Teaching robots to navigate new environments is tough. You can train them on physical, real-world data taken from recordings made by humans, but that’s scarce, and expensive to collect. Digital simulations are a rapid, scalable way to teach them to do new things, but the robots often fail when they’re pulled out of virtual worlds and asked to do the same tasks in the real one.
Now, there’s potentially a better option: a new system that uses generative AI models in conjunction with a physics simulator to develop virtual training grounds that more accurately mirror the physical world. Robots trained using this method worked with a higher success rate than those trained using more traditional techniques during real-world tests.
Researchers used the system, called LucidSim, to train a robot dog in parkour, getting it to scramble over a box and climb stairs, despite never seeing any real world data. The approach demonstrates how helpful generative AI could be when it comes to teaching robots to do challenging tasks. It also raises the possibility that we could ultimately train them in entirely virtual worlds. Read the full story.
—Rhiannon Williams
Africa’s AI researchers are ready for takeoff
When we talk about the global race for AI dominance, the conversation often focuses on tensions between the US and China, and European efforts at regulating the technology. But it’s high time we talk about another player: Africa.
African AI researchers are forging their own path, developing tools that answer the needs of Africans, in their own languages. Their story is not only one of persistence and innovation, but of preserving cultures and fighting to shape how AI technologies are used on their own continent. However, they face many barriers. Read the full story.
—Melissa Heikkilä