Techniques described herein relate to using reduced-dimensionality embeddings generated
from robot sensor data to identify predetermined semantic labels that guide robot interaction …

Techniques described herein relate to generating a posteriori knowledge about where
objects are typically located within environments to improve object location. In various …

(57) ABSTRACT A grasp management system and corresponding methods are described. In
some examples, information about a set of grasps of a robotic manipulator is accessed. The …

Some implementations of this specification are directed generally to deep machine learning
methods and apparatus related to predicting motion (s)(if any) that will occur to object (s) in …

Implementations relate to using deep reinforcement learning to train a model that can be
utilized, at each of a plurality of time steps, to determine a corresponding robotic action for …

BACKGROUND [0001] Various machine learning based approaches to robotic control have
been proposed. Some of those approaches train a machine learning model (eg, a deep …

Methods, apparatus, systems, and computer-readable media are provided for generating
spatial affordances for an object, in an environment of a robot, and utilizing the generated …

Methods, apparatus, and computer-readable media for determining and utilizing corrections
to robot actions. Some implementations are directed to updating a local features model of a …

In at least one embodiment, a system determines a set of possible grasp poses that allow a
robot to successfully grasp an object by generating a set of potential grasp poses, and then …

Methods, systems, and apparatus, including computer-read able media, for robot grasp
learning. In some implementa tions, grasp data describing grasp attempts by robots is …