AI Agents in Engineering Design: A Multi-Agent Framework for Aesthetic and Aerodynamic Car Design

2025-03-30

AI Summary

This paper addresses the longstanding challenge in automotive design of jointly optimizing aesthetic appeal and aerodynamic performance—a process traditionally hindered by low iteration efficiency and prolonged development cycles. To this end, we propose a novel multi-agent framework tailored for automotive design, introducing the paradigm of “Design Agents” for the first time. The framework integrates vision-language models (VLMs), large language models (LLMs), and geometric deep learning, coupled with high-fidelity computational fluid dynamics (CFD) simulation and rapid surrogate modeling. It supports end-to-end tasks including conceptual sketching, styling optimization, 3D modeling, mesh generation, and aerodynamic simulation. Through human-in-the-loop iterative refinement, it transcends conventional single-objective optimization, enabling concurrent aesthetic and aerodynamic co-optimization. The design–simulation closed loop is accelerated from days/weeks to minutes, substantially expanding creative exploration space and enhancing engineering decision quality. Benchmark validation has been successfully conducted on multiple mass-production vehicle programs.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Adversarial Agents
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

We introduce the concept of"Design Agents"for engineering applications, particularly focusing on the automotive design process, while emphasizing that our approach can be readily extended to other engineering and design domains. Our framework integrates AI-driven design agents into the traditional engineering workflow, demonstrating how these specialized computational agents interact seamlessly with engineers and designers to augment creativity, enhance efficiency, and significantly accelerate the overall design cycle. By automating and streamlining tasks traditionally performed manually, such as conceptual sketching, styling enhancements, 3D shape retrieval and generative modeling, computational fluid dynamics (CFD) meshing, and aerodynamic simulations, our approach reduces certain aspects of the conventional workflow from weeks and days down to minutes. These agents leverage state-of-the-art vision-language models (VLMs), large language models (LLMs), and geometric deep learning techniques, providing rapid iteration and comprehensive design exploration capabilities. We ground our methodology in industry-standard benchmarks, encompassing a wide variety of conventional automotive designs, and utilize high-fidelity aerodynamic simulations to ensure practical and applicable outcomes. Furthermore, we present design agents that can swiftly and accurately predict simulation outcomes, empowering engineers and designers to engage in more informed design optimization and exploration. This research underscores the transformative potential of integrating advanced generative AI techniques into complex engineering tasks, paving the way for broader adoption and innovation across multiple engineering disciplines.

Problem

• AI-driven agents enhance automotive design creativity and efficiency
• Automate manual tasks like sketching, CFD meshing, and simulations
• Predict simulation outcomes for informed design optimization

Innovation

• AI-driven design agents enhance engineering workflow
• Automate sketching, modeling, and aerodynamic simulations
• Leverage VLMs, LLMs, and geometric deep learning