# Waypoint Planning Networks

arXiv: https://arxiv.org/abs/2105.00312 · HTML: https://mlsanity.com/paper/2105.00312/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 51 references that are in the map.
- First posted on arXiv 1 May 2021.

## Builds on (most cited first, 15 of 15)

- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [Cognitive Mapping and Planning for Visual Navigation](https://mlsanity.com/paper/1702.03920/) (2017)
- [Value Iteration Networks](https://mlsanity.com/paper/1602.02867/) (2016)
- [Motion Planning Networks](https://mlsanity.com/paper/1806.05767/) (2018)
- [Motion Planning Networks: Bridging the Gap Between Learning-based and Classical Motion Planners](https://mlsanity.com/paper/1907.06013/) (2019)
- [Batch Informed Trees (BIT*): Sampling-based Optimal Planning via the Heuristically Guided Search of Implicit Random Geometric Graphs](https://mlsanity.com/paper/1405.5848/) (2014)
- [Universal Planning Networks](https://mlsanity.com/paper/1804.00645/) (2018)
- [HouseExpo: A Large-scale 2D Indoor Layout Dataset for Learning-based Algorithms on Mobile Robots](https://mlsanity.com/paper/1903.09845/) (2019)
- [Neural Path Planning: Fixed Time, Near-Optimal Path Generation via Oracle Imitation](https://mlsanity.com/paper/1904.11102/) (2019)
- [Deeply Informed Neural Sampling for Robot Motion Planning](https://mlsanity.com/paper/1809.10252/) (2018)
- [Neural Manipulation Planning on Constraint Manifolds](https://mlsanity.com/paper/2008.03787/) (2020)
- [Dynamically Constrained Motion Planning Networks for Non-Holonomic Robots](https://mlsanity.com/paper/2008.05112/) (2020)
- [Using Local Experiences for Global Motion Planning](https://mlsanity.com/paper/1903.08693/) (2019)
- [Planning Beyond the Sensing Horizon Using a Learned Context](https://mlsanity.com/paper/1908.09171/) (2019)
- [2D Map Alignment With Region Decomposition](https://mlsanity.com/paper/1709.00309/) (2017)

## Built on by (most cited first, 4 of 4)

- [Potential Based Diffusion Motion Planning](https://mlsanity.com/paper/2407.06169/) (2024)
- [PathBench: A Benchmarking Platform for Classical and Learned Path Planning Algorithms](https://mlsanity.com/paper/2105.01777/) (2021)
- [Robot Motion Planning as Video Prediction: A Spatio-Temporal Neural Network-based Motion Planner](https://mlsanity.com/paper/2208.11287/) (2022)
- [Systematic Comparison of Path Planning Algorithms using PathBench](https://mlsanity.com/paper/2203.03092/) (2022)

## Abstract (arXiv)

With the recent advances in machine learning, path planning algorithms are also evolving; however, the learned path planning algorithms often have difficulty competing with success rates of classic algorithms. We propose waypoint planning networks (WPN), a hybrid algorithm based on LSTMs with a local kernel - a classic algorithm such as A*, and a global kernel using a learned algorithm. WPN produces a more computationally efficient and robust solution. We compare WPN against A*, as well as related works including motion planning networks (MPNet) and value iteration networks (VIN). In this paper, the design and experiments have been conducted for 2D environments. Experimental results outline the benefits of WPN, both in efficiency and generalization. It is shown that WPN's search space is considerably less than A*, while being able to generate near optimal results. Additionally, WPN works on partial maps, unlike A* which needs the full map in advance. The code is available online.