Abstract: Inspection robots with removeable interface plates and method for configuring payload interfaces are described. An example robot may include a payload, with at least one sensor, mounted to a housing of the inspection robot. The housing may include a removeable interface plate coupled to the at least one sensor and to an electronic board, the electronic board positioned within the housing. The removeable interface plate may define an electrical coupling interface compatible with the payload, and the electronic board may include an electrical processing configuration compatible with the payload.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for searching an autonomous vehicle sensor data repository. One of the methods includes maintaining a collection of sensor samples and, for each sensor sample, an embedding of the sensor sample; receiving a request specifying a query sensor sample, wherein the query sensor sample characterizes a query environment region; and identifying, from the collection of sensor samples, a plurality of relevant sensor samples that characterize similar environment regions to the query environment region, comprising: processing the query sensor sample through the embedding neural network to generate a query embedding; and identifying, from sensor samples in a subset of the sensor samples in the collection, a plurality of sensor samples that have embeddings that are closest to the query embedding.

Abstract: This description provides an autonomous or semi-autonomous excavation vehicle that is capable of navigating through a dig site and carrying out an excavation routine using a system of sensors physically mounted to the excavation vehicle. The sensors collects any one or more of spatial, imaging, measurement, and location data representing the status of the excavation vehicle and its surrounding environment. Based on the collected data, the excavation vehicle executes instructions to carry out an excavation routine. The excavation vehicle is also able to carry out numerous other tasks, such as checking the volume of excavated earth in an excavation tool, and helping prepare a digital terrain model of the site as part of a process for creating the excavation routine.

Abstract: This description provides an autonomous or semi-autonomous excavation vehicle that is capable of navigating through a dig site and carrying out an excavation routine using a system of sensors physically mounted to the excavation vehicle. The sensors collect any one or more of spatial, imaging, measurement, and location data representing the status of the excavation vehicle and its surrounding environment. Based on the collected data, the excavation vehicle executes instructions to carry out an excavation routine. The excavation vehicle is also able to carry out numerous other tasks, such as checking the volume of excavated earth in an excavation tool and helping prepare a digital terrain model of the site as part of a process for creating the excavation routine.

Abstract: A non-invasive analyte sensor includes one or more temperatures sensors that sense the temperatures of one or more components of the analyte sensor. The sensed temperature(s) can be used to post-process (i.e. correct) the data collected by the analyte sensor and/or used to adjust operation of the analyte sensor.

Abstract: A non-invasive analyte sensor includes a receive side with a superheterodyne circuit. The superheterodyne circuit include a mixer with an input that is electrically connected to a receive antenna, and a radio frequency generator connected to another input of the mixer and that is configured to generate a radio frequency signal. The mixer outputs a signal that is based on a frequency of a signal received by the receive antenna and the frequency of the signal generated by the radio frequency generator.

Abstract: This description provides an autonomous or semi-autonomous excavation vehicle that is capable of navigating through a dig site and carrying out an excavation routine using a system of sensors physically mounted to the excavation vehicle. The sensors collects any one or more of spatial, imaging, measurement, and location data representing the status of the excavation vehicle and its surrounding environment. Based on the collected data, the excavation vehicle executes instructions to carry out an excavation routine. The excavation vehicle is also able to carry out numerous other tasks, such as checking the volume of excavated earth in an excavation tool, and helping prepare a digital terrain model of the site as part of a process for creating the excavation routine.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a classifier to detect open vehicle doors. One of the methods includes obtaining a plurality of initial training examples, each initial training example comprising (i) a sensor sample from a collection of sensor samples and (ii) data classifying the sensor sample as characterizing a vehicle that has an open door; generating a plurality of additional training examples, comprising, for each initial training example: identifying, from the collection of sensor samples, one or more additional sensor samples that were captured less than a threshold amount of time before the sensor sample in the initial training example was captured; and training the machine learning classifier on first training data that includes the initial training examples and the additional training examples to generate updated weights for the machine learning classifier.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for open vehicle doors prediction using a neural network model. One of the methods includes: obtaining sensor data (i) that includes a portion of a point cloud generated by a laser sensor of an autonomous vehicle and (ii) that characterizes a vehicle that is in a vicinity of the autonomous vehicle in an environment; and processing the sensor data using an open door prediction neural network to generate an open door prediction that predicts a likelihood score that the vehicle has an open door.

Abstract: An access control system includes a plurality of physical access control readers that form a reader network which utilizes a first communication protocol. The system includes a plurality of mobile communication devices each having a first communication interface and a second communication interface. The first communication interface enables the mobile communication devices to access a mobile communication network which utilizes a second communication protocol, and the second communication interlace enables the mobile communication devices to communicate with the access control readers. The plurality of physical access control readers exchange status information for the plurality of physical access control readers and for the plurality of mobile communication devices over the reader network.

