RAPTOR: A foundation policy for quadrotor control
Science Robotics · 13.05.2026 · 11 (114)
DOI: 10.1126/scirobotics.aec1481 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science Robotics, erschienen am 13.05.2026. Verfasst von Jonas Eschmann und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering and Computer Sciences (EECS), UC Berkeley, Berkeley, CA 94720, USA. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: National Science Foundation, Defense Advanced Research Projects Agency.
Abstract (Originalsprache)
Humans are remarkably data efficient when adapting to previously 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 gap and require system identification and retraining for even minimal changes to the system. Here, 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 tested 10 different real quadrotors, from 32 grams to 2.4 kilograms, that also differed in motor type (brushed versus brushless), frame type (soft versus rigid), propeller type (two, three, or four blades), and flight controller (PX4, Betaflight, Crazyflie, M5StampFly). We found that a tiny, three-layer policy with only 2084 parameters was sufficient for zero-shot adaptation to a wide variety of platforms. The adaptation through in-context learning was made possible by using a recurrence in the hidden layer. The policy was trained through our proposed meta-imitation learning algorithm, where we sampled 1000 quadrotors and trained a teacher policy for each of them using RL. The 1000 teachers were distilled into a single, adaptive student policy. We found that within milliseconds, the resulting foundation policy adapted zero-shot to unseen quadrotors. We tested the capabilities of the foundation policy under numerous conditions (trajectory tracking, indoor/outdoor, wind disturbance, poking, and different propellers).
Autor:innen und Institutionen
- Department of Electrical Engineering and Computer Sciences (EECS), UC Berkeley, Berkeley, CA 94720, USA.
- Autonomous Robotics Research Center, Technology Innovation Institute, Abu Dhabi, UAE.
ORCID-Profile: Jonas Eschmann
Förderung
- National Science Foundation
- Defense Advanced Research Projects Agency
Zitieren
APA
Eschmann, J., Albani, D., & Loianno, G. (2026). RAPTOR: A foundation policy for quadrotor control. Science Robotics, 11(114). https://doi.org/10.1126/scirobotics.aec1481
Vancouver
Eschmann J, Albani D, Loianno G. RAPTOR: A foundation policy for quadrotor control. Science Robotics. 2026;11(114). doi:10.1126/scirobotics.aec1481
BibTeX
@article{Eschmann2026,
author = {Eschmann, Jonas and Albani, Dario and Loianno, Giuseppe},
title = {RAPTOR: A foundation policy for quadrotor control},
journal = {Science Robotics},
year = {2026},
volume = {11},
number = {114},
doi = {10.1126/scirobotics.aec1481}
}
EUVIMED