# WOLF: World Model Guided LiDAR Exploration with Predictive Frontiers

arXiv: https://arxiv.org/abs/2609.23656 · HTML: https://mlsanity.com/paper/2609.23656/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in World models for navigation, one of 11 directions in World models.
- Builds on 7 of its 26 references that are in the map.
- First posted on arXiv 20 Sep 2026.

## Placed in

- World models / [World models for navigation](https://mlsanity.com/wm/world-models-for-navigation/)

## Builds on (most cited first, 7 of 7)

- [Learning to Fly via Deep Model-Based Reinforcement Learning](https://mlsanity.com/paper/2003.08876/) (2020)
- [Dream to Fly: Model-Based Reinforcement Learning for Vision-Based Drone Flight](https://mlsanity.com/paper/2501.14377/) (2025)
- [SkyDreamer: Interpretable End-to-End Vision-Based Drone Racing with Model-Based Reinforcement Learning](https://mlsanity.com/paper/2510.14783/) (2025)
- [PIPE Planner: Pathwise Information Gain with Map Predictions for Indoor Robot Exploration](https://mlsanity.com/paper/2503.07504/) (2025)
- [MAD: Mapping-Aware World Models for Agile Quadrotor Flight](https://mlsanity.com/paper/2606.04534/) (2026)
- [AirDreamer: Generalist Drone Navigation with World Models](https://mlsanity.com/paper/2606.03252/) (2026)
- [FlowPilot: Real-Time World-Action Modeling for Agile UAV Navigation](https://mlsanity.com/paper/2608.00635/) (2026)

## Abstract (arXiv)

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.