CAD-Driven Co-Design for Flight-Ready Jet-Powered Humanoids

2025-09-18

AI Summary

Achieving stable flight for jet-powered aerial bipedal robots under dynamically constrained trajectories remains challenging. Method: This paper proposes a CAD-driven co-optimization framework integrating parametric CAD modeling, K-means clustering for dimensionality reduction, linearized momentum-based model predictive control (MPC) design, and NSGA-II multi-objective optimization to jointly search for optimal robot configurations and controller parameters. Minimum-jerk trajectory planning and Design of Experiments (DoE) are incorporated to enhance solution feasibility. Contribution/Results: We present the first end-to-end joint optimization of geometric design and real-time MPC parameters. The framework generates 5,000 feasible configurations and identifies Pareto-optimal solutions, achieving a significant trade-off between trajectory tracking accuracy and energy consumption. The resulting designs are flight-ready—directly deployable without further modification.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Search and Optimization: Mixed Discrete/Continuous Search
• Constraint Satisfaction and Optimization: Mixed Discrete/Continuous Optimization

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
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

This paper presents a CAD-driven co-design framework for optimizing jet-powered aerial humanoid robots to execute dynamically constrained trajectories. Starting from the iRonCub-Mk3 model, a Design of Experiments (DoE) approach is used to generate 5,000 geometrically varied and mechanically feasible designs by modifying limb dimensions, jet interface geometry (e.g., angle and offset), and overall mass distribution. Each model is constructed through CAD assemblies to ensure structural validity and compatibility with simulation tools. To reduce computational cost and enable parameter sensitivity analysis, the models are clustered using K-means, with representative centroids selected for evaluation. A minimum-jerk trajectory is used to assess flight performance, providing position and velocity references for a momentum-based linearized Model Predictive Control (MPC) strategy. A multi-objective optimization is then conducted using the NSGA-II algorithm, jointly exploring the space of design centroids and MPC gain parameters. The objectives are to minimize trajectory tracking error and mechanical energy expenditure. The framework outputs a set of flight-ready humanoid configurations with validated control parameters, offering a structured method for selecting and implementing feasible aerial humanoid designs.

Problem

• Optimizing jet-powered aerial humanoid robots for constrained trajectories
• Exploring design and control parameters through multi-objective optimization
• Minimizing trajectory tracking error and mechanical energy expenditure

Innovation

• CAD-driven co-design framework for jet-powered humanoids
• K-means clustering for design space reduction
• NSGA-II multi-objective optimization for flight performance