Data-oriented state space discretization for crowdsourced robot learning of physical skills

This work discusses a crowdsourced learning scheme for robot physical intelligence. Using a large amount of data from crowdsourced mentors, the scheme allows robots to synthesize new physical skills that are never demonstrated or only partially demonstrated without heavy re-training. The learning scheme features a data management method to sustainably manage continuously collected data and a growing knowledge library. The method is validated using a simulated challenge of solving a bottle puzzle. The learning scheme aims at realizing ubiquitous robot learning of physical skills and has the potential of automating many demanding tasks that are currently hard to robotize.