# The Artificial Intelligence behind the winning entry to the 2019 AI Robotic Racing Competition

arXiv: https://arxiv.org/abs/2109.14985 · HTML: https://mlsanity.com/paper/2109.14985/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 40 references that are in the map.
- First posted on arXiv 30 Sep 2021.

## Builds on (most cited first, 12 of 12)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [Deep Learning in Neural Networks: An Overview](https://mlsanity.com/paper/1404.7828/) (2014)
- [Revisiting Active Perception](https://mlsanity.com/paper/1603.02729/) (2016)
- [Deep Drone Racing: From Simulation to Reality with Domain Randomization](https://mlsanity.com/paper/1905.09727/) (2019)
- [Deep Drone Acrobatics](https://mlsanity.com/paper/2006.05768/) (2020)
- [AlphaPilot: Autonomous Drone Racing](https://mlsanity.com/paper/2005.12813/) (2020)
- [Beauty and the Beast: Optimal Methods Meet Learning for Drone Racing](https://mlsanity.com/paper/1810.06224/) (2018)
- [Aggressive Online Control of a Quadrotor via Deep Network Representations of Optimality Principles](https://mlsanity.com/paper/1912.07067/) (2019)
- [Aggressive Quadrotor Flight through Narrow Gaps with Onboard Sensing and Computing using Active Vision](https://mlsanity.com/paper/1612.00291/) (2016)
- [Autonomous drone race: A computationally efficient vision-based navigation and control strategy](https://mlsanity.com/paper/1809.05958/) (2018)
- [PRGFlow: Benchmarking SWAP-Aware Unified Deep Visual Inertial Odometry](https://mlsanity.com/paper/2006.06753/) (2020)

## Built on by (most cited first, 8 of 8)

- [Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learning](https://mlsanity.com/paper/2310.10943/) (2023)
- [Fully neuromorphic vision and control for autonomous drone flight](https://mlsanity.com/paper/2303.08778/) (2023)
- [Dream to Fly: Model-Based Reinforcement Learning for Vision-Based Drone Flight](https://mlsanity.com/paper/2501.14377/) (2025)
- [Reinforcement Learning for Collision-free Flight Exploiting Deep Collision Encoding](https://mlsanity.com/paper/2402.03947/) (2024)
- [A Map-free Deep Learning-based Framework for Gate-to-Gate Monocular Visual Navigation aboard Miniaturized Aerial Vehicles](https://mlsanity.com/paper/2503.05251/) (2025)
- [Continual Learning for Robust Gate Detection under Dynamic Lighting in Autonomous Drone Racing](https://mlsanity.com/paper/2405.01054/) (2024)
- [A physics-driven sensor placement optimization methodology for temperature field reconstruction](https://mlsanity.com/paper/2409.18423/) (2024)
- [Self-Supervised Monocular Visual Drone Model Identification through Improved Occlusion Handling](https://mlsanity.com/paper/2504.21695/) (2025)

## Abstract (arXiv)

Robotics is the next frontier in the progress of Artificial Intelligence (AI), as the real world in which robots operate represents an enormous, complex, continuous state space with inherent real-time requirements. One extreme challenge in robotics is currently formed by autonomous drone racing. Human drone racers can fly through complex tracks at speeds of up to 190 km/h. Achieving similar speeds with autonomous drones signifies tackling fundamental problems in AI under extreme restrictions in terms of resources. In this article, we present the winning solution of the first AI Robotic Racing (AIRR) Circuit, a competition consisting of four races in which all participating teams used the same drone, to which they had limited access. The core of our approach is inspired by how human pilots combine noisy observations of the race gates with their mental model of the drone's dynamics to achieve fast control. Our approach has a large focus on gate detection with an efficient deep neural segmentation network and active vision. Further, we make contributions to robust state estimation and risk-based control. This allowed us to reach speeds of ~9.2m/s in the last race, unrivaled by previous autonomous drone race competitions. Although our solution was the fastest and most robust, it still lost against one of the best human pilots, Gab707. The presented approach indicates a promising direction to close the gap with human drone pilots, forming an important step in bringing AI to the real world.