
The researchers additionally expanded the system’s skills by including texture and coloration choices. For instance, utilizing an look immediate like “Electrical guitar in metallic purple,” LegoGPT can generate a guitar mannequin, with bricks assigned a purple coloration.
Testing with robots and people
To show their designs labored in actual life, the researchers had robots assemble the AI-created Lego fashions. They used a dual-robot arm system with power sensors to choose up and place bricks in accordance with the AI-generated directions.
Human testers additionally constructed a few of the designs by hand, exhibiting that the AI creates genuinely buildable fashions. “Our experiments present that LegoGPT produces secure, numerous, and aesthetically pleasing Lego designs that align intently with the enter textual content prompts,” the staff famous in its paper.
When examined towards different AI techniques for 3D creation, LegoGPT stands out by means of its concentrate on structural integrity. The staff examined towards a number of alternate options, together with LLaMA-Mesh and different 3D era fashions, and located its method produced the very best share of secure buildings.
A video of two robotic arms constructing a LegoGPT creation, supplied by the researchers.
Nonetheless, there are some limitations. The present model of LegoGPT solely works inside a 20×20×20 constructing house and makes use of a mere eight normal brick varieties. “Our technique at present helps a set set of generally used Lego bricks,” the staff acknowledged. “In future work, we plan to develop the brick library to incorporate a broader vary of dimensions and brick varieties, reminiscent of slopes and tiles.”
The researchers additionally hope to scale up their coaching dataset to incorporate extra objects than the 21 classes at present out there. In the meantime, others can actually construct on their work—the researchers launched their dataset, code, and fashions on their venture web site and GitHub.

The researchers additionally expanded the system’s skills by including texture and coloration choices. For instance, utilizing an look immediate like “Electrical guitar in metallic purple,” LegoGPT can generate a guitar mannequin, with bricks assigned a purple coloration.
Testing with robots and people
To show their designs labored in actual life, the researchers had robots assemble the AI-created Lego fashions. They used a dual-robot arm system with power sensors to choose up and place bricks in accordance with the AI-generated directions.
Human testers additionally constructed a few of the designs by hand, exhibiting that the AI creates genuinely buildable fashions. “Our experiments present that LegoGPT produces secure, numerous, and aesthetically pleasing Lego designs that align intently with the enter textual content prompts,” the staff famous in its paper.
When examined towards different AI techniques for 3D creation, LegoGPT stands out by means of its concentrate on structural integrity. The staff examined towards a number of alternate options, together with LLaMA-Mesh and different 3D era fashions, and located its method produced the very best share of secure buildings.
A video of two robotic arms constructing a LegoGPT creation, supplied by the researchers.
Nonetheless, there are some limitations. The present model of LegoGPT solely works inside a 20×20×20 constructing house and makes use of a mere eight normal brick varieties. “Our technique at present helps a set set of generally used Lego bricks,” the staff acknowledged. “In future work, we plan to develop the brick library to incorporate a broader vary of dimensions and brick varieties, reminiscent of slopes and tiles.”
The researchers additionally hope to scale up their coaching dataset to incorporate extra objects than the 21 classes at present out there. In the meantime, others can actually construct on their work—the researchers launched their dataset, code, and fashions on their venture web site and GitHub.