Abstract: A shield assembly includes a closing structure configured to be disposed over an opening of an enclosure. The closing structure includes an inner surface configured to face an inside of the enclosure when the closing structure is closed and a finger bracket structure mounted on the inner surface, the finger bracket structure having a bracket and one or more finger gaskets coupled to the bracket. An electromagnetic interference (EMI) shielded gasket disposed along a portion of the opening of the enclosure shields an edge of the opening of the enclosure or a radio frequency (RF) fence bracket coupled to a frame disposed around the opening of the enclosure creates a narrow path between the frame and the closing structure, the narrow path attenuating RF signals passing through the narrow path and shielding an edge of the opening of the enclosure.

Abstract: An access control system includes a plurality of physical access control readers that form a reader network which utilizes a first communication protocol. The system includes a plurality of mobile communication devices each having a first communication interface and a second communication interface. The first communication interface enables the mobile communication devices to access a mobile communication network which utilizes a second communication protocol, and the second communication interlace enables the mobile communication devices to communicate with the access control readers. The plurality of physical access control readers exchange status information for the plurality of physical access control readers and for the plurality of mobile communication devices over the reader network.

Abstract: An occluder detection system is disclosed. At least one occluder element moves according to a cam motion to apply a periodic compression to a flexible infusion line. A portion of the occluder element is configured to emit or modify an energy or magnetic field. A sensor is configured to measure the energy being emitted or modified by the section of the occluder element. A processor causes the at least one occluder element to move according to the cam motion to move a fluid within the flexible infusion line by periodically compressing the flexible infusion line, measures the energy of the energy source via the sensor, obtains a current cam state associated with the cam motion at a time corresponding to the measured energy, and determines, based on the measured energy and the current cam state, a state of the occluder element. The processor may issue an alarm on a fault condition.

Abstract: An access control system includes a plurality of physical access control readers that form a reader network which utilizes a first communication protocol. The system includes a plurality of mobile communication devices each having a first communication interface and a second communication interface. The first communication interface enables the mobile communication devices to access a mobile communication network which utilizes a second communication protocol, and the second communication interface enables the mobile communication devices to communicate with the access control readers. The plurality of physical access control readers exchange status information for the plurality of physical access control readers and for the plurality of mobile communication devices over the reader network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a classifier to detect open vehicle doors. One of the methods includes obtaining a plurality of initial training examples, each initial training example comprising (i) a sensor sample from a collection of sensor samples and (ii) data classifying the sensor sample as characterizing a vehicle that has an open door; generating a plurality of additional training examples, comprising, for each initial training example: identifying, from the collection of sensor samples, one or more additional sensor samples that were captured less than a threshold amount of time before the sensor sample in the initial training example was captured; and training the machine learning classifier on first training data that includes the initial training examples and the additional training examples to generate updated weights for the machine learning classifier.

Abstract: This description provides an autonomous or semi-autonomous excavation vehicle that is capable of navigating through a dig site and carrying out an excavation routine using a system of sensors physically mounted to the excavation vehicle. The sensors collects any one or more of spatial, imaging, measurement, and location data representing the status of the excavation vehicle and its surrounding environment. Based on the collected data, the excavation vehicle executes instructions to carry out an excavation routine. The excavation vehicle is also able to carry out numerous other tasks, such as checking the volume of excavated earth in an excavation tool, and helping prepare a digital terrain model of the site as part of a process for creating the excavation routine.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a student machine learning model using a teacher machine learning model that has a pre-trained feature extractor.

Abstract: A drone comprises at least one propeller for generating lift and an article containment area for containing an article to be carried by the drone. The floor of the article containment area comprises a dynamic support surface for supporting the article and allowing the article to move into, out of and through the article containment area. The dynamic support surface may be a conveyor belt forming the floor of the article containment area.

Abstract: A secure receptacle includes within it a vertically-aligned carousel having a plurality of securable containers horizontally disposed around the carousel. Each container includes a securable lid preventing access to the contents of the container, and the vertically-aligned carousel is configured to lock in a secured position. A sensor within the secure receptacle determines a position of the carousel, and a motorized controller rotates the carousel to a requested position. On determining a requested container, the carousel is rotated so that the requested container is moved from a current position to the opening of the secure receptacle, and the securable lid of the requested container is actuated to provide access to its contents.

Abstract: This description provides an autonomous or semi-autonomous excavation vehicle that is capable of navigating through a dig site and carrying out an excavation routine using a system of sensors physically mounted to the excavation vehicle. The sensors collects any one or more of spatial, imaging, measurement, and location data representing the status of the excavation vehicle and its surrounding environment. Based on the collected data, the excavation vehicle executes instructions to carry out an excavation routine. The excavation vehicle is also able to carry out numerous other tasks, such as checking the volume of excavated earth in an excavation tool, and helping prepare a digital terrain model of the site as part of a process for creating the excavation routine.