A Highly Maneuverable Flying Squirrel Drone with Controllable Foldable Wings

2023-10-01

IEEE/RJS International Conference on Intelligent RObots and Systems

AI Summary

Conventional multirotor UAVs suffer from limited maneuverability in confined spaces due to unidirectional thrust generation. To address this, we propose a bio-inspired, foldable-wing UAV inspired by flying squirrels. Our approach integrates a flexible silicone-membrane folding-wing mechanism enabling multi-configuration aerodynamic morphing; a novel reinforcement learning–based wing control policy trained on human teleoperation demonstrations, which—uniquely for multirotor systems—enables active aerodynamic drag modulation to compensate for thrust saturation; and a real-time aerodynamic–propulsive coupling control framework. Experiments demonstrate that the platform generates controllable, thrust-independent repulsive aerodynamic forces under thrust saturation, significantly improving narrow-space obstacle avoidance success rate and dynamic trajectory tracking accuracy. Overall, the system achieves superior agility compared to conventional multirotor platforms.

Technology Category

• Intelligent Robots: Manipulation
• Machine Learning: Bio-inspired Learning
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Typical drones with multi rotors are generally less maneuverable due to unidirectional thrust, which may be unfavorable to agile flight in very narrow and confined spaces. This paper suggests a new bio-inspired drone that is empowered with high maneuverability in a lightweight and easy-to-carry way. The proposed flying squirrel inspired drone has controllable foldable wings to cover a wider range of flight attitudes and provide more maneuverable flight capability with stable tracking performance. The wings of a drone are fabricated with silicone membranes and sophisticatedly controlled by reinforcement learning based on human-demonstrated data. Specially, such learning based wing control serves to capture even the complex aerodynamics that are often impossible to model mathematically. It is shown through experiment that the proposed flying squirrel drone intentionally induces aerodynamic drag and hence provides the desired additional repulsive force even under saturated mechanical thrust. This work is very meaningful in demonstrating the potential of biomimicry and machine learning for realizing an animal-like agile drone.

Problem

• Enhance drone maneuverability in narrow spaces
• Develop bio-inspired drone with foldable wings
• Control wings using reinforcement learning for agility

Innovation

• Bio-inspired drone with foldable wings
• Reinforcement learning controls wing dynamics
• Induces aerodynamic drag for agile flight