract

Autonomous robotic navigation in real-world environments requires exploration to acquire environmental information as well as goal-directed navigation in order to reach specified targets. Active inference (AIF) based on the free-energy principle provides a unified framework for these behaviors by minimizing the expected free energy (EFE), thereby combining epistemic and extrinsic values. To realize this practically, we propose a deep AIF framework that integrates a diffusion policy as the policy model and a multiple timescale recurrent state-space model (MTRSSM) as the world model. The diffusion policy generates diverse candidate actions while the MTRSSM predicts their long-horizon consequences through latent imagination, enabling action selection that minimizes EFE. Real-world navigation experiments demonstrated that our framework achieved higher success rates and fewer collisions compared with the baselines, particularly in exploration-demanding scenarios. These results highlight how AIF based on EFE minimization can unify exploration and goal-directed navigation in real-world robotic settings.