Los investigadores de Google est\u00e1n utilizando el aprendizaje por imitaci\u00f3n para ense\u00f1ar a los robots aut\u00f3nomos c\u00f3mo caminar, girar y moverse de manera m\u00e1s \u00e1gil. Usando un conjunto de datos de captura de movimiento de varios sensores conectados a un perro, los investigadores le ense\u00f1aron a un robot cuadr\u00fapedo llamado Laikago varios movimientos diferentes que son dif\u00edciles de lograr a trav\u00e9s de controles rob\u00f3ticos codificados a mano tradicionales.<\/p>\n
What they did:<\/strong>\u00a0Using a data set of motion capture data recorded from various sensors attached to a dog, the researchers taught a quadruped robot named Laikago several different movements that are hard to achieve through traditional hand-coded robotic controls.<\/p>\n How they did it:<\/strong>\u00a0First, they used the motion data from the real dog to construct simulations of each maneuver, including a dog trot, side-step, and \u2026 a dog version of classic \u201980s dance move, the running man. (The last one was not, in fact, performed by the real dog itself. The researchers manually animated the simulated dog to dance to see if that would translate to the robot as well.) They then matched together key joints on the simulated dog and the robot to make the simulated robot move in the exact same way as the animal. Using reinforcement learning, it then learned to stabilize the movements and correct for differences in weight distribution and design. Finally, the researchers were able to port the final control algorithm into a physical robot in the lab\u2014though some moves, like the running man, weren\u2019t entirely successful.<\/p>\n