“Robot, make me a chair” - Robohub

Researchers from MIT and collaborators have developed an AI-driven robotic assembly system that enables users to create physical objects simply by describing them in natural language. Unlike traditional computer-aided design (CAD) tools, which require specialized expertise and are often too detailed for rapid prototyping, this system uses generative AI models to translate textual prompts into 3D object geometries and then determine the placement of prefabricated components based on the object’s function and structure. The robot can assemble the object from these parts and iteratively refine the design based on user feedback, making the design process more accessible and interactive. The team demonstrated the system by fabricating furniture such as chairs and shelves from reusable structural and panel components, which can be disassembled and reassembled to minimize waste. A user study showed that over 90% of participants preferred the AI-generated designs compared to other methods. While still an initial demonstration, the framework holds promise for rapid prototyping of complex objects in fields like aerospace and architecture, and potentially for