Abstract: A method comprising: sampling a temporal causal graph from a temporal graph distribution specifying probabilities of directed causal edges between different variables of a feature vector at a present time step, and from one variable at a preceding time step to another variables at the present time step. Based on this there are identified: a present parent which is a cause of the selected variable in the present time step, and a preceding parent which is a cause of the selected variable from the preceding time step. The method then comprises: inputting a value of each identified present and preceding parent into a respective encoder, resulting in a respective embedding of each of the present and preceding parents; combining the embeddings of the present and preceding parents, resulting in a combined embedding; inputting the combined embedding into a decoder, resulting in a reconstructed value of the selected variable.

Abstract: Embodiments of the present disclosure relate to encoding of junction area information in map data. In particular, the encoding may include organizing vehicle paths that traverse through a junction area according to path groups and organizing contentions that influence behavior of vehicles traveling along the vehicle paths according to contention groups. In addition, the encoding may include generating direction data structures that associate respective path groups with one or more of the contention groups. In these or other embodiments, the map data that corresponds to the junction area may be updated with direction data structures.

Abstract: In various examples, sensor representation generation associated with maps for autonomous and semi-autonomous systems and applications are described. For instance, systems and methods described herein use sensor data to generate sensor representations associated with portions (e.g., segments, tiles, etc.) of a map using one or more processes that cause the map to still adequately represent an environment while also reducing the amount of computing and networking resources required for generating and/or providing the map. For instance, the locations of the sensor representations may be determined such that the sensor representations still cover a substantial area of the map (e.g., an entirety of the map) while also reducing the amount of overlap between the sensor representations. Systems and methods are then disclosed that send the sensor representations to one or more machines navigating within the environment, such as based on the locations of the machine(s) when navigating.

Abstract: In various examples, a network of servers, such as a content delivery network, is used to provide a lightweight approach to hosting and serving HD map data to vehicles. The lightweight approach may allow for modifying various map components, such as tiles, layers, and/or segments. Modifying may include adding, removing, and/or updating the various components. A request to modify a first version of a High definition (HD) map may be received. Map data may be recorded that represents a second version of the HD map. A second request associated with the HD map may be received from a vehicle. Based on this second request, second map data representative of at least a portion of a layer may be identified on at least one server of the network of servers. The second map data may then be transmitted to the vehicle by the network of servers.

Abstract: In various examples, systems and methods of the present disclosure correspond to speed limit fusion for automotive systems and applications. Systems and methods are disclosed that fuse speed limit data from both one or more map sources (e.g., nav-maps, HD maps, SD maps, etc.) and a perception system, and that employ rules to help resolve conflicts in speed limits from the perception system and the map(s). For example, if a conflict occurs, the rules may indicate whether to use the speed limit data from the perception data, the speed limit data from the map(s), and/or whether to use another type of speed limit data, such as cached speed limit data.

Abstract: Embodiments of the present disclosure relate to performing navigation operations based on junction area information digested at runtime of one or more systems of a machine. In some embodiments, the junction area information may be encoded in map data corresponding to a map, and the encoding may include organizing vehicle paths that traverse through a junction area according to path groups and organizing contentions that influence behavior of vehicles traveling along the vehicle paths according to contention groups. In addition, the encoding may include generating direction data structures that associate respective path groups with one or more of the contention groups. In these or other embodiments, the map data that corresponds to the junction area may be updated with direction data structures.

Abstract: Embodiments of the present disclosure relate to encoding of junction area information in map data. In particular, the encoding may include organizing vehicle paths that traverse through a junction area according to path groups and organizing contentions that influence behavior of vehicles traveling along the vehicle paths according to contention groups. In addition, the encoding may include generating direction data structures that associate respective path groups with one or more of the contention groups. In these or other embodiments, the map data that corresponds to the junction area may be updated with direction data structures.

Abstract: In various examples, a method includes computing a current keyframe, the current keyframe being representative of an area around an autonomous vehicle at a current time based on map data. The method includes transforming a preceding keyframe to a coordinate frame of the autonomous vehicle at a first time prior to completing computation of the current keyframe to generate a first world model frame. The method includes transforming the preceding keyframe to the coordinate frame of the autonomous vehicle at a second time after the first time and prior to completing computation of the current keyframe to generate a second world model frame.

Abstract: A method comprising: sampling a temporal causal graph from a temporal graph distribution specifying probabilities of directed causal edges between different variables of a feature vector at a present time step, and from one variable at a preceding time step to another variables at the present time step. Based on this there are identified: a present parent which is a cause of the selected variable in the present time step, and a preceding parent which is a cause of the selected variable from the preceding time step. The method then comprises: inputting a value of each identified present and preceding parent into a respective encoder, resulting in a respective embedding of each of the present and preceding parents; combining the embeddings of the present and preceding parents, resulting in a combined embedding; inputting the combined embedding into a decoder, resulting in a reconstructed value of the selected variable.

Abstract: A method comprising: sampling a first causal graph from a first graph distribution modelling causation between variables in a feature vector, and sampling a second causal graph from a second graph distribution modelling presence of possible confounders, a confounder being an unobserved cause of both of two variables. The method further comprises: identifying a parent variable which is a cause of a selected variable according to the first causal graph, and which together with the selected variable forms a confounded pair having a respective confounder being a cause of both according to the second causal graph. A machine learning model encodes the parent to give a first embedding, and encodes information on the confounded pair give a second embedding. The embeddings are combined and then decoded to give a reconstructed value. This mechanism may be used in training the model or in treatment effect estimation.

Abstract: Embodiments of the present disclosure relate to encoding of junction area information in map data. In particular, the encoding may include organizing vehicle paths that traverse through a junction area according to path groups and organizing contentions that influence behavior of vehicles traveling along the vehicle paths according to contention groups. In addition, the encoding may include generating direction data structures that associate respective path groups with one or more of the contention groups. In these or other embodiments, the map data that corresponds to the junction area may be updated with direction data structures.

Abstract: In various examples, a method includes computing a current keyframe, the current keyframe being representative of an area around an autonomous vehicle at a current time based on map data. The method includes transforming a preceding keyframe to a coordinate frame of the autonomous vehicle at a first time prior to completing computation of the current keyframe to generate a first world model frame. The method includes transforming the preceding keyframe to the coordinate frame of the autonomous vehicle at a second time after the first time and prior to completing computation of the current keyframe to generate a second world model frame.

Abstract: In various examples, a network of servers, such as a content delivery network, is used to provide a lightweight approach to hosting and serving HD map data to vehicles. The lightweight approach may allow for modifying various map components, such as tiles, layers, and/or segments. Modifying may include adding, removing, and/or updating the various components. A request to modify a first version of a High definition (HD) map may be received. Map data may be recorded that represents a second version of the HD map. A second request associated with the HD map may be received from a vehicle. Based on this second request, second map data representative of at least a portion of a layer may be identified on at least one server of the network of servers. The second map data may then be transmitted to the vehicle by the network of servers.

Abstract: Disclosed is a technique for providing a mixed-reality view to user of the visualization device. The device provides the user with a real-world, real-time view of an environment of the user, on a display area of the device. The device additionally determines a location at which a virtual reality window should be displayed within the real-world, real-time view of the environment of the user, and displays the virtual reality window at the determined location within the real-world, real-time view of the environment of the user. The device may additionally display one or more augmented reality objects within the real-world, real-time view of the environment of the user.