A robot dog chased down a ball and clambered over obstacles after learning the skills from images and video generated by artificial intelligence.
Ge Yang at the Massachusetts Institute of Technology and his colleagues developed their training platform “LucidSim” by taking a popular computer simulation software that follows the principles of real-world physics and inserting a generative AI model to produce artificial environments such as a stone pathway.
They also used OpenAI’s ChatGPT to generate thousands of text descriptions that were fed into the…
