Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space. In some embodiments, ground truth training data for the neural network(s) may be generated from LIDAR data. More specifically, a scene may be observed with RADAR and LIDAR sensors to collect RADAR data and LIDAR data for a particular time slice. The RADAR data may be used for input training data, and the LIDAR data associated with the same or closest time slice as the RADAR data may be annotated with ground truth labels identifying objects to be detected. The LIDAR labels may be propagated to the RADAR data, and LIDAR labels containing less than some threshold number of RADAR detections may be omitted. The (remaining) LIDAR labels may be used to generate ground truth data.

Abstract: Systems and methods are disclosed that relate to freespace detection using machine learning models. First data that may include object labels may be obtained from a first sensor and freespace may be identified using the first data and the object labels. The first data may be annotated to include freespace labels that correspond to freespace within an operational environment. Freespace annotated data may be generated by combining the one or more freespace labels with second data obtained from a second sensor, with the freespace annotated data corresponding to a viewable area in the operational environment. The viewable area may be determined by tracing one or more rays from the second sensor within the field of view of the second sensor relative to the first data. The freespace annotated data may be input into a machine learning model to train the machine learning model to detect freespace using the second data.

Abstract: A deep neural network(s) (DNN) may be used to detect objects from sensor data of a three dimensional (3D) environment. For example, a multi-view perception DNN may include multiple constituent DNNs or stages chained together that sequentially process different views of the 3D environment. An example DNN may include a first stage that performs class segmentation in a first view (e.g., perspective view) and a second stage that performs class segmentation and/or regresses instance geometry in a second view (e.g., top-down). The DNN outputs may be processed to generate 2D and/or 3D bounding boxes and class labels for detected objects in the 3D environment. As such, the techniques described herein may be used to detect and classify animate objects and/or parts of an environment, and these detections and classifications may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Abstract: Disclosed herein are system, method, and computer program product embodiments for clustering lane segments of a roadway in order to improve and simplify autonomous vehicle behavior testing. The approaches disclosed herein provide a hybrid methodology of dividing lane segments into hard features and soft features, and using a metric learning model trained in a supervised process on the entirety of lane segment features to cluster the lane segments based on the soft features. These clustered lane segments can then be assigned to what is termed as protolanes, where a single set of tests applied to a given protolane is considered valid across all of the lane segments assigned to the protolane.

Abstract: Disclosed herein are system, method, and computer program product aspects for testing autonomous vehicle intent using protolanes. For example, the method includes selecting a first lane segment of a roadway within a geonet, wherein the geonet comprises a plurality of lane segments. It is determined that the first lane segment corresponds to a protolane of a set of protolanes, wherein the protolane is associated with one or more additional lane segments of the plurality of lane segments. The protolane is associated with the first lane segment based on the determination that the first lane segment corresponds to the protolane.

Abstract: Methods and systems to provide supplemental content to a user who is viewing video or other content. The user's device (through which he will access the video) then provides an identifier of that video to a server or other computing facility. Here, the video identifier is used to identify supplemental content that corresponds to the user's video. The supplemental content is then provided to the user device for the user's consumption. The supplemental content may be structured in such a way that pieces of the supplemental content are accessible at particular points in the video. The piece(s) of the supplemental content available at a particular point in the video will be related to one or more objects that are present at this point. This allows a user to access one or more pieces of supplemental content in a context-specific manner, at a point in the video where the piece(s) of supplemental content are relevant.

Abstract: Methods and systems to improve the efficiency of a content delivery system. A local distribution node is introduced to the network, between the content provider and the end user device (i.e., the leaf node). The local distribution node is responsible for servicing a localized subset of the leaf nodes that would otherwise be serviced by a conventional server of the content delivery system. Requests for content are received at the local distribution node from leaf nodes, and content is received at the local distribution node for transmission to the leaf node(s). Content may be cached at the local distribution node to allow faster service of subsequent requests for this content. Caching may also be used to make the channel surfing process more efficient. If demand is high, a leaf node may be promoted to serve as an additional local distribution node. Leaf nodes may also share content among themselves.

Abstract: Methods and systems to improve the efficiency of a content delivery system. A local distribution node is introduced to the network, between the content provider and the end user device (i.e., the leaf node). The local distribution node is responsible for servicing a localized subset of the leaf nodes that would otherwise be serviced by a conventional server of the content delivery system. Requests for content are received at the local distribution node from leaf nodes, and content is received at the local distribution node for transmission to the leaf node(s). Content may be cached at the local distribution node to allow faster service of subsequent requests for this content. Caching may also be used to make the channel surfing process more efficient. If demand is high, a leaf node may be promoted to serve as an additional local distribution node. Leaf nodes may also share content among themselves.

