Controlled Flight of an Insect-Scale Flapping-Wing Robot via Integrated Onboard Sensing and Computation

2026-02-09

AI Summary

This work presents a 1.29-gram flapping-wing aerial robot that achieves fully autonomous flight without reliance on external motion capture systems—a longstanding challenge for insect-scale robots. For the first time at this scale, the platform integrates onboard sensing, a lightweight state estimation algorithm, and a low-level controller to form a complete perception–computation–control loop. Leveraging a hierarchical control architecture, the system executes high-level navigation commands and demonstrates centimeter-level positioning accuracy in outdoor environments devoid of motion capture infrastructure. In experimental validation, the robot successfully performed a 30-second obstacle-avoidance flight and precisely landed on a sunflower, showcasing its potential for real-world applications such as search-and-rescue operations and precision agriculture.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Computer Vision: Vision for Robotics & Autonomous Driving
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Aerial insects can effortlessly navigate dense vegetation, whereas similarly sized aerial robots typically depend on offboard sensors and computation to maintain stable flight. This disparity restricts insect-scale robots to operation within motion capture environments, substantially limiting their applicability to tasks such as search-and-rescue and precision agriculture. In this work, we present a 1.29-gram aerial robot capable of hovering and tracking trajectories with solely onboard sensing and computation. The combination of a sensor suite, estimators, and a low-level controller achieved centimeter-scale positional flight accuracy. Additionally, we developed a hierarchical controller in which a human operator provides high-level commands to direct the robot's motion. In a 30-second flight experiment conducted outside a motion capture system, the robot avoided obstacles and ultimately landed on a sunflower. This level of sensing and computational autonomy represents a significant advancement for the aerial microrobotics community, further opening opportunities to explore onboard planning and power autonomy.

Problem

• insect-scale robot
• onboard sensing
• autonomous flight
• flapping-wing
• microrobotics

Innovation

• insect-scale robotics
• onboard sensing
• autonomous flight
• flapping-wing MAV
• hierarchical control