Abstract: 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.

Abstract: 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.

Abstract: Disclosed is a decontamination robot. The robot includes a decontamination box including at least two arrays of ultraviolet LEDs, the two arrays arranged to irradiate an object placed inside the decontamination box from at least two independent directions, the decontamination box further including an interior surface with at least 90% reflectivity of ultraviolet light. The robot also includes a drivetrain including four swerve-drive units, each swerve-drive unit capable of rotating a wheel on an axis of the wheel and capable of orienting the wheel in a plane defined by the axes of the four wheels of the four swerve-drive units, whereby the four swerve-drive units coordinate to generate translational motion of the decontamination robot on a working surface.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: Disclosed is a decontamination robot. The robot includes a decontamination box including at least two arrays of ultraviolet LEDs, the two arrays arranged to irradiate an object placed inside the decontamination box from at least two independent directions, the decontamination box further including an interior surface with at least 90% reflectivity of ultraviolet light. The robot also includes a drivetrain including four swerve-drive units, each swerve-drive unit capable of rotating a wheel on an axis of the wheel and capable of orienting the wheel in a plane defined by the axes of the four wheels of the four swerve-drive units, whereby the four swerve-drive units coordinate to generate translational motion of the decontamination robot on a working surface.

Abstract: Systems, devices, and methods for making and using curved holographic optical elements (“HOEs”) are described. A hologram to apply a first optical power to playback light may be embedded in an internal volume of a curved lens, where the curved lens has a first curvature to apply a second optical power to the playback light and a second curvature opposite the first curvature to define the internal volume of the curved lens. The first optical power may be equal in magnitude and opposite in sign to the second optical power. The curved HOEs described herein are particularly well-suited for use when integrated with a curved eyeglass lens to form the transparent combiner of a virtual retina display.

Abstract: Systems, devices, and methods that integrate eye tracking capability into scanning laser projector (“SLP”)-based wearable heads-up displays are described. An infrared laser diode is added to an RGB SLP and an infrared photodetector is aligned to detect reflections of the infrared light from features of the eye. A holographic optical element (“HOE”) may be used to combine visible light, infrared light, and environmental light into the user's “field of view.” The HOE may be heterogeneous and multiplexed to apply positive optical power to the visible light and zero or negative optical power to the infrared light.

Abstract: Systems, devices, and methods that integrate eye tracking capability into scanning laser projector (“SLP”)-based wearable heads-up displays are described. An infrared laser diode is added to an RGB SLP and an infrared photodetector is aligned to detect reflections of the infrared light from features of the eye. A holographic optical element (“HOE”) may be used to combine visible light, infrared light, and environmental light into the user's “field of view.” The HOE may be heterogeneous and multiplexed to apply positive optical power to the visible light and zero or negative optical power to the infrared light.

Abstract: Systems, devices, and methods that integrate eye tracking capability into scanning laser projector (“SLP”)-based wearable heads-up displays are described. At least one narrow waveband laser diode is used in an SLP to define one or more portion(s) of a visible image. At least one corresponding narrow waveband photodetector is aligned to detect reflections of the portion(s) of the image from features of the eye. A holographic optical element (“HOE”) may be used to combine the image and environmental light into the user's “field of view.” Three narrow waveband photodetectors each responsive to a respective one of three narrow wavebands output by the RGB laser diodes of an RGB SLP are aligned to detect reflections of a projected RGB image from features of the eye.

Abstract: Systems, devices, and methods for wearable computer systems are described. A wearable heads-up display (“WHUD”) is implemented as a peripheral to a wearable electronic band worn on a limb of the user. The majority (or all) of the application storage and processing is performed on the band instead of on the WHUD, and therefore the WHUD does not include all of the hardware infrastructure necessary for application storage and processing. This significantly reduces the bulk of the WHUD and enables more aesthetically pleasing WHUD designs. Graphics processing is also performed on the band instead of on the WHUD. In some implementations, rasterized display data is wirelessly transmitted from the band to the WHUD using an ultra-wideband wireless communication scheme. Gesture-based control of content displayed by the WHUD is enabled by sensors on-board the band itself or by a third wearable component in communication with the band.

