Google DeepMind Watch posted an update
Google DeepMind has trained simulated bodies to climb walls, jump between planks and recover after falling, Mashable reports. The work focuses on flexible motor skills that could be reused across different simulated bodies, rather than teaching one figure a single set routine.
Why it mattersThe training took place on digital obstacle courses, not with physical robots. Still, learning to cope with varied terrain without specific instructions is a useful step towards adaptable control, not just a tidier walk cycle.
Discuss: How much should progress in simulation count as evidence that a robot will cope with the untidy real world?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.