What question did this study set out to answer?

The aim is to introduce FORGE, a framework that combines probabilistic programming with reinforcement learning for vehicle design.

July 4, 2026Proceedings of the Design Society0 citations

Generating vehicle designs using probabilistic programs and reinforcement learning

DEDaniel EleniusSRI International AGA. GhiglinoStanford University KAKrishiv AgarwalUniversity of Florida

Key Points

The aim is to introduce FORGE, a framework that combines probabilistic programming with reinforcement learning for vehicle design.
Developed the FORGE framework for generative engineering using probabilistic programming and reinforcement learning
Utilized simulator-derived rewards to refine design generation
Applied FORGE across various vehicle domains to test feasibility and effectiveness.
FORGE successfully generated vehicle designs that enhanced design optimization and interpretability
Demonstrated an effective integration of RL with declarative modeling for design tasks
Provided a competitive alternative to traditional neural network methods.

Abstract

ABSTRACT: We present FORGE (Framework for Optimization and Reinforcement-driven Generative Engineering), a probabilistic programming framework for generative design that unifies declarative, symbolic modeling and reinforcement learning (RL). FORGE can learn and refine a design generator through RL based on simulator-derived rewards. We demonstrate FORGE across several vehicle domains. FORGE creates an extensible, interpretable foundation for generative engineering. It can act as both a data generator for machine learning and a design optimizer, offering a practical alternative to purely neural methods.

问 AI

Bookmark

View Full Paper