Abstract: Robot systems including a robot, an on-premise computing device, and a cloud services system are disclosed. An on-premise computing device includes a processor and a non-transitory memory device storing machine-readable instructions that, when executed by the processor, cause the processor to receive raw sensor data from a robot, pre-process the sensor data to remove unnecessary information from the sensor data and obtain pre-processed data, transmit the pre-processed data to a cloud services system, receive, from the cloud services system, an object type, an object pose, and an object location of an object corresponding to the pre-processed data, and transmit a signal to the robot based on at least one of the object type, the object pose, and the object location of the object.

Abstract: Methods and devices are disclosed for monitoring environmental conditions in one or more environments. In one embodiment, the method includes maintaining a plurality of environmental-condition thresholds, each of which corresponds to an environmental condition and is predetermined based on data corresponding to the environmental condition that is received from a plurality of robots. The method further includes receiving from a first robot first data corresponding to a first environmental condition in a first environment. The method may still further include making a first comparison of the first data and a first environmental-condition threshold corresponding to the first environmental condition and, based on the first comparison, triggering a notification. Triggering the notification may comprise transmitting to the robot instructions to transmit the notification to at least one of a call center and a remote device.

Abstract: Systems and devices for acquiring imagery and three-dimensional (3D) models of objects are provided. An example device includes a platform configured to enable an object to be positioned thereon, and a plurality of scanners configured to capture geometry and texture information of the object when the object is positioned on the platform. A first scanner is positioned below the platform so as to capture an image of a portion of an underside of the object, a second scanner is positioned above the platform, and a third scanner is positioned above the platform and offset from a position of the second scanner. The scanners are positioned such that each scanner is outside of a field of view of other scanners. Scanners may include a camera, a light source, and a light-dampening element, and the device may include a control module configured to operate the scanners to individually scan the object.

Abstract: Examples relating to the detection of rigid shaped objects are described herein. An example method may involve a computing system determining a first point cloud representation of an environment at a first time using a depth sensor positioned within the environment. The computing system may also determine a second point cloud representation of the environment at a second time using the depth sensor. This way, the computing system may detect a change in position of a rigid shape between a first position in the first point cloud representation and a second position in the second point cloud representation. Based on the detected change in position of the rigid shape, the computing system may determine that the rigid shape is representative of an object in the environment and store information corresponding to the object.

Abstract: Within examples, object image masking is provided. An example method includes receiving a depth mask of an object, projecting the depth mask of the object onto an image of the object in a background so as to generate a depth image of the object in the background, determining portions of the depth image of the object in the background that are representative of the object and that are representative of the background, based on the portions of the depth image of the object in the background that are representative of the object determining a foreground mask of the object, and using the foreground mask of the object to identify portions of the image representative of the object.

Abstract: Implementations disclosed herein may relate to sensor calibration based on environmental factors. An example method may involve a computing system receiving an indication of a current environment state of an area from environment state sensors. While the environment sensors indicate that the area is in a particular environment state, the system may receive data corresponding to an aspect of the area from a first sensor as well as data from additional sensors. Using the received data, the system may compare the data from the first sensor with a compilation of the data from the additional sensors to determine an accuracy metric that represents an accuracy of the first sensor when the first sensor operates in the area during the particular environment state. The system may repeat the process to determine accuracy metrics to calibrate sensors in the area depending on the environment state of the area.

Abstract: Implementations disclosed herein may include a system and method for engaging in a technique for calibrating and/or boosting the accuracy of an arrangement of sensors positioned about a physical space. In one implementation, a method includes receiving from a primary sensor an indication of a particular location of a subject and receiving a first feature from a plurality of secondary sensors. The first feature may comprise a set of estimated locations of the subject. The method may further include resolving the first feature as being indicative of the particular location, receiving a second feature from the plurality of secondary sensors, identifying a match between the second feature and the first feature, and based on the identifying, determining a location of the new subject to be the particular location.

