The US National Science Foundation has backed researchers to teach a robotic mini cheetah how to run fast. The robot cheetah, trained to adapt to changes in the terrain by simulated experience, broke the record for the fastest run recorded.
The team utilized a “learn by experience” model to train the robot cheetah. Humans have built robots previously that can walk, lift, and jump. However, no robot had been made until now that could run fast and efficiently in the robot animal repertoire until now. Running requires robots to respond to changes in the environment and terrain fast.
Researchers have made it possible by using the learn-by-experience model, artificial intelligence, and machine learning. These helped teach the robot cheetah how to adapt to changes in its environment while in motion. Using simulated scenarios, the robot can experience and learn from different terrains quickly.
According to the researchers, training robots manually to adapt is a timely, labor-intensive, and tedious process. Teaching robots to teach themselves might solve the scalability problem and allow the robots to build a more diverse set of skills and functions, the scientists believe.