Sanctuary Cognitive Systems Corporation

Systems, methods, and computer program products for managing and populating environment models are described. An environment model is accessed which represents an environment, and the environment model is populated with instances of object models. Locations where the instances of object models should be positioned in the environment model are identified, by determining where in the environment model a respective size of each instance when viewed from a vantage point at the environment model matches a size of the object represented by the respective instance when viewed from a corresponding vantage point at the environment.

Systems, methods, and computer program products for managing and populating environment models are described. An environment model is accessed which represents an environment, and the environment model is populated with instances of object models. Locations where the instances of object models should be positioned in the environment model are identified, by determining where in the environment model a respective size of each instance when viewed from a vantage point at the environment model matches a size of the object represented by the respective instance when viewed from a corresponding vantage point at the environment.

Systems, methods, and computer program products for managing and populating environment models are described. An environment model is accessed which represents an environment, and the environment model is populated with instances of object models. Locations where the instances of object models should be positioned in the environment model are identified, by determining where in the environment model a respective size of each instance when viewed from a vantage point at the environment model matches a size of the object represented by the respective instance when viewed from a corresponding vantage point at the environment.

Systems, methods, and computer program products for generating training data are described. Action data and context data are recorded for a robot body performing an action or task in an environment. The context data is augmented virtually to include variations from the recorded environment while the action data remains unchanged, and instances of training data are generated including the augmentations, to produce a large and varied training data set.

In an implementation, a stereo vision system comprises a first, a second, and a third camera. The first and second cameras are separated by a first baseline, the second and third cameras by a second baseline, and the first and third cameras by a third baseline. The third baseline is greater than the second baseline which is greater than the first baseline. The stereo vision system is operable to determine a first depth characterization of a first object using data received from the first camera and the second camera, determine a second depth characterization of a second object using data received from the second camera and the third camera, and determine a third depth characterization of a third object using data received from the first camera and the third camera. The third object is farther away than the second object which is farther away than the first object.

Systems, methods, and computer program products for generating training data are described. Action data and context data are recorded for a robot body performing an action or task in an environment. The context data is augmented virtually to include variations from the recorded environment while the action data remains unchanged, and instances of training data are generated including the augmentations, to produce a large and varied training data set.

Systems, methods, and computer program products for managing simulated environments are described. A simulated environment is accessed which represents a physical environment, and representations of objects are included, maintained, or removed in the simulated environment based on whether objects are represented in image data of the physical environment, and based on whether objects are occluded by other objects in the image data of the physical environment. Future occlusion can also be predicted based on motion paths of objects.

The present disclosure describes systems, robots, and methods for organizing and selecting classifiers of a library of classifiers. The classifiers of the library of classifiers can be organized in a relational model, such as a hierarchy or probability model. Instead of storing, activating, or executing the entire library of classifiers at once by a robot system, computational resource demand is reduced by executing subset of classifiers to determine context, and the determined context is used as a basis for selection of another subset of classifiers. This process can be repeated, to iteratively refine context and select more specific subsets of classifiers. A selected subset of classifiers can eventually be specific to a task to be performed by the robot system, such that the robot system can take action based on output from executing such specific classifiers.

Machine vision apparatus, methods and articles advantageously employ neural networks to parse or evaluate a three-dimensional environment which may, for example, be useful in robotics. Such may advantageously allow detection of objects (e.g., targets, obstacles, or even portions of the robot itself or neighboring robots) in a three-dimensional environment using limited physical computational resources, limited processing time, and/or with a high level of accuracy. Detection may include representation of a volume occupied by an object in the three-dimensional environment and/or a pose (i.e., position and orientation) of the object in the three-dimensional environment. Such may, for example, allow a robot to engage or otherwise interact with one or more target objects while avoiding obstacles in the three-dimensional environment, for instance while the robot operates autonomously and/or in real-time in the three-dimensional environment.

The present disclosure describes systems, robots, and methods for organizing and selecting classifiers of a library of classifiers. The classifiers of the library of classifiers can be organized in a relational model, such as a hierarchy or probability model. Instead of storing, activating, or executing the entire library of classifiers at once by a robot system, computational resource demand is reduced by executing subset of classifiers to determine context, and the determined context is used as a basis for selection of another subset of classifiers. This process can be repeated, to iteratively refine context and select more specific subsets of classifiers. A selected subset of classifiers can eventually be specific to a task to be performed by the robot system, such that the robot system can take action based on output from executing such specific classifiers.