{"ID":2849595,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.23258","arxiv_id":"2510.23258","title":"Deep Active Inference with Diffusion Policy and Multiple Timescale World Model for Real-World Exploration and Navigation","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.","short_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 expecte...","url_abs":"https://arxiv.org/abs/2510.23258","url_pdf":"https://arxiv.org/pdf/2510.23258v1","authors":"[\"Riko Yokozawa\",\"Kentaro Fujii\",\"Yuta Nomura\",\"Shingo Murata\"]","published":"2025-10-27T12:21:33Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Diffusion Model\",\"LoRA\"]","has_code":false}