Quadrotor Morpho-Transition: Learning vs Model-Based Control Strategies

TL;DR

This paper compares model-based and reinforcement learning control strategies for quadrotor morpho-transitions, demonstrating RL's effectiveness in hardware transfer when accounting for motor dynamics and delays.

Contribution

It introduces an end-to-end RL controller for quadrotor morpho-transitions and analyzes its transferability to hardware compared to traditional MPC methods.

Findings

RL controller achieves agile landing in hardware

Transferability depends on modeling motor dynamics and delays

MPC transfers without detailed actuator modeling but is less disturbance-resistant

Abstract

Quadrotor Morpho-Transition, or the act of transitioning from air to ground through mid-air transformation, involves complex aerodynamic interactions and a need to operate near actuator saturation, complicating controller design. In recent work, morpho-transition has been studied from a model-based control perspective, but these approaches remain limited due to unmodeled dynamics and the requirement for planning through contacts. Here, we train an end-to-end Reinforcement Learning (RL) controller to learn a morpho-transition policy and demonstrate successful transfer to hardware. We find that the RL control policy achieves agile landing, but only transfers to hardware if motor dynamics and observation delays are taken into account. On the other hand, a baseline MPC controller transfers out-of-the-box without knowledge of the actuator dynamics and delays, at the cost of reduced recovery from disturbances in the event of unknown actuator failures. Our work opens the way for more robust control of agile in-flight quadrotor maneuvers that require mid-air transformation.