Abstract: Example systems and methods are disclosed for associating detected attributes with an actor. An example method may include receiving point cloud data for a first actor at a first location within the environment. The method may include associating sensor data from an additional sensor with the first actor based on the sensor data being representative of the first location. The method may include identifying one or more attributes of the first actor based on the sensor data. The method may include subsequently receiving a second point cloud representative of a second actor at a second location within the environment. The method may include determining, based on additional sensor data from the additional sensor, that the second actor has the one or more attributes. The method may include providing a signal indicating that the first actor is the second actor based on the second actor having the one or more attributes.

Abstract: Methods and devices are disclosed for monitoring environmental conditions in one or more environments. In one embodiment, the method includes maintaining a plurality of environmental-condition thresholds, each of which corresponds to an environmental condition and is predetermined based on data corresponding to the environmental condition that is received from a plurality of robots. The method further includes receiving from a first robot first data corresponding to a first environmental condition in a first environment. The method may still further include making a first comparison of the first data and a first environmental-condition threshold corresponding to the first environmental condition and, based on the first comparison, triggering a notification. Triggering the notification may comprise transmitting to the robot instructions to transmit the notification to at least one of a call center and a remote device.

Abstract: Disclosed are methods and systems for determining and displaying a simulated deformation of a 3D object data model. In one aspect, a method is disclosed that includes causing a force to be applied to an object to cause a deformation of the object and causing a plurality of reference scans of the object to be captured. The method further includes, based on the plurality of reference scans, generating a 3D object data model representing the object and, further based on the plurality of reference scans, identifying a constraint point of the 3D object data model, where the constraint point represents a point of minimum deformation of the object. The method still further includes selecting a predefined deformation model, where the predefined deformation model defines a simulated deformation, and where the simulated deformation simulates at least a portion of the deformation of the object proximate to the point of minimum deformation.

Abstract: Methods and systems for comparing a 3D model of a target object to a shape-search database are provided. An example method includes using a mobile device to acquire a plurality of images of a target object, determining a 3D model based on the images, transmitting a search query that includes the 3D model, and receiving a search query result. In another example method, a server could receive a search query that includes a 3D model of an object, compare the 3D model to a shape-search database, generate a search query result based on the comparison, and transmit the search query result. The search query result could include one or more of: information regarding the target object, information regarding one or more objects similar to the target object, and a suggestion for acquiring additional images of the target object.

Abstract: Methods and devices are disclosed for monitoring environmental conditions in one or more environments. In one embodiment, the method includes maintaining a plurality of environmental-condition thresholds, each of which corresponds to an environmental condition and is predetermined based on data corresponding to the environmental condition that is received from a plurality of robots. The method further includes receiving from a first robot first data corresponding to a first environmental condition in a first environment. The method may still further include making a first comparison of the first data and a first environmental-condition threshold corresponding to the first environmental condition and, based on the first comparison, triggering a notification. Triggering the notification may comprise transmitting to the robot instructions to transmit the notification to at least one of a call center and a remote device.

Abstract: Systems and devices for acquiring imagery and three-dimensional (3D) models of objects are provided. An example device includes a platform configured to enable an object to be positioned thereon, and a plurality of scanners configured to capture geometry and texture information of the object when the object is positioned on the platform. A first scanner is positioned below the platform so as to capture an image of a portion of an underside of the object, a second scanner is positioned above the platform, and a third scanner is positioned above the platform and offset from a position of the second scanner. The scanners are positioned such that each scanner is outside of a field of view of other scanners. Scanners may include a camera, a light source, and a light-dampening element, and the device may include a control module configured to operate the scanners to individually scan the object.

