AlphaJet: Automated Conceptual Aircraft Synthesis via Disentangled Generative Priors and Topology-Preserving Evolutionary Search

2026-04-29

AI Summary

Traditional aircraft design relies heavily on expert-driven iterative refinement, which is inefficient and difficult to automate. This work proposes an end-to-end, text-driven method for generating 3D aircraft configurations that enables real-time design iteration under multidisciplinary constraints. The approach introduces several key innovations: an anatomy-disentangled AD-VAE prior for structured latent representation, a topology-preserving elitist genetic algorithm to maintain feasible configurations, a mount-aware geometric scoring mechanism that evaluates component compatibility, and a CPU-based real-time rendering pipeline. The integrated system operates interactively on standard CPUs, providing immediate visual feedback for each design generation and substantially enhancing both the efficiency and diversity of early-stage design space exploration.

Abstract

Conceptual aircraft design is traditionally an expert-mediated iterative process in which a human designer proposes a configuration, runs low-order physics, inspects the result, and re-proposes. We present AlphaJet, an end-to-end automated synthesis pipeline that closes this loop. From a textual mission specification (mass, range, cruise speed, hard size envelope, engine count, areal density) AlphaJet evolves a feasible 3D aircraft in real time, scored by a transparent multi-disciplinary fitness function covering aerodynamics, structures, weights, stability, packaging, and geometric mount consistency. Three contributions distinguish our approach: (i) an Anatomically-Disentangled Variational Autoencoder (AD-VAE) whose first 25 latent dimensions are supervised to align with named anatomical parameters, providing an interpretable shape prior; (ii) a topology-elitist genetic algorithm that protects the best individual from each of five tail topologies and triggers stagnation restarts, preventing premature collapse to a single configuration; and (iii) mount-aware geometric scoring that computes signed penetration between engines and other structural parts, eliminating the redundant artifacts common in generative aircraft models. The full loop runs interactively on a CPU and streams every generation to a browser viewer, making it a practical real-world automation tool for early-phase design-space exploration.

Problem

• conceptual aircraft design
• automated synthesis
• generative design
• design-space exploration
• aircraft configuration

Innovation

• disentangled generative prior
• topology-preserving evolutionary search
• automated aircraft synthesis
• mount-aware geometric scoring
• interpretable latent space