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: Aspects of the disclosure provide for automatically generating labels for sensor data. For instance, first sensor data, for a vehicle may be identified. This first sensor data may have been captured by a first sensor of the vehicle at a first location during a first point in time and may be associated with a first label for an object. Second sensor data for the vehicle may be identified. The second sensor data may have been captured by a second sensor of the vehicle at a second location at a second point in time outside of the first point in time. The second location is different from the first location. A determination may be made as to whether the object is a static object. Based on the determination that the object is a static object, the first label may be used to automatically generate a second label for the second sensor data.

Abstract: Aspects of the disclosure relate to training a labeling model to automatically generate labels for objects detected in a vehicle's environment. In this regard, one or more computing devices may receive sensor data corresponding to a series of frames perceived by the vehicle, each frame being captured at a different time point during a trip of the vehicle. The computing devices may also receive bounding boxes generated by a first labeling model for objects detected in the series of frames. The computing devices may receive user inputs including an adjustment to at least one of the bounding boxes, the adjustment corrects a displacement of the at least one of the bounding boxes caused by a sensing inaccuracy. The computing devices may train a second labeling model using the sensor data, the bounding boxes, and the adjustment to increase accuracy of the second labeling model when automatically generating bounding boxes.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium that validates labels associated with sensor measurements of a scene in an environment. One of the methods includes receiving data representing a sensor measurement of a scene in an environment generated by one or more sensors. The sensor measurement can be associated with one or more labels, and each label can identify a portion of the sensor measurement that has been classified as measuring an object in the environment. For each of the labels, a determination can be made as to whether the label satisfies each of the validation criteria. Each validation criterion can measure whether one or more characteristics of the label are consistent with one or more characteristics of real-world objects in the environment.

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, computer systems, and apparatus, including computer programs encoded on computer storage media, for generating and editing object track labels for objects detected in video data. One of the methods includes obtaining a video segment comprising multiple image frames associated with multiple time points; obtaining object track data specifying a set of object tracks; providing, for presentation to a user, a user interface for modifying the object track data, the user interface displaying object timeline representations of the object tracks; receiving one or more user inputs that indicate one or more modifications to the object timeline representations; updating the object timeline representations displayed in the timeline display area; and updating the object track data according to the updated object timeline representations.

Abstract: Aspects of the disclosure provide for automatically generating labels for sensor data. For instance, first sensor data for a vehicle may be identified. This first sensor data may have been captured by a first sensor of the vehicle at a first location during a first point in time and may be associated with a first label for an object. Second sensor data for the vehicle may be identified. The second sensor data may have been captured by a second sensor of the vehicle at a second location at a second point in time outside of the first point in time. The second location is different from the first location. A determination may be made as to whether the object is a static object. Based on the determination that the object is a static object, the first label may be used to automatically generate a second label for the second sensor data.

Abstract: Aspects of the disclosure provide for automatically generating labels for sensor data. For instance, first sensor data for a first vehicle may be identified. This first sensor data may have been captured by a first sensor of the vehicle at a first location during a first point in time and may be associated with a first label for an object. Second sensor data for a vehicle may be identified. The second sensor data may have been captured by a second sensor of the vehicle at a second location at a second point in time outside of the first point in time. The second location is different from the first location. The object is a static object may be determined. Based on the determination that the object is a static object, the first label may be used to automatically generate a second label for the second sensor data.

Abstract: Aspects of the disclosure relate to facilitating review of labels. For instance, a first type of label for a first set of labels and a second type of label for a second set of labels may be received. The first set of labels may be generated by a first labeling source and may classify one or more objects captured by a sensor of a vehicle. The second set of labels may be generated by a second labeling source different from the first labeling source and may classify the one or more objects. A search is conducted for objects associated with both the first type of labels for the first set of labels and the second type of label for the second set of labels in order to identify search results. The histograms may be generated from the search results and histograms may be provided for display to a human operator.

Abstract: Aspects of the disclosure relate to training a labeling model to automatically generate labels for objects detected in a vehicle's environment. In this regard, one or more computing devices may receive sensor data corresponding to a series of frames perceived by the vehicle, each frame being captured at a different time point during a trip of the vehicle. The computing devices may also receive bounding boxes generated by a first labeling model for objects detected in the series of frames. The computing devices may receive user inputs including an adjustment to at least one of the bounding boxes, the adjustment corrects a displacement of the at least one of the bounding boxes caused by a sensing inaccuracy. The computing devices may train a second labeling model using the sensor data, the bounding boxes, and the adjustment to increase accuracy of the second labeling model when automatically generating bounding boxes.

