Children usually learn to tie their shoes by age 5 or 6. At the same time, robots have been trying to master this task for several decades. It looks like the developers at Google DeepMind have made some progress on this. In addition, they succeeded in teaching the robot to perform some other actions that require dexterity.
Image Source: Google DeepMind
Researchers at Google DeepMind have demonstrated a training method that can teach a robot to perform certain dexterity tasks, such as tying shoelaces, hanging up shirts, and even fixing other robots.
Some success has been achieved in this direction thanks to the new ALOHA Unleashed training platform and its own modeling program DemoStart, which allows robots to learn by observing people.
The DeepMind team’s research primarily demonstrates how robotic systems can learn to perform fairly complex tasks by learning from visual demonstrations. However, this work also has important practical implications, since such robots may be useful, especially for assisting people with disabilities.
The small Mars drone Ingenuity has proven that flying machines have good prospects for aerial…
The small Mars drone Ingenuity has proven that flying machines have good prospects for aerial…
The Chinese company Zephyr, which is famous for its non-standard approach to design, presented the…
To celebrate its 50th anniversary, Microsoft has added a host of new features to its…
Japanese company Kawasaki presented a new type of personal transport — literally an iron horse…
Japanese company Kawasaki presented a new type of personal transport — literally an iron horse…