Google Inc.

Deepmind Technologies Limited

Pierre Sermanet

Yevgen Chebotar

Yunfei Bai

Seyed Mohammad Khansari Zadeh

Andrew Zisserman

Harrison Lynch

Soeren Pirk

Yusuf Aytar

Jonathan Tompson

Debidatta Dwibedi

Techniques are disclosed that enable processing a video capturing a periodic activity using a repetition network to generate periodic output (e.g., a period length of the periodic activity captured in the video and/or a frame wise periodicity indication of the video capturing the periodic activity). Various implementations include a class agnostic repetition network which can be used to generate periodic output for a wide variety of periodic activities. Additional or alternative implementations include generating synthetic repetition videos which can be utilized to train the repetition network.

Class agnostic repetition counting in video(s) utilizing a temporal self-similarity matrix

There are provided systems, methods, and apparatus, for optimizing a policy controller to control a robotic agent that interacts with an environment to perform a robotic task. One of the methods includes optimizing the policy controller using a neural network that generates numeric embeddings of images of the environment and a demonstration sequence of demonstration images of another agent performing a version of the robotic task.

Optimizing policy controllers for robotic agents using image embeddings

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting intermediate reinforcement learning goals. One of the methods includes obtaining a plurality of demonstration sequences, each of the demonstration sequences being a sequence of images of an environment while a respective instance of a reinforcement learning task is being performed; for each demonstration sequence, processing each image in the demonstration sequence through an image processing neural network to determine feature values for a respective set of features for the image; determining, from the demonstration sequences, a partitioning of the reinforcement learning task into a plurality of subtasks, wherein each image in each demonstration sequence is assigned to a respective subtask of the plurality of subtasks; and determining, from the feature values for the images in the demonstration sequences, a respective set of discriminative features for each of the plurality of subtasks.

Unsupervised detection of intermediate reinforcement learning goals

Training a machine learning model (e.g., a neural network model such as a convolutional neural network (CNN) model) so that, when trained, the model can be utilized in processing vision data (e.g., from a vision component of a robot), that captures an object, to generate a rich object-centric embedding for the vision data. The generated embedding can enable differentiation of even subtle variations of attributes of the object captured by the vision data.

Training a deep neural network model to generate rich object-centric embeddings of robotic vision data

This description relates to a neural network that has multiple network parameters and is configured to receive an input observation characterizing a state of an environment and to process the input observation to generate a numeric embedding of the state of the environment. The neural network can be used to control a robotic agent. The network can be trained using a method comprising: obtaining a first observation captured by a first modality; obtaining a second observation that is co-occurring with the first observation and that is captured by a second, different modality; obtaining a third observation captured by the first modality that is not co-occurring with the first observation; determining a gradient of a triplet loss that uses the first observation, the second observation, and the third observation; and updating current values of the network parameters using the gradient of the triplet loss.

Growing community of inventors

Palo Alto, CA, United States of America

Pierre Sermanet