Abstract: Aspects of the disclosure relate to generating a grid or a visual list to facilitate operator review of labels. The system receives a first set of labels generated by a first labeling source and a second set of labels generated by a second labeling source. The first set of labels and the second set of labels each classify one or more objects perceived in one or more scenes captured by a sensor of a vehicle, such that each of the one or more objects has a corresponding first label and a corresponding second label. The system determines discrepancies between the corresponding first label and the corresponding second label for each of the one or more objects, and generates a grid or a visual list using the determined discrepancies. The system provides the grid or the visual list for display to a human operator.

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: A communication system is provided that includes a controller providing a map of information to enable communication with a plurality of nodes. The information includes identification of two separate time slots, one for random access requests when a node initially contacts a controller and another for exclusively assigned access to transmit messages. The map further provides information to enable identification of the nodes and assigns transmission frequencies.

Abstract: A communication system is provided for communication between network nodes and communication controllers. The communication controllers transmit common mode signals C1-C4 in small communication areas between two controllers to enable mobile nodes to be handed off from one controller to another. A node will use the low power common mode signals C1-4 that have common frequencies between two controllers during handoff, and then transition to higher power communication frequencies such as f1-f4 that are used for transmission of general telephone signal messages after handoff. A single communication controller may use multiple common mode signals to overlapping with other controllers, thus providing a wider spectrum of common mode signals than dedicated telephone signals used after handoff.

Abstract: A network communication system is provided for communication between network nodes, including individual nodes and a communication controller. In the network, signals are transmitted from the communication controller to identify a slot of a frame in which individual nodes may transmit a request to transmit data. When a first individual node has data to transmit, the first node transmits a request signal to the controller in its identified slot, the request including randomly generated information (RGI) for identification of the node. In response to the request signal, the controller transmits a grant signal along with the RGI back to the first node to allow the first node to identify the grant.

Abstract: A communication system is provided that includes nodes and communication controllers each operating with multiple antennas. During communications, the communication controller assigns timeslots to individual nodes for transmitting requests to a controller. When an individual node has data to transmit, the node transmits a request signal to a communication controller over the assigned timeslot. After receipt of a grant, the node transmits the data message in packetized form to the controller. The request, grant and data message can be transmitted and received using multiple antennas on both the node and the controller.

Abstract: A communication system is provided for communication between network nodes and multiple communication controllers. The communication method provides for request timeslot management, assigning request timeslots to individual nodes. In the network, when an individual node has data to transmit, the node transmits a request signal to a communication controller over an assigned timeslot. For a first node in the network area of a first controller communicating with a second node in the network area of a second communication controller, data is relayed between the first and second communication controllers to enable communication between the first and second nodes. Acknowledgement back that communication is successful is made by a node to a controller indicating a grant was successfully received by the node.

Abstract: A communication system is provided for communication between network nodes and a communication controller. In the network, a request signal is transmitted from a first node to the communication controller to allow communication with a second node. After grant of the request by the controller, the first node sends its data through the communication controller to the second node. The second node sends an acknowledgement through the communication controller to the first node once the data message is received. The first node then acknowledges receipt of the acknowledgment by the second node.

Abstract: A network node in a communication system which transmits at least two reservation requests in order for the node to obtain radio resources for transmitting data. In the network, downstream signals are transmitted from the central control node to identify at least one upstream request opportunity in which nodes may transmit a request signal to the central control node. When a first individual node has data to transmit, the first individual node transmits a request signal to the central control node within the at least one upstream request opportunity. Subsequent to receiving the request signal, the central control node transmits a subsequent downstream signal specifying at least one subsequent request opportunity wherein the first individual node is assigned to subsequently transmit a subsequent request signal. In response to receiving the subsequent downstream signal, the node transmits a subsequent request signal in the subsequent request opportunity assigned to the node.

Abstract: A communication system is provided for communication between network nodes and a communication controller. In the network, a reservation request is transmitted from a node to the communication controller in an assigned timeslot. In response the controller provides a grant of permission to the requesting node to transmit packet data containing a message. The timeslot assigned to the requesting node is one of a series of timeslots occurring repeatedly on a separate frequency. The timeslots will be continuously available to receive requests from nodes irrespective of transmission of data from one node to the controller, or transmission of a grant from the controller to a node.