# RAPTOR: A Foundation Policy for Quadrotor Control

arXiv: https://arxiv.org/abs/2509.11481 · HTML: https://mlsanity.com/paper/2509.11481/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 72 references that are in the map.
- First posted on arXiv 15 Sep 2025.

## Builds on (most cited first, 30 of 45)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Reconciling modern machine learning practice and the bias-variance trade-off](https://mlsanity.com/paper/1812.11118/) (2018)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [Deep Reinforcement Learning that Matters](https://mlsanity.com/paper/1709.06560/) (2017)
- [Solving Rubik's Cube with a Robot Hand](https://mlsanity.com/paper/1910.07113/) (2019)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [RMA: Rapid Motor Adaptation for Legged Robots](https://mlsanity.com/paper/2107.04034/) (2021)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Learning by Cheating](https://mlsanity.com/paper/1912.12294/) (2019)
- [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016)
- [Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation](https://mlsanity.com/paper/1708.05144/) (2017)
- [Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learning](https://mlsanity.com/paper/2310.10943/) (2023)
- [Learning values across many orders of magnitude](https://mlsanity.com/paper/1602.07714/) (2016)
- [Deep Drone Racing: From Simulation to Reality with Domain Randomization](https://mlsanity.com/paper/1905.09727/) (2019)
- [A Benchmark Comparison of Learned Control Policies for Agile Quadrotor Flight](https://mlsanity.com/paper/2202.10796/) (2022)
- [Sim-to-(Multi)-Real: Transfer of Low-Level Robust Control Policies to Multiple Quadrotors](https://mlsanity.com/paper/1903.04628/) (2019)
- [Autonomous Drone Racing: A Survey](https://mlsanity.com/paper/2301.01755/) (2023)
- [Learning to Fly in Seconds](https://mlsanity.com/paper/2311.13081/) (2023)

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

- [SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors](https://mlsanity.com/paper/2606.23444/) (2026)
- [Efficient Knowledge Transfer for Jump-Starting Control Policy Learning of Multirotors through Physics-Aware Neural Architectures](https://mlsanity.com/paper/2602.15533/) (2026)
- [Learning End-to-End Control for Omnidirectional Aerial Motion on Overactuated Tilt-rotor Quadrotors](https://mlsanity.com/paper/2602.21583/) (2026)
- [MAVEN: A Meta-Reinforcement Learning Framework for Varying-Dynamics Expertise in Agile Quadrotor Maneuvers](https://mlsanity.com/paper/2603.10714/) (2026)
- [Dynamics Distillation for Efficient and Transferable Control Learning](https://mlsanity.com/paper/2605.01516/) (2026)
- [Adaptive Outer-Loop Control of Quadrotors via Reinforcement Learning](https://mlsanity.com/paper/2605.16015/) (2026)
- [Embodiment-conditioned Generalist Control for Multirotor Aerial Robots](https://mlsanity.com/paper/2606.10857/) (2026)
- [VLN on the Fly: An Onboard Vision-Language Navigation Stack for Aerial Robots](https://mlsanity.com/paper/2609.20191/) (2026)

## Abstract (arXiv)

Humans are remarkably data-efficient when adapting to new unseen conditions, like driving a new car. In contrast, modern robotic control systems, like neural network policies trained using Reinforcement Learning (RL), are highly specialized for single environments. Because of this overfitting, they are known to break down even under small differences like the Simulation-to-Reality (Sim2Real) gap and require system identification and retraining for even minimal changes to the system. In this work, we present RAPTOR, a method for training a highly adaptive foundation policy for quadrotor control. Our method enables training a single, end-to-end neural-network policy to control a wide variety of quadrotors. We test 10 different real quadrotors from 32 g to 2.4 kg that also differ in motor type (brushed vs. brushless), frame type (soft vs. rigid), propeller type (2/3/4-blade), and flight controller (PX4/Betaflight/Crazyflie/M5StampFly). We find that a tiny, three-layer policy with only 2084 parameters is sufficient for zero-shot adaptation to a wide variety of platforms. The adaptation through in-context learning is made possible by using a recurrence in the hidden layer. The policy is trained through our proposed Meta-Imitation Learning algorithm, where we sample 1000 quadrotors and train a teacher policy for each of them using RL. Subsequently, the 1000 teachers are distilled into a single, adaptive student policy. We find that within milliseconds, the resulting foundation policy adapts zero-shot to unseen quadrotors. We extensively test the capabilities of the foundation policy under numerous conditions (trajectory tracking, indoor/outdoor, wind disturbance, poking, different propellers).