Abstract: A wearable heads-up display includes a support structure that in use is worn on a head of a user, a scanning laser projector carried by the support structure, and a holographic optical element carried by the support structure. The holographic optical element includes a set of holograms formed in one or more layers of holographic material. The set of holograms includes a red hologram that is exclusively responsive to red laser light incident thereon over a first range of angles of incidence, a green hologram that is exclusively responsive to blue laser light incident thereon over the first range of angles of incidence, and a blue hologram that is exclusively responsive to green laser light incident thereon over the first range of angles of incidence.

Abstract: A holographic optical element includes a set of holograms formed in one or more layers of holographic material. The set of holograms includes a red hologram that is exclusively responsive to a first wavelength of red light incident thereon over a first range of angles of incidence, a green hologram that is exclusively responsive to a second wavelength of green light incident thereon over the first range of angles of incidence, and a blue hologram that is exclusively responsive to a third wavelength of blue light incident thereon over the first range of angles of incidence.

Abstract: Systems, devices, and methods for engineering the eyebox of a display using multiple heterogeneous exit pupils are described. The eyebox of a display includes at least two heterogeneous exit pupils that are different from one another in terms of size and/or shape. Heterogeneous exit pupils may overlap, one may encompass another, or they may be completely spatially-separated from one another. Such configurations enable specific eyebox and/or visual display configurations that can be advantageous in certain applications. An example in which a scanning laser-based wearable heads-up virtual retina display implements a holographic combiner that is engineered to provide multiple heterogeneous exit pupils is described.

Abstract: Systems, devices, and methods that integrate eye tracking capability into scanning laser projector (“SLP”)-based wearable heads-up displays are described. At least one narrow waveband laser diode is used in an SLP to define one or more portion(s) of a visible image. At least one corresponding narrow waveband photodetector is aligned to detect reflections of the portion(s) of the image from features of the eye. A holographic optical element (“HOE”) may be used to combine the image and environmental light into the user's “field of view.” Three narrow waveband photodetectors each responsive to a respective one of three narrow wavebands output by the RGB laser diodes of an RGB SLP are aligned to detect reflections of a projected RGB image from features of the eye.

Abstract: Systems, devices, and methods for spatial multiplexing in holographic optical elements (“HOEs”) are described. A spatially-multiplexed HOE includes multiple spatially-separated holographic regions and each spatially-separated region applies a respective optical function to light that is incident thereon. An exemplary application as a spatially-multiplexed holographic combiner (“SMHC”) in a scanning laser-based wearable heads-up display (“WHUD”) is described. In this exemplary application, a scanning laser projector directs multiple light signals over the area of the SMHC and the SMHC converges the light signals towards multiple spatially-separated exit pupils at or proximate the eye of the user. The particular exit pupil at the eye of the user towards which any particular light signal is converged by the SMHC depends on the particular region of the SMHC upon which the light signal is incident.

Abstract: Systems, devices, and methods that integrate eye tracking capability into scanning laser projector (“SLP”)-based wearable heads-up displays are described. An infrared laser diode is added to an RGB SLP and an infrared photodetector is aligned to detect reflections of the infrared light from features of the eye. A holographic optical element (“HOE”) may be used to combine visible light, infrared light, and environmental light into the user's “field of view.” The HOE may be heterogeneous and multiplexed to apply positive optical power to the visible light and zero or negative optical power to the infrared light.

Abstract: Systems, devices, and methods that integrate eye tracking capability into scanning laser projector (“SLP”)-based wearable heads-up displays are described. At least one narrow waveband laser diode is used in an SLP to define one or more portion(s) of a visible image. At least one corresponding narrow waveband photodetector is aligned to detect reflections of the portion(s) of the image from features of the eye. A holographic optical element (“HOE”) may be used to combine the image and environmental light into the user's “field of view.” Three narrow waveband photodetectors each responsive to a respective one of three narrow wavebands output by the RGB laser diodes of an RGB SLP are aligned to detect reflections of a projected RGB image from features of the eye.

Abstract: Systems, devices, and methods for making and using curved holographic optical elements (“HOEs”) are described. A hologram to apply a first optical power to playback light may be embedded in an internal volume of a curved lens, where the curved lens has a first curvature to apply a second optical power to the playback light and a second curvature opposite the first curvature to define the internal volume of the curved lens. The first optical power may be equal in magnitude and opposite in sign to the second optical power. The curved HOEs described herein are particularly well-suited for use when integrated with a curved eyeglass lens to form the transparent combiner of a virtual retina display.