Construction & Engineering

New AI copilot helps engineers design better structures

MIT researchers developed an AI copilot that uses human feedback to improve the manufacturability and strength of algorithmically designed structures.

MIT researchers introduced an AI copilot for structural design that keeps human designers involved while topology-optimization algorithms generate structures. The system presents regions of a design to a human for feedback, allowing engineers to influence the algorithm’s decisions rather than accepting an entirely automated result. In demonstrations described by MIT, the approach improved manufacturability and linear buckling load by 39 percent while adding only about 15 seconds to total design time compared with an all-algorithmic approach. The researchers believe the method could make algorithmic design more accessible and practical for a broader group of design engineers. The work applies to structures such as buildings and bridges, making it directly relevant to civil and structural engineering. Its significance lies in combining computational design with human judgment, potentially improving trust and constructability. The source describes research demonstrations and an open-access Communications Engineering paper; it does not report commercial deployment or completed building projects.

Original source: MIT News

Related RAQI solutions

In-depth analysis on RAQI Insight

Work with RAQI