Abstract: A machine learning system builds and uses computer models for controlling robotic performance of a task. Such computer models may be first trained using feedback on computer simulations of the robotic system performing the task, and then refined using feedback on real-world trials of the robot performing the task. Some examples of the computer models can be trained to automatically evaluate robotic task performance and provide the feedback. This feedback can be used by a machine learning system, for example an evolution strategies system or reinforcement learning system, to generate and refine the controller.

Abstract: Disclosed are systems and methods for reducing the amount of messaging between aerial vehicles and between controllers of aerial vehicles and simplifying aerial vehicle traffic management. In one implementation, a large service area, such as the United States, may be separated into a series of hierarchal regions. Rather than sending notifications to all agents (e.g., aerial vehicles, controllers) in the service area, each agent may subscribe to one or more regions of the hierarchal regions and only receive messages intended for the subscribed regions. In one example, as discussed below, messages for a particular region are only sent to agents subscribed to that region. Other agents within the larger service area do not receive the messages as they may not be relevant to those agents.

Abstract: A machine learning system builds and uses computer models for controlling robotic performance of a task. Such computer models may be first trained using feedback on computer simulations of the robot performing the task, and then refined using feedback on real-world trials of the robot performing the task. Some examples of the computer models can be trained to automatically evaluate robotic task performance and provide the feedback. This feedback can be used by a machine learning system, for example an evolution strategies system or reinforcement learning system, to generate and refine the controller.

Abstract: A machine learning system builds and uses computer models for controlling robotic performance of a task. Such computer models may be first trained using feedback on computer simulations of the robot performing the task, and then refined using feedback on real-world trials of the robot performing the task. Some examples of the computer models can be trained to automatically evaluate robotic task performance and provide the feedback. This feedback can be used by a machine learning system, for example an evolution strategies system or reinforcement learning system, to generate and refine the controller.

Abstract: A machine learning system builds and uses computer models for identifying how to evaluate the level of success reflected in a recorded observation of a task. Such computer models may be used to generate a policy for controlling a robotic system performing the task. The computer models can also be used to evaluate robotic task performance and provide feedback for recalibrating the robotic control policy.

Abstract: A machine learning system builds and uses computer models for identifying how to evaluate the level of success reflected in a recorded observation of a task. Such computer models may be used to generate a policy for controlling a robotic system performing the task. The computer models can also be used to evaluate robotic task performance and provide feedback for recalibrating the robotic control policy.

Abstract: Disclosed are systems and methods for reducing the amount of messaging between aerial vehicles and between controllers of aerial vehicles and simplifying aerial vehicle traffic management. In one implementation, a large service area, such as the United States, may be separated into a series of hierarchal regions. Rather than sending notifications to all agents (e.g., aerial vehicles, controllers) in the service area, each agent may subscribe to one or more regions of the hierarchal regions and only receive messages intended for the subscribed regions. In one example, as discussed below, messages for a particular region are only sent to agents subscribed to that region. Other agents within the larger service area do not receive the messages as they may not be relevant to those agents.

Abstract: Disclosed are systems and methods for reducing the amount of messaging between aerial vehicles and between controllers of aerial vehicles and simplifying aerial vehicle traffic management. In one implementation, a large service area, such as the United States, may be separated into a series of hierarchal regions. Rather than sending notifications to all agents (e.g., aerial vehicles, controllers) in the service area, each agent may subscribe to one or more regions of the hierarchal regions and only receive messages intended for the subscribed regions. In one example, as discussed below, messages for a particular region are only sent to agents subscribed to that region. Other agents within the larger service area do not receive the messages as they may not be relevant to those agents.

Abstract: Disclosed are systems and methods for storing path data for all vehicles of a service area in a path data store and representing each path with a unique hash value, generated based on the path data. Rather than controllers and/or aerial vehicles exchanging the full path data for each path, a common hash function may be used to generate unique hash values for each path and the unique hash values may be exchanged and used to lookup the full path data.

Abstract: Techniques for single pass radiosity from depth peels are described. In one or more embodiments, radiosity for frames of a graphics presentation is computed using depth peel techniques. This may occur by rendering geometry for a frame and then computing two depth peels per frame based on the geometry, which can be used to determine occlusion of secondary bounce lights as well as color and intensity of third bounce lights for radiosity. The two depth peels may be generated in a single rendering pass by reusing rejected geometry of a front depth peel as geometry for a back depth peel. The use of depth peels in this manner enables accelerated radiosity computations for photorealistic illumination of three dimensional graphics that may be performed dynamically at frame rates typical for real-time game play and other graphics presentations.

Abstract: Techniques for single pass radiosity from depth peels are described. In one or more embodiments, radiosity for frames of a graphics presentation is computed using depth peel techniques. This may occur by rendering geometry for a frame and then computing two depth peels per frame based on the geometry, which can be used to determine occlusion of secondary bounce lights as well as color and intensity of third bounce lights for radiosity. The two depth peels may be generated in a single rendering pass by reusing rejected geometry of a front depth peel as geometry for a back depth peel. The use of depth peels in this manner enables accelerated radiosity computations for photorealistic illumination of three dimensional graphics that may be performed dynamically at frame rates typical for real-time game play and other graphics presentations.