IHMC Teaches Atlas to Walk Like a Human

Re:IHMC Teaches Atlas to Walk Like a Human by warent on Thursday December 13, 2018 @05:44PM (#18676829)

Another reminder of how incredibly powerful our brains are. Walking and motor skills seem like such basic things because we start mastering them as toddlers. Meanwhile, teams of experts across the world are still trying to figure out how to get a robot to do it. For example, they're talking about finding out the location of where to toe-off based on some instantaneous capture point. None of that ever consciously came to my mind, but these crazy calculations are constantly running in the background.

[ Parent | on HN ]

Re:IHMC Teaches Atlas to Walk Like a Human by krapp on Thursday December 13, 2018 @05:53PM (#18676883)

This is known as Moravec's Paradox[0]. Fine motor skills and basic visual cognition require far more computational effort than high-level reasoning.

[0]https://medium.com/@froger_mcs/moravecs-paradox-c79bf638103f

[ Parent | on HN ]

Re:IHMC Teaches Atlas to Walk Like a Human by dwaltrip on Thursday December 13, 2018 @08:47PM (#18677755)

I think it is a bit generous to call an AI's behavior in those areas "high-level reasoning" :)

It is certainly quite impressive. But it seems to me that the paradox is neatly solved by comparing the how well-constrained the activity is.

Movement and (especially) visual processing are incredibly general problems. Where as board games are very narrow, well-constrained problems.

It always interesting when people expect AI to robustly and effectively process visual content without first actually understanding the world (which obviously no AI is even close to doing).

[ Parent | on HN ]

Re:IHMC Teaches Atlas to Walk Like a Human by maxerickson on Friday December 14, 2018 @01:19PM (#18683080)

A lot of animals are walking a few minutes after they are born. The parts of the brain that take care of it seem to be more hard wired.

[ Parent | on HN ]