Abstract: Systems and methods for receiving commands at a head-wearable device and presenting artificially-intelligent (AI) assistant outputs responsive to the commands are disclosed. The method includes, while a pair of smart glasses is worn by a user, receiving a voice command from the user, at the pair of smart glasses, directed to an artificial-intelligence (AI) model, in response to receiving the voice command from the user at the pair of smart glasses directed to the AI model, obtaining, from the AI model, information that is responsive to the voice command from the user, and causing, at a display of a wrist-wearable device communicatively coupled to the pair of smart glasses, presentation of a portion of the information that is responsive to the voice command from the user.

Abstract: Systems and methods for interacting with an artificially intelligent agent at a wrist-wearable device are described. An example method includes detecting an invocation of an artificially intelligent agent, the invocation based on data associated with neuromuscular signals sensed by one or more biopotential sensors, causing capture of image data using one or more cameras included on a head-wearable device, the image data including a real-world object, providing the image data to the artificially intelligent agent, presenting, at a display of a wrist-wearable device: a representation of the real-world object and a dialogue message generated by the artificially intelligent agent, the dialogue message generated based on an object type of the real-world object and a selected set of pre-defined user-specific preferences associated with the object type of the real-world object.

Abstract: One or more instructions executed by a wrist-wearable device and/or a head-wearable device is described herein. Instructions that, when executed by a wrist-wearable device and/or a head- wearable device worn by a user, cause the wrist-wearable device and/or the head-wearable device to perform or cause performance of one or more actions. The instructions further include capturing sensor data using sensors, initiating an assistant associated with the head-wearable device and/or wrist-wearable device. The instructions further include, in accordance with a determination that the hand gesture is no longer maintained, ceasing to capture sensor data via the sensors, and providing, by the assistant, a response to the user based on the sensor data. The response includes a characterization of a scene within the sensor data and a characterization of one or more objects within the sensor data.

Abstract: A non-transitory computer readable storage medium includes instructions that are executed by one or more processors. The instructions cause the processors to, while a head-wearable device and a wrist-wearable device are communicatively coupled and worn by a user and a plurality of pending notifications is available at the head-wearable device and/or the wrist-wearable device and in response to detecting a distillation user input (i) obtain, from an AI model, a summary of the plurality of pending notifications, wherein the summary of the plurality of pending notifications includes an explanation for each pending notifications of the plurality of pending notifications, each explanation associated with a priority score and (ii) cause presentation of a representation of the summary of the plurality of pending notifications at one or more of the head-wearable device and the wrist-wearable device, the representation providing each explanation in an order based on the priority score.

Abstract: Systems and methods for smart message delivery for message handoff between communication devices and artificial reality systems are provided. In various examples, a communication device or HMD may receive a message initiating a detection of motion(s) and/or position(s) of the communication device and/or the HMD associated with a user with respect to each other. The communication device and/or the HMD may determine a movement level associated with each other, and based on the movement level relative to a predetermined threshold a message delivery process may be determined. If the predetermined threshold is not met, the message may be output to a user via audio and if the predetermined threshold is met, text associated with the message may be presented by the communication device for the user to read.

Abstract: A real-time operating system runs on a processor and dynamically manages the power state of individual circuits or resources with the processor. Thus, if a particular circuit is not needed, power to that circuit can be disabled. If a circuit is shut down, any configuration information or other type of data can be saved before powering off the circuit. Power can be re-enabled to the circuit on a responsive or predictive basis and the configuration information and/or data (collectively referred to as “state” information) can be reloaded into the circuit.