摘要:
A robot that uses sensor inputs for attention activation and corresponding methods, systems, and computer programs encoded on computer storage media. The robot can be configured to compute a plurality of attention signals from sensor inputs and provide the plurality of attention signals as input to the attention level classifier to generate an attention level. If a user is paying attention to the robot based on the generated attention level, the robot selects a behavior to execute based on the current attention level, wherein a behavior comprises one or more coordinated actions to be performed by the robot.
摘要:
This specification relates to robots and audio processing in robots. In general, one innovative aspect of the subject matter described in this specification can be embodied in a robot that includes: a body and one or more physically moveable components; a plurality of accessory input subsystems and one or more other sensor subsystems; one or more processors; and one or more storage devices storing instructions that are operable, when executed by the one or more processors, to cause the robot to perform operations. The operations can include: receiving one or more sensor inputs from the one or more other sensor subsystems; determining a predicted direction of a detected sound emitter based on the one or more sensor inputs of the one or more other sensor subsystems; calculating a spatial filter based on the predicted direction; obtaining, by the plurality of accessory input subsystems, respective audio inputs; and processing the respective audio inputs according to the calculated spatial filter.
摘要:
This specification relates to robots and audio processing in robots. In general, one innovative aspect of the subject matter described in this specification can be embodied in a robot that includes: a body and one or more physically moveable components; a plurality of microphones and one or more other sensor subsystems; one or more processors; and one or more storage devices storing instructions that are operable, when executed by the one or more processors, to cause the robot to perform operations. The operations can include: receiving one or more sensor inputs from the one or more other sensor subsystems; determining a predicted direction of a detected sound emitter based on the one or more sensor inputs of the one or more other sensor subsystems; calculating a spatial filter based on the predicted direction; obtaining, by the plurality of microphones, respective audio inputs; and processing the respective audio inputs according to the calculated spatial filter.
摘要:
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for audio augmentation of physical robot sounds. A robot can determine that a first physically moveable component of the robot is to be actuated and in response, obtain a conditional state of the robot. The robot can obtain an audio object that generates an audio enhancement for the first physically moveable component being actuated, the audio enhancement having one or more characteristics that match the obtained conditional state of the robot. The robot can output the audio enhancement while actuating the first physically moveable component.
摘要:
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing goal-based robot animation. One system includes a robot configured to receive a goal that specifies a goal state to be attained by the robot or one of the components. A collection of animation tracks is searched to identify one or more animation tracks that when executed by the robot cause the robot to perform one or more physical movements to satisfy the goal state. The identified one or more animation tracks are executed to perform the one or more physical movements to satisfy the received goal state.
摘要:
Mobile agents automatically manipulate components such as blocks on a working surface, to perform operations such as construction of generalized structures. The working surface and/or the components can have machine-readable codes to assist the agents in maintaining current knowledge of their respective locations. Agents identify components by type and location, and can move components according to directions; such directions can be provided by a user, or can be based on a pre-programmed directive, or can be determined dynamically based on current conditions or in response to actions of other agents. Agents may cooperate with one another. Agents can also respond to changes in the environment, alterations in works in progress, and/or other conditions, and may be configured to exhibit responses simulating emotional reactions. Different mobile agents can be associated with different character traits, which may be configured to change based on environmental conditions and/or the behavior of other mobile agents.
摘要:
A closed-loop service, referred to as an Adaptive Data Analytics Service (ADAS), characterizes the performance of a system or systems by providing information describing how users or agents are operating the system, how the system components interact, and how these respond to external influences and factors. The ADAS then builds models and/or defines relationships that can be used to optimize performance and/or to predict the results of changes made to the system(s). Subsequently, this learning provides the basis for administering, maintaining, and/or adjusting the system(s) under study. Measurement can be ongoing, even after the operating parameters or controls of a system under the administration or monitoring of the ADAS have been adjusted, so that the impact of such adjustments can be determined. This recursive process of observation, analysis, and adjustment provides a closed-loop system that affords adaptability to changing operating conditions and facilitates self-regulation and self-adjustment of systems.
摘要:
A minimum of one Master Block and one or more Activity Blocks connected (via “wireless or wired transmission”) to a System (the “electronic device”) for a digital and non-digital game, experience, or other engaging activity. Master Blocks can communicate with a System, and can connect to many Activity Blocks. Activity Blocks can communicate with Master Blocks. Furthermore, when multiple Activity Blocks are connected to a single Master Block, they create physical relationships between each other that the Master Block can detect and process and/or relay to the System as a form of input for whatever process the System is running. A user can interact with the System by manipulating the relationships between Activity Blocks and the Master Block.
摘要:
This specification relates to robots and audio processing in robots. In general, one innovative aspect of the subject matter described in this specification can be embodied in a robot that includes: a body and one or more physically moveable components; a plurality of accessory input subsystems and one or more other sensor subsystems; one or more processors; and one or more storage devices storing instructions that are operable, when executed by the one or more processors, to cause the robot to perform operations. The operations can include: receiving one or more sensor inputs from the one or more other sensor subsystems; determining a predicted direction of a detected sound emitter based on the one or more sensor inputs of the one or more other sensor subsystems; calculating a spatial filter based on the predicted direction; obtaining, by the plurality of accessory input subsystems, respective audio inputs; and processing the respective audio inputs according to the calculated spatial filter.