Abstract: Among other things, techniques are described for operating an autonomous vehicle station. One technique involves receiving information indicating arrival of a vehicle at a station designated for a primary service. The technique further involves measuring, using at least one sensor located in the station, a first parameter associated with the vehicle. Also, the technique involves performing, based on the information and the first parameter, a first action to provide the primary service to the vehicle. Additionally, the technique involves determining, while performing the first action, a secondary service to provide to the vehicle.

Abstract: A method for semantic annotation of sensor data may include obtaining sensor data representing an image of a geographic area. The boundary points defining a first polygon in the image of the geographic area may be determined based on the sensor data. An overlap between the first polygon and a second polygon in the image of the geographic area may be detected based at least on the boundary points defining the first polygon. At least one of the first polygon or the second polygon may be modified to remove the overlap between the first polygon and the second polygon. An annotation corresponding to the first polygon may be generated based on the modifying of at least one of the first polygon or the second polygon. The annotation may identify a physical feature within the geographic area. Related systems and computer program products are also provided.

Abstract: The present disclosure is directed to a computer system and techniques for updating map data used for navigating an autonomous vehicle. In some embodiments, the computer system is configured to obtain map data including a starting location and a destination location; obtain a plurality of travel times corresponding to a plurality of respective possible routes for traveling from the starting location to the destination location; obtain benefit information for at least a first respective possible route; and determine a selected route based on the travel times and the benefit information. In some embodiments, the computer system is configured to obtain a route between a starting location and a destination location; obtain map-age information for the route; determine a first set of driving parameters for the autonomous vehicle based on the map-age information; and navigate the autonomous vehicle along the route using the first set of driving parameters.

Abstract: Among other things, methods for generating maps using hyper-graph data structures are disclosed. The method can include receiving and storing data from at least one sensor of a vehicle in an environment. The method can include generating, based on the received data, a graph, having at least one node corresponding to at least one subgraph. The at least one subgraph can include subgraph nodes corresponding to geographical and/or logical positions. The subgraph nodes can be connected by subgraph edges representing spatial constraints and/or logical connections. The at least one subgraph can include contextual data classifying each of the subgraph nodes according to a property of the environment associated with the subgraph.

Abstract: Provided are methods for aligning a raster map of a geographic area with a geodata map of the geographic area. A method includes obtaining, using at least one processor, the raster map of the geographic area. A distance map corresponding to the raster map of the geographic area may be generated. The raster map may be aligned with a geodata map of the geographic area by deforming the geodata map relative to the distance map in order to maximize a coverage of the geodata map over the raster map. An updated geodata map of the geographