MIT builds AI copilot for live topology optimization
Start here
MIT researchers have built an AI "copilot" that lets engineers give feedback on regions of a structure while topology optimization is still running, rather than waiting for a finished design. In demonstrations, the system improved manufacturability and linear buckling load by 39 percent while adding only 15 seconds to total design time, according to MIT News. The copilot relies on machine learning trained on synthetic human-feedback data. For now, users can only make regions of a structure thicker or thinner; the researchers say they hope to add other modification options in future versions.
Generated from reports · updated 1 h ago
Report timeline
Follow the reports to see the event from different sides.
- MIT NewsMIT researchers build an AI "copilot" for topology optimization in structural design
MIT researchers developed an AI copilot that lets engineers give feedback on regions of a structure while topology optimization is still running, instead of waiting for the final design. In demonstrations it improved manufacturability and linear buckling load by 39 percent while adding only 15 seconds to total design time. The system uses machine learning trained on synthetic human feedback data, and currently only lets users thicken or thin regions.
Heat for this event
Not enough continuous observations yet to draw a trend.