Learning Aerodynamics for the Control of Flying Humanoid Robots

TL;DR

This paper presents a comprehensive approach to model and control aerodynamic forces in flying humanoid robots, combining CFD simulations, machine learning, and experimental validation on a jet-powered humanoid prototype.

Contribution

It introduces the design of a jet-powered humanoid robot and develops aerodynamic models using CFD and learning techniques for improved control.

Findings

CFD simulations accurately predict aerodynamic forces.

Deep Neural Network effectively models aerodynamic effects.

Aerodynamic-aware controllers improve flight stability.

Abstract

Robots with multi-modal locomotion are an active research field due to their versatility in diverse environments. In this context, additional actuation can provide humanoid robots with aerial capabilities. Flying humanoid robots face challenges in modeling and control, particularly with aerodynamic forces. This paper addresses these challenges from a technological and scientific standpoint. The technological contribution includes the mechanical design of iRonCub-Mk1, a jet-powered humanoid robot, optimized for jet engine integration, and hardware modifications for wind tunnel experiments on humanoid robots for precise aerodynamic forces and surface pressure measurements. The scientific contribution offers a comprehensive approach to model and control aerodynamic forces using classical and learning techniques. Computational Fluid Dynamics (CFD) simulations calculate aerodynamic forces, validated through wind tunnel experiments on iRonCub-Mk1. An automated CFD framework expands the aerodynamic dataset, enabling the training of a Deep Neural Network and a linear regression model. These models are integrated into a simulator for designing aerodynamic-aware controllers, validated through flight simulations and balancing experiments on the iRonCub-Mk1 physical prototype.