Generative-Model Predictive Planning for Navigation in Partially Observable Environments
Quick Answer
The BeliefDiffusion framework enhances navigation in partially observable environments by integrating diffusion models for multimodal belief representation with Model Predictive Control (MPC) for planning.
Quick Take
Extensive experiments show it significantly outperforms model-free reinforcement learning and other generative methods in navigation success rates and path efficiency.
Key Points
- BeliefDiffusion combines generative models with Model Predictive Control for effective navigation.
- It addresses challenges in high-dimensional belief spaces with perceptual aliasing.
- Extensive experiments demonstrate superior navigation success rates compared to existing methods.
- The framework consists of imagining environment configurations and planning navigation strategies.
- Incorporating multimodal belief representations leads to more robust navigation.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Navigation in partially observable environments presents a significant challenge for autonomous agents, requiring effective decision-making with limited sensory information in unknown environments. Belief-based methods, particularly those using neural networks to approximate the belief space, often fail to capture the inherent multimodality of belief spaces, especially in high-dimensional cases with perceptual aliasing. While generative models present a compelling alternative, they typically require substantial data or expert demonstrations and lack explicit mechanisms for long-term planning. In this paper, we introduce BeliefDiffusion, a novel framework that combines the benefits of both generation and planning. BeliefDiffusion leverages diffusion models to explicitly characterize multimodal belief distributions and utilizes Model Predictive Control (MPC) to simultaneously plan ahead. It consists of two steps: (1) Imagining plausible environment configurations based on observation history and (2) Planning efficient navigation strategies across an aggregated configurations. Through extensive experiments in synthetic map environments, we demonstrate that BeliefDiffusion significantly outperforms both model-free reinforcement learning baselines and other generative approaches in navigation success rate and path efficiency. Our results validate that explicitly incorporating multimodal belief representations into planning enables more robust navigation in partially observable settings.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.18888 [cs.AI] |
| (or arXiv:2606.18888v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.18888 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tom Quilter Dr [view email]
[v1]
Wed, 17 Jun 2026 10:06:39 UTC (226 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.