The network is given the entirety of the first demonstration and a single observation from the second demonstration. Each training example is a pair of demonstrations that perform the same task. It is trained on dozens of different tasks with thousands of demonstrations for each task. The network learns this from the distribution of training examples. But how does the imitation network know how to generalize? Thus, the imitation network must generalize the demonstration to a new setting. The imitation network observes a demonstration, processes it to infer the intent of the task, and then accomplishes the intent starting from another starting configuration. (The vision system is never trained on a real image.) As before, the vision network is trained with hundreds of thousands of simulated images with different perturbations of lighting, textures, and objects. The vision network ingests an image from the robot's camera and outputs state representing the positions of the objects. The system is powered by two neural networks: a vision network and an imitation network. Our system can learn a behavior from a single demonstration delivered within a simulator, then reproduce that behavior in different setups in reality.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |