Google's AI bots are learning to get around obstacles

A hilarious new video reveals the clumsy progress of AI'parkour,' as scientists work to teach computer systems how to navigate'challenging terrains and obstacles.' DeepMind researchers have trained a number of simulated bodies, including a headless'walker,' a four-legged'ant,' and a 3D humanoid, to learn more complex behaviours as they carry out different locomotion tasks. The results, while comical, show how these systems can learn to improve their own techniques as they interact with the different environments, eventually allowing them to run, jump, crouch and turn as needed. Footage from the study offers a hilarious look into the trial-and-error process. As the team explains in the paper, the environments presented to the simulated bodies are of varying levels of difficulty.