Google develops table tennis robot that can catch 340 times in one round

Visit the original URL

IT House reported on October 20th. Yesterday, Google announced that it is working on a “ping-pong robot” project that can catch the ball 340 times in one round when playing against humans.

At present, Google emphasizes that this is just a “cooperation” between humans and AI, not to defeat humans, but with the speed of AI growth, it will soon start against professional players.

The project, called i-Sim2Real, is not just about ping pong, but about building a robotic system that can work with fast-paced and relatively unpredictable human behavior. The advantages of table tennis are that it is fairly restricted (compared to playing basketball or cricket) and strikes a balance between complexity and simplicity. In the process, machine-learning models are taught what to do in a virtual environment or simulation, and that knowledge is then applied, with the goal of playing catch-up rounds with humans for as long as possible without mistakes.

IT Home has learned that in addition to the i-Sim2Real method of alternating simulation and reality, Google researchers are also exploring a method of learning using only real data, namely the GoalsEye project, the former can alternately learn strategies in simulation and reality, While the latter learning from real-world unstructured data, combined with self-training, is effective for learning target-conditioned policies with precise and dynamic requirements.

media coverage

CNBeta Sohu Sina Technology IT Home Pinwan
Related events

This article is reprinted from: https://readhub.cn/topic/8keuzkx5Uwe
This site is for inclusion only, and the copyright belongs to the original author.