Abstract: Systems and devices for acquiring imagery and three-dimensional (3D) models of objects are provided. An example device includes a platform configured to enable an object to be positioned thereon, and a plurality of scanners configured to capture geometry and texture information of the object when the object is positioned on the platform. A first scanner is positioned below the platform so as to capture an image of a portion of an underside of the object, a second scanner is positioned above the platform, and a third scanner is positioned above the platform and offset from a position of the second scanner. The scanners are positioned such that each scanner is outside of a field of view of other scanners. Scanners may include a camera, a light source, and a light-dampening element, and the device may include a control module configured to operate the scanners to individually scan the object.

Abstract: Systems are provided to facilitate imaging of a person or other target in an environment by providing modulated illumination to the target and to other aspects of the environment. Modulated illumination is provided to the target such that the target receives more illumination when a camera is capturing images of the target than during other periods of time. Modulated illumination is provided to background objects or other portions of the environment of the target such that the background or other non-target elements of the environment receive less illumination when the camera is capturing images than during other periods of time. In this way, imaging of a target can be improved by increasing effective illumination of the target while decreasing glare and other effects of illumination of background objects. The illumination can be modulated at a sufficiently high frequency that the illumination appears, to the human eye, to be substantially constant.

Abstract: Example implementations may relate to methods and systems for detecting an event in a physical region within a physical space. Accordingly, a computing system may receive from a subscriber device an indication of a virtual region within a virtual representation of the physical space such that the virtual region corresponds to the physical region. The system may also receive from the subscriber a trigger condition associated with the virtual region, where the trigger condition corresponds to a particular physical change in the physical region. The system may also receive sensor data from sensors in the physical space and a portion of the sensor data may be associated with the physical region. Based on the sensor data, the system may detect an event in the physical region that satisfies the trigger condition and may responsively provide to the subscriber a notification that indicates that the trigger condition has been satisfied.

Abstract: Methods and systems for determining the shape of an object based on shadows cast by the object are described. An example method may include receiving a plurality of images of an object casting a shadow. Each image may include a shadow cast by the object as the object is illuminated by a light source that moves over a plurality of positions. The method may further include determining, by a computing device, respectively for each image of the plurality of images a two-dimensional (2D) silhouette of the object and a respective position of the light source relative to the object. According to the method, a three-dimensional (3D) object data model of the object may be generated by the computing device based on the 2D silhouette of the object and the respective position of the light source relative to the object for each image of the plurality of images.

Abstract: Methods and devices are disclosed for monitoring environmental conditions in one or more environments. In one embodiment, the method includes maintaining a plurality of environmental-condition thresholds, each of which corresponds to an environmental condition and is predetermined based on data corresponding to the environmental condition that is received from a plurality of robots. The method further includes receiving from a first robot first data corresponding to a first environmental condition in a first environment. The method may still further include making a first comparison of the first data and a first environmental-condition threshold corresponding to the first environmental condition and, based on the first comparison, triggering a notification. Triggering the notification may comprise transmitting to the robot instructions to transmit the notification to at least one of a call center and a remote device.

Abstract: Methods and systems for controlling light arrays to determine properties of an object are described. An example method includes causing illumination of a surface of an object from multiple illumination positions using a programmable array of lights, and receiving images from an image-capture device while the surface of the object is illuminated. For example, the programmable array of lights may be modulated to cause illumination of a portion of the surface of the object from first and second illumination positions, and a first and second image of the surface of the object captured during illumination from the first and second illumination positions respectively may be received. Subsequently, a processor may determine material information for the object based on an amount of specular reflectivity for the surface of the object and reference to a database of known amounts of specular reflectivity for a plurality of materials.

Abstract: A method includes receiving first sensor data acquired by a first sensor in communication with a cloud computing system. The first sensor data has a first set of associated attributes including a time and a location at which the first sensor data was acquired. The method also includes receiving second sensor data acquired by a second sensor in communication with the cloud computing system. The second data has a second set of associated attributes including a time and a location at which the second sensor data was acquire. Further, the method includes generating a data processing result based at least in part on the first sensor data, the first set of associated attributes, the second sensor data, and the second set of associated attributes and instructing a robot in communication with the cloud computing system to perform a task based at least in part on the data processing result.