Researchers developed LegoGPT, an AI capable of generating buildable Lego models based on text prompts, featuring options for texture and color. In testing, both robots and human testers successfully assembled the AI-generated models, demonstrating that the designs are practical and functional. Compared to other AI systems, LegoGPT excels in producing structurally sound creations. However, it has limitations, including a restricted building space and a small set of brick types, with plans for future enhancements and a broader dataset.
The researchers noted, 'Our experiments show that LegoGPT produces stable, diverse, and aesthetically pleasing Lego designs that align closely with the input text prompts.'
They acknowledged, 'Our method currently supports a fixed set of commonly used Lego bricks.'
The team found that LegoGPT produced the highest percentage of stable structures when tested against other AI systems.
Collection
[
|
...
]