UAVs use predicted views to explore hidden spaces faster and better
WOLF: World Model Guided LiDAR Exploration with Predictive Frontiers
Robotics
Summary
Mapping unknown places with drones using laser sensors can miss important spots hidden behind obstacles. The authors present WOLF, a method where a smart model predicts what is likely to be behind these obstacles based on past observations, helping the drone decide where to look next. This prediction guides the drone more effectively, speeding up exploration and covering more area. They tested WOLF in simulations and real flights, showing improved speed and completeness compared to a prior method.
What this means in practice
- •For drone navigation teams: Improve UAV autonomous mapping speed and coverage by predicting and exploring occluded areas.
- •For search and rescue operators: Enhance aerial search by enabling drones to better anticipate and scan hidden or occluded spaces in complex environments.
Authors
Yuyang Tian, Penghui Yang, Pengyuan Wu, Haoran Yang, Chenhui Li, Pengfei Han, Dong Wang, Zhigang Wang, Bin Zhao, Xuelong Li
Abstract
LiDAR-based unmanned aerial vehicle (UAV) exploration builds maps by continually selecting where to observe next. However, decisions based on the measured map provide limited foresight into spatial continuations behind occlusions, leaving potentially informative directions unrecognized. We present WOLF, a world-model-guided framework that predicts future observations to enhance autonomous exploration. In the training stage, a recurrent world model learns observation dynamics from exploration trajectories, with recurrent memory retaining the spatial context needed to interpret partial observations across successive views. Building on this context, the model combines observation history with candidate motions during exploration to predict local occupancy and visibility. To guide further sensing, a predictive frontier generation mechanism then aligns and fuses these predictions using confidence, branch agreement, and observation quality to identify promising regions. The resulting predictive frontiers join measured ones to guide geometric viewpoint selection and trajectory generation, while new scans update subsequent predictions. In simulations, our method reduces mean terminal time by 10.9% relative to EPIC in Garage at comparable coverage and increases mean coverage from 42.12% to 98.35% in Tunnel. Real-world experiments further demonstrate onboard deployment of the learned model for online inference during physical flight.