# Fast and Compute-efficient Sampling-based Local Exploration Planning via Distribution Learning

arXiv: https://arxiv.org/abs/2202.13715 · HTML: https://mlsanity.com/paper/2202.13715/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2022.

## Built on by (most cited first, 6 of 6)

- [NeurAR: Neural Uncertainty for Autonomous 3D Reconstruction with Implicit Neural Representations](https://mlsanity.com/paper/2207.10985/) (2022)
- [Deep Reinforcement Learning-based Large-scale Robot Exploration](https://mlsanity.com/paper/2403.10833/) (2024)
- [SC-Explorer: Incremental 3D Scene Completion for Safe and Efficient Exploration Mapping and Planning](https://mlsanity.com/paper/2208.08307/) (2022)
- [Beyond the Frontier: Predicting Unseen Walls from Occupancy Grids by Learning from Floor Plans](https://mlsanity.com/paper/2406.09160/) (2024)
- [Information Gain Is Not All You Need](https://mlsanity.com/paper/2504.01980/) (2025)
- [Learning-Guided Sparsification of Dynamic Graphs in Robotic Exploration](https://mlsanity.com/paper/2604.16509/) (2026)

## Abstract (arXiv)

Exploration is a fundamental problem in robotics. While sampling-based planners have shown high performance, they are oftentimes compute intensive and can exhibit high variance. To this end, we propose to directly learn the underlying distribution of informative views based on the spatial context in the robot's map. We further explore a variety of methods to also learn the information gain. We show in thorough experimental evaluation that our proposed system improves exploration performance by up to 28% over classical methods, and find that learning the gains in addition to the sampling distribution can provide favorable performance vs. compute trade-offs for compute-constrained systems. We demonstrate in simulation and on a low-cost mobile robot that our system generalizes well to varying environments.