Capturing Structural Intuition + Teaching to Teaming

Good structural design depends on judgment that is hard to write down: how a designer reads a design brief, conceptualizes a scheme, and knows when a structure feels right. We present a human-AI co-design framework that keeps the designer in the loop throughout training and deployment. The model learns implicit design knowledge directly from human demonstrations and collaborates with the designer through iterative back-and-forth on a shared artifact.

Teaching-to-teaming framework: demonstration in the Bridge Designer, curation in the Gallery, correction in the Inspector, and a flow-based policy training cycle, with the human in the loop.

→ Project Overview

We developed GooGym2D, an open-source 2D structural design testbed based on the Gymnasium API. It frames truss design as graph construction in continuous space, with terminal finite-element analysis checking connectivity, mechanisms, yielding, and buckling. The pieces form a single human-in-the-loop cycle — teaching becomes teaming.

Demonstration

Designers build bridges in the browser. 323 seed demonstrations across three spans capture different ways of solving the same structural problem.

Correction

A flow-matching policy learns a distribution of plausible design actions. The AI acts first; the designer replays its rollouts and takes over only where it fails.

Co-design

The trained policy returns to the Bridge Designer as a partner, offering ghost-bar continuations while the designer keeps the final say.

Bridge Designer web interface with AI Assist suggesting ghost-bar continuations for a 10 m bridge.
Bridge Designer — build bridges in the browser; AI Assist offers ghost-bar continuations.
Bridge Gallery: curated successful bridge demonstrations at 8, 10, and 12 m spans.
Bridge Gallery — replay, compare, and curate successful bridges before training.
Rollout Inspector replaying a policy rollout so the designer can take over and correct it.
Rollout Inspector — replay the policy’s rollouts and take over where they fail.

→ Publications

  • Capturing Structural Intuition: Human-Gated Imitation Learning for Structural Design with Flow Matching
    Tao Sun, Shaoyi Wang, Simon Schleicher, Ramon E. Weber · IASS 2026
  • From Teaching to Teaming: Human-AI Co-Design Environment for Architectural and Structural Design
    Tao Sun, Shaoyi Wang, Simon Schleicher, Ramon E. Weber · ACADIA 2026

Explore the full interactive project page, best viewed on desktop: luposun.github.io/GooGym2D

Leave a Reply