DPWM: Autonomous Exploration Via Diffusion-Based Map Prediction Guided Planning
Zemei Jia, Peng Qi, Xiaoxiang Liu, Zhihao Yao, Liang Li
AI summary
Problem
Autonomous robots struggle to plan efficient long-term exploration paths due to limited partial observations and the lack of global foresight in existing prediction methods.
Approach
The method uses a diffusion model with positional heatmaps to predict full environmental maps from partial scans, then solves a dynamic Watchman Route Problem to compute optimal closed-loop exploration paths.
Key results
- Reduces exploration path length by 18.53% on the HouseExpo dataset
- Achieves 16.37% better cross-domain generalization on the Dungeon dataset
- Outperforms state-of-the-art frontier, reinforcement learning, and map-prediction baselines
- Successfully validated in real-world physical robot experiments
Why it matters
Provides a robust, globally optimal planning framework that enhances exploration efficiency for autonomous robots in complex, unknown environments.
Abstract
Autonomous exploration aims to efficiently map unknown environments, yet utilizing limited environmental information to achieve efficient path planning remains chal- lenging. In this work, we focus on leveraging latent information in partial observations to predict the complete environmental structure, thereby furnishing a proposed path planner with the necessary context to devise a long-term optimal explo- ration strategy. Most existing prediction approaches extract environment features through convolutional neural networks (CNN) and infer the characteristics of neighboring regions. This information then feeds into a value function that evaluates candidate frontiers and guides the robot’s planning. Notwith- standing its advantages over traditional heuristic methods, this paradigm remains inherently constrained by its lack of long- term foresight. To this end, we propose dPWM, a diffusion model-based framework for global map prediction, consisting of two key components. The first employs a DDPM with a variable mask to estimate the probability distribution of unknown regions and thereby predict structural features of the global map. We incorporate Gaussian heatmap positional fields into the denoising process via a cross-attention mechanism to enhance regional awareness. This guides the model to focus on nearby areas that are most valuable for exploration. Once the global predictive map is obtained, the second component refers to a designed Watchman Route Problem (WRP) solver to generate an optimal path from the current exploration state. Extensive evaluations show that dPWM reduces exploration path length by 18.53% on HouseExpo and achieves a 16.37% improvement in cross-domain generalization on Dungeon over SOTA baselines. Real-world experiments further validate its effectiveness in physical environments. This work is supported by the National Key R&D Program of China (No. 2024YFB3909903), and the NSFC 62088101 Autonomous Intelligent Unmanned Systems. (Corresponding author: Liang Li.) 1 College of Control Science and Engineering, Zhejiang University, Hangzhou, 310027, China. 2 Beijing Institute of Control Engineering, Beijing, 100190, China.