arXiv AI September 10, 2026 By Riko Yokozawa, Kentaro Fujii, Yuta Nomura, Shingo Murata

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

The paper presents a deep active inference framework for real‑world robotic navigation that combines a diffusion policy with a multiple‑timescale recurrent state‑space model. The diffusion policy generates diverse candidate actions, while the state‑space model predicts long‑horizon outcomes, allowing the system to select actions that minimize expected free energy. Experiments show higher success rates and fewer collisions, especially in exploration‑heavy scenarios, demonstrating the effectiveness of this unified exploration and goal‑directed approach.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Statistics ML

1d ago

Learning to Plan from Random Exploration

arXiv:2609.38383v1 Announce Type: cross Abstract: Random exploration reveals how an environment can be traversed before a goal is specified. Can this experience support long-range planning without po...

By Deqian Kong, Guangyan Sun, Sheng Cheng, Sirui Xie, Bo Pang, Jianwen Xie, Tony Geng, Caiwen Ding, Ying Nian Wu

rag agents diffusion robotics

arXiv Machine Learning

Aug 17

Expected Free Energy-based Informative Path Planning for Robotic Mars Exploration

arXiv:2608. 14466v1 Announce Type: cross Abstract: An autonomous robot efficiently exploring an unknown environment, such as looking for water sources on Mars, faces two simultaneous demands: building an accurate information map while quickly finding the regions of greatest value, and paying for every meter of travel and the cost of every measurement it takes.

By Ajith Anil Meera, Pablo Lanillos, Wouter Kouw

agents robotics

Hugging Face Trending Papers

Jun 23

NavWM: A Unified Navigation World Model for Foresight-Driven Planning

Conventional visual navigation policies often struggle with myopic decision-making and mode collapse in complex environments. While world models offer a promising alternative, existing paradigms typically isolate perception, generation, and control, failing to capture their shared spatio-temporal dynamics.

agents robotics multimodal benchmarks

arXiv AI

Aug 11

Energy-Structured Latent World Models with Neural Time Fields for Physically Constistent Open-World Motion Planning

arXiv:2608. 09876v1 Announce Type: cross Abstract: Physically consistent motion planning remains a fundamental challenge in embodied AI, as generated trajectories must strictly conform to real-world execution dynamics.

By Yapeng Liu, Yuanzhao Zhai, Bo Ding, Huaimin Wang, Lin Wang

rag robotics multimodal

arXiv AI

Jun 2

Improving Diffusion Planners by Self-Supervised Action Gating with Energies

arXiv:2603. 02650v2 Announce Type: replace-cross Abstract: Diffusion planners are a strong approach for offline reinforcement learning, but they can fail when value-guided selection favours trajectories that score well yet are locally inconsistent with the environment dynamics, resulting in brittle execution.

By Yuan Lu, Dongqi Han, Yansen Wang, Dongsheng Li

rag diffusion reinforcement-learning robotics benchmarks

arXiv Computer Vision

Sep 16

World-Action Models for Robot Learning and Control: A Survey

The survey "World-Action Models for Robot Learning and Control" reviews recent advances in coupling future world prediction with executable action generation for robots in open environments. It clarifies the scope of World-Action Models (WAMs) relative to conventional world models, model-based RL, and Vision‑Language‑Action policies, and organizes existing methods through a unified taxonomy covering representations, transition modeling, action interfaces, architectures, training pipelines, data modalities, and scaling strategies. The paper also surveys applications in manipulation, navigation, and autonomous driving, summarizes datasets, benchmarks, and metrics, and discusses key challenges such as action alignment, spatial consistency, long‑horizon memory, and efficient inference.

By Zuxing Lu, Hongjia Zhai, Guanzhi Wang, Huajian Zeng, Jiaqi Yang, Jingyu Liu, Lei Cheng, Yuantai Zhang, Yuheng Qiu, Zezhou Cheng, Ivan Laptev, Danfei Xu, Benjamin Riviere, Giuseppe Loianno, Eric Xing, Xingxing Zuo

agents diffusion reinforcement-learning robotics multimodal benchmarks safety