MonoRace: Robust monocular AI for champion-level drone racing
MonoRace: Robust monocular AI for champion-level drone racing
MonoRace is an onboard drone racing approach that uses a monocular rolling-shutter camera and IMU to achieve champion-level performance without external motion tracking. It combines neural network-based gate segmentation with a drone model for robust state estimation and includes an offline optimization procedure to refine parameters. The system won the 2025 Abu Dhabi Autonomous Drone Racing Competition, reaching speeds up to 100 km/h and handling challenges like camera interference and IMU saturation.
Full article
Article text is not available for this item. Read it at the original source.
Read full article at sourcedoi.org · Opens in a new tab; source language may differ.
MonoRace demonstrates a significant advancement in autonomous drone racing by achieving champion-level performance using only a monocular camera and IMU, without external motion tracking. The system's robust state estimation and offline optimization procedures are key innovations that enhance onboard autonomy and performance in competitive environments.
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Control
- Reported autonomousOpen source S2
Reported numbers
speed
≤100
View original evidence
reached speeds up to 100 kilometers per hour on the competition track
Open source S5
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
rtz. The proposed approach won the Abu Dhabi Autonomous Drone Racing Competition 2025, outperforming all competing autonomous drone race teams and three world champion human pilots in a direct knockout tournament. It reached speeds up to 100 kilometers per hour on the competition track and successfully coped with problems such as camera interference and IMU saturation.
Open source S5
Autonomous drone racing represents a major frontier in robotics research. It requires an artificial intelligence (AI) that can run onboard lightweight flying robots under tight resource and time constraints while pushing the physical system to its limits. The state of the art in this area consists of a system with a stereo camera and an inertial measurement unit (IMU) that beat human drone-racing champions in a contr
Open source S2
ages the known geometry of gates to refine any state estimation parameter. This offline optimization is based purely on onboard flight data and is important for fine-tuning the extrinsic camera calibration parameters. Furthermore, the guidance and control are performed by a neural network that forgoes inner-loop controllers by directly sending motor commands. This small network runs on the flight controller at 500 he
Open source S4
Source：Science Robotics — Journal metadata · doi.org