Robot dogs can learn to walk in an hour: Mimicking animal instincts, research has been published in a Nature sub-publication

When a typical robot walks, machine learning uses a lot of calculations to pre-design the details of each leg's movement, which consumes a lot of power. Morti uses this feedback data to learn how to walk without the need for extensive calculations. morti can reduce energy consumption as it learns to walk. The study found that after Morti walked for an hour, it used 42% less energy than when it first started walking.

In general, artificial intelligence can learn a specific task very well, but artificial intelligence cannot recalibrate when the environment changes," said Dhireesha Kudithipudi, a professor at the University of Texas at San Antonio. Whereas Morti can autonomously adjust its movement patterns based on data feedback, it may perform better at recalibrating the environment."

Conclusion: Combining artificial intelligence and biology to explore more possibilities for robots

Rupert's robot dog can learn autonomously like a living creature through artificial intelligence algorithms. This not only combines machine learning technology, but also involves the biological field.

If this technology could be used on a large scale, there would be two benefits: First, machine learning would be more energy efficient and consume less energy. Instead of violent calculations based on large amounts of data, machines could become "smarter" through autonomous learning. Second, this technology can bring inspiration for the combination of artificial intelligence and biological fields.

At present, this technology can make the robot dog become more like animals. In the future, with the development of this technology, robots may become more human-like.