Learning-based Trajectory Tracking for Bird-inspired Flapping-Wing Robots

TL;DR

This paper introduces a reinforcement learning-based control framework for bird-inspired flapping-wing robots, enabling stable, agile, and adaptive flight with multimodal trajectory tracking in complex aerodynamic environments.

Contribution

It presents a novel model-free RL approach for high-DoF flapping-wing robots, enhancing their versatility and robustness in trajectory tracking and flight mode switching.

Findings

RL controller learns complex wing trajectories

Achieves stable and agile flight in simulations

Enables spontaneous mode switching under various conditions

Abstract

Bird-sized flapping-wing robots offer significant potential for agile flight in complex environments, but achieving agile and robust trajectory tracking remains a challenge due to the complex aerodynamics and highly nonlinear dynamics inherent in flapping-wing flight. In this work, a learning-based control approach is introduced to unlock the versatility and adaptiveness of flapping-wing flight. We propose a model-free reinforcement learning (RL)-based framework for a high degree-of-freedom (DoF) bird-inspired flapping-wing robot that allows for multimodal flight and agile trajectory tracking. Stability analysis was performed on the closed-loop system comprising of the flapping-wing system and the RL policy. Additionally, simulation results demonstrate that the RL-based controller can successfully learn complex wing trajectory patterns, achieve stable flight, switch between flight modes spontaneously, and track different trajectories under various aerodynamic conditions.