In a recent paper, Google’s DeepMind Robotics team introduced a robot that can compete at human levels in table tennis. reports TechCrunch post.
During the tests, the robot managed to beat all entry-level players and won 55% of the matches against intermediate players. However, despite the impressive results, the robot lost all the fights with professionals. Overall, the system won 45% of the 29 matches played.
The main problem of the system is the delay in response to fast balls and the difficulty in playing backhand, receiving high and low balls, and evaluating the spin of the ball. The developers recommend investigating advanced control algorithms and hardware optimizations to address the latency limitations that hinder the robot’s response time to fast balls.
The DeepMind team is confident in the promise of the development, which they see as just one small step toward a long-standing goal in robotics: achieving human-level performance in many useful real-world skills. The developers plan to continue creating universal robots that can perform many useful tasks while interacting with humans deftly and safely.
Previously in the US Congress anxious the coming invasion of humanoid robots.
What are you thinking?
Source: Gazeta
Jackson Ruhl is a tech and sci-fi expert, who writes for “Social Bites”. He brings his readers the latest news and developments from the world of technology and science fiction.