Even this quadruped robot can solve a Rubik’s Cube faster than I can.
Researchers from ETH Zürich’s Robotic Systems Lab used reinforcement learning through simulations and “teacher-student distillation” to teach a quadruped robot how to independently solve an oversized Rubik’s Cube. The feat is even more impressive given the bot has to use its stubby legs and feet to reorient the cube and rotate its sides. [Media: https://www.youtube.com/watch?v=HFdRsFiE68c]
Researchers from ETH Zürich’s Robotic Systems Lab used reinforcement learning through simulations and “teacher-student distillation” to teach a quadruped robot how to independently solve an oversized Rubik’s Cube. The feat is even more impressive given the bot has to use its stubby legs and feet to reorient the cube and rotate its sides.
Sign in to see your notifications or create an account to join the conversation.
Gathered from external sources. Rights to this text belong to whoever originally published it.