# NNPP: A Learning-Based Heuristic Model for Accelerating Optimal Path Planning on Uneven Terrain

arXiv: https://arxiv.org/abs/2308.04792 · HTML: https://mlsanity.com/paper/2308.04792/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 33 references that are in the map.
- First posted on arXiv 9 Aug 2023.

## Builds on (most cited first, 6 of 6)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigation](https://mlsanity.com/paper/1703.00420/) (2017)
- [PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model](https://mlsanity.com/paper/2204.02681/) (2022)
- [Deep Reinforcement Learning with Interactive Feedback in a Human-Robot Environment](https://mlsanity.com/paper/2007.03363/) (2020)

## Built on by (most cited first, 1 of 1)

- [Leveraging Energy Features for Surface Classification with Deep Learning: A Comparative Analysis Across Three Independent Datasets](https://mlsanity.com/paper/2606.18698/) (2026)

## Abstract (arXiv)

Intelligent autonomous path planning is essential for enhancing the exploration efficiency of mobile robots operating in uneven terrains like planetary surfaces and off-road environments.In this paper, we propose the NNPP model for computing the heuristic region, enabling foundation algorithms like Astar to find the optimal path solely within this reduced search space, effectively decreasing the search time. The NNPP model learns semantic information about start and goal locations, as well as map representations, from numerous pre-annotated optimal path demonstrations, and produces a probabilistic distribution over each pixel representing the likelihood of it belonging to an optimal path on the map. More specifically, the paper computes the traversal cost for each grid cell from the slope, roughness and elevation difference obtained from the digital elevation model. Subsequently, the start and goal locations are encoded using a Gaussian distribution and different location encoding parameters are analyzed for their effect on model performance. After training, the NNPP model is able to textcolorrevisionaccelerate path planning on novel maps.