Learning Aerodynamics for the Control of Flying Humanoid Robots

2025-05-30

AI Summary

Inaccurate aerodynamic modeling and challenges in real-time perception–control co-design hinder flight stabilization of humanoid robots. Method: This work proposes a closed-loop “modeling–validation–control” framework, introducing the first multi-source fusion aerodynamic modeling approach for humanoid robots—integrating CFD simulation, wind-tunnel experiments, and data-driven modeling. An automated CFD data generation pipeline is developed, enabling the first synergistic integration of deep learning-based and linear interpretable modeling for full-pose aerodynamic force prediction. Contribution/Results: The resulting model achieves <8% prediction error and is embedded in an aerodynamically enhanced simulator and a jet-propulsion hardware platform. Flight dynamic balance control is successfully demonstrated on the iRonCub-Mk1 prototype, significantly improving aerial attitude stability and tracking accuracy.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• Modeling aerodynamic forces for flying humanoid robots
• Designing jet-powered humanoid robots for wind tunnel tests
• Integrating learning techniques for aerodynamic-aware control

Innovation

• Jet-powered humanoid robot design optimization
• CFD simulations for aerodynamic force modeling
• Deep Neural Network for aerodynamic control