# Long Short-Term Memory for Spatial Encoding in Multi-Agent Path Planning

arXiv: https://arxiv.org/abs/2203.10823 · HTML: https://mlsanity.com/paper/2203.10823/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 40 references that are in the map.
- First posted on arXiv 21 Mar 2022.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Deep Neural Network Compression for Aircraft Collision Avoidance Systems](https://mlsanity.com/paper/1810.04240/) (2018)
- [Distributed Wildfire Surveillance with Autonomous Aircraft using Deep Reinforcement Learning](https://mlsanity.com/paper/1810.04244/) (2018)
- [Learning an Urban Air Mobility Encounter Model from Expert Preferences](https://mlsanity.com/paper/1907.05575/) (2019)
- [On Replacing PID Controller with ANN Controller for DC Motor Position Control](https://mlsanity.com/paper/1312.0148/) (2013)

## Abstract (arXiv)

Reinforcement learning-based path planning for multi-agent systems of varying size constitutes a research topic with increasing significance as progress in domains such as urban air mobility and autonomous aerial vehicles continues. Reinforcement learning with continuous state and action spaces is used to train a policy network that accommodates desirable path planning behaviors and can be used for time-critical applications. A Long Short-Term Memory module is proposed to encode an unspecified number of states for a varying, indefinite number of agents. The described training strategies and policy architecture lead to a guidance that scales to an infinite number of agents and unlimited physical dimensions, although training takes place at a smaller scale. The guidance is implemented on a low-cost, off-the-shelf onboard computer. The feasibility of the proposed approach is validated by presenting flight test results of up to four drones, autonomously navigating collision-free in a real-world environment.