# Nearest-Neighbor-based Collision Avoidance for Quadrotors via Reinforcement Learning

arXiv: https://arxiv.org/abs/2104.14912 · HTML: https://mlsanity.com/paper/2104.14912/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 43 references that are in the map.
- First posted on arXiv 30 Apr 2021.

## Builds on (most cited first, 18 of 18)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms](https://mlsanity.com/paper/1911.10635/) (2019)
- [Unity: A General Platform for Intelligent Agents](https://mlsanity.com/paper/1809.02627/) (2018)
- [A Survey and Critique of Multiagent Deep Reinforcement Learning](https://mlsanity.com/paper/1810.05587/) (2018)
- [Socially Aware Motion Planning with Deep Reinforcement Learning](https://mlsanity.com/paper/1703.08862/) (2017)
- [Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learning](https://mlsanity.com/paper/1609.07845/) (2016)
- [Uncertainty-Aware Reinforcement Learning for Collision Avoidance](https://mlsanity.com/paper/1702.01182/) (2017)
- [Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning](https://mlsanity.com/paper/1709.10082/) (2017)
- [Unmanned Aerial Vehicles: A Survey on Civil Applications and Key Research Challenges](https://mlsanity.com/paper/1805.00881/) (2018)
- [Collision Avoidance in Pedestrian-Rich Environments with Deep Reinforcement Learning](https://mlsanity.com/paper/1910.11689/) (2019)
- [Deep Reinforcement Learning for Swarm Systems](https://mlsanity.com/paper/1807.06613/) (2018)
- [Multi-agent Motion Planning for Dense and Dynamic Environments via Deep Reinforcement Learning](https://mlsanity.com/paper/2001.06627/) (2020)
- [GLAS: Global-to-Local Safe Autonomy Synthesis for Multi-Robot Motion Planning with End-to-End Learning](https://mlsanity.com/paper/2002.11807/) (2020)
- [Reinforcement Learning with Attention that Works: A Self-Supervised Approach](https://mlsanity.com/paper/1904.03367/) (2019)
- [MAMBPO: Sample-efficient multi-robot reinforcement learning using learned world models](https://mlsanity.com/paper/2103.03662/) (2021)
- [A Comparative Study of Bug Algorithms for Robot Navigation](https://mlsanity.com/paper/1808.05050/) (2018)
- [Force-based Algorithm for Motion Planning of Large Agent Teams](https://mlsanity.com/paper/1909.05415/) (2019)

## Built on by (most cited first, 3 of 3)

- [A Survey on Large-Population Systems and Scalable Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2209.03859/) (2022)
- [Scalable Task-Driven Robotic Swarm Control via Collision Avoidance and Learning Mean-Field Control](https://mlsanity.com/paper/2209.07420/) (2022)
- [FPGA-Based Neural Thrust Controller for UAVs](https://mlsanity.com/paper/2403.18703/) (2024)

## Abstract (arXiv)

Collision avoidance algorithms are of central interest to many drone applications. In particular, decentralized approaches may be the key to enabling robust drone swarm solutions in cases where centralized communication becomes computationally prohibitive. In this work, we draw biological inspiration from flocks of starlings (Sturnus vulgaris) and apply the insight to end-to-end learned decentralized collision avoidance. More specifically, we propose a new, scalable observation model following a biomimetic nearest-neighbor information constraint that leads to fast learning and good collision avoidance behavior. By proposing a general reinforcement learning approach, we obtain an end-to-end learning-based approach to integrating collision avoidance with arbitrary tasks such as package collection and formation change. To validate the generality of this approach, we successfully apply our methodology through motion models of medium complexity, modeling momentum and nonetheless allowing direct application to real world quadrotors in conjunction with a standard PID controller. In contrast to prior works, we find that in our sufficiently rich motion model, nearest-neighbor information is indeed enough to learn effective collision avoidance behavior. Our learned policies are tested in simulation and subsequently transferred to real-world drones to validate their real-world applicability.