Abstract: Methods and systems to improve the efficiency of a content delivery system. A local distribution node is introduced to the network, between the content provider and the end user device (i.e., the leaf node). The local distribution node is responsible for servicing a localized subset of the leaf nodes that would otherwise be serviced by a conventional server of the content delivery system. Requests for content are received at the local distribution node from leaf nodes, and content is received at the local distribution node for transmission to the leaf node(s). Content may be cached at the local distribution node to allow faster service of subsequent requests for this content. Caching may also be used to make the channel surfing process more efficient. If demand is high, a leaf node may be promoted to serve as an additional local distribution node. Leaf nodes may also share content among themselves.

Abstract: Methods and systems to improve the efficiency of a content delivery system. A local distribution node is introduced to the network, between the content provider and the end user device (i.e., the leaf node). The local distribution node is responsible for servicing a localized subset of the leaf nodes that would otherwise be serviced by a conventional server of the content delivery system. Requests for content are received at the local distribution node from leaf nodes, and content is received at the local distribution node for transmission to the leaf node(s). Content may be cached at the local distribution node to allow faster service of subsequent requests for this content. Caching may also be used to make the channel surfing process more efficient. If demand is high, a leaf node may be promoted to serve as an additional local distribution node. Leaf nodes may also share content among themselves.

Abstract: Methods and systems to indicate events of interest to a user. IN an embodiment, an event processor queries each of a plurality of event data sources, then receives event data from one or more event data source. The event processor then identifies an event to be indicated to a user device based on the event data. The identified event to the user through a user device. The event processor may receive, via the user device, feedback regarding the identified event. This feedback may be used to train future event identification. The event processor may be implemented at a computing device that is remote from the user, such as a server. Alternatively, the event processor may be implemented internal to the user device.

Abstract: Methods and systems to improve the efficiency of a content delivery system. A local distribution node is introduced to the network, between the content provider and the end user device (i.e., the leaf node). The local distribution node is responsible for servicing a localized subset of the leaf nodes that would otherwise be serviced by a conventional server of the content delivery system. Requests for content are received at the local distribution node from leaf nodes, and content is received at the local distribution node for transmission to the leaf node(s). Content may be cached at the local distribution node to allow faster service of subsequent requests for this content. Caching may also be used to make the channel surfing process more efficient. If demand is high, a leaf node may be promoted to serve as an additional local distribution node. Leaf nodes may also share content among themselves.

Abstract: Methods and systems to indicate events of interest to a user. IN an embodiment, an event processor queries each of a plurality of event data sources, then receives event data from one or more event data source. The event processor then identifies an event to be indicated to a user device based on the event data. The identified event to the user through a user device. The event processor may receive, via the user device, feedback regarding the identified event. This feedback may be used to train future event identification. The event processor may be implemented at a computing device that is remote from the user, such as a server. Alternatively, the event processor may be implemented internal to the user device.

Abstract: Methods and systems to provide supplemental content to a user who is viewing video or other content. The user's device (through which he will access the video) then provides an identifier of that video to a server or other computing facility. Here, the video identifier is used to identify supplemental content that corresponds to the user's video. The supplemental content is then provided to the user device for the user's consumption. The supplemental content may be structured in such a way that pieces of the supplemental content are accessible at particular points in the video. The piece(s) of the supplemental content available at a particular point in the video will be related to one or more objects that are present at this point. This allows a user to access one or more pieces of supplemental content in a context-specific manner, at a point in the video where the piece(s) of supplemental content are relevant.

Abstract: Methods and systems to provide supplemental content to a user who is viewing video or other content. The user's device (through which he will access the video) then provides an identifier of that video to a server or other computing facility. Here, the video identifier is used to identify supplemental content that corresponds to the user's video. The supplemental content is then provided to the user device for the user's consumption. The supplemental content may be structured in such a way that pieces of the supplemental content are accessible at particular points in the video. The piece(s) of the supplemental content available at a particular point in the video will be related to one or more objects that are present at this point. This allows a user to access one or more pieces of supplemental content in a context-specific manner, at a point in the video where the piece(s) of supplemental content are relevant.