Figure's robots now walk a little less like C-3PO, thanks to reinforcement learning Figure's AI-powered controller teaches its humanoid robots to walk more like a human, with subtle improvements ...

For example, a pair of robot legs called Cassie taught itself to walk using reinforcement learning, but only after it had done so in a simulation. “The problem is your simulator will never be as ...

“If a robot cannot use legs, they cannot navigate the human world.” To have more stories like this delivered directly to your inbox, sign up for our Webby-nominated AI newsletter The Algorithm.

In a groundbreaking experiment, researchers from the ArcLab(Adaptive Robotic Controls Lab) at the University of Hong Kong(HKU) have unveiled a quadruped robot that can mimic human walking style and ...

Using reinforcement learning, they were able to achieve a new top-speed for the robot of 3.9m/s, or roughly 8.7mph. You can watch what that looks like in the video below: ...

A robot dog can learn to walk on unfamiliar and hard-to-master terrain, such as grass, bark and hiking trails, in just 20 minutes, thanks to a machine learning algorithm.

NVIDIA’s new Eureka “AI agent” utilizes GPT-4 by asking the large language model (LLM) to write its own reward-based reinforcement learning software code.

Using adaptive reinforcement learning, an AI-powered robot named Curly was able to beat human competitors in three out of four curling matches, a sport that requires strategy and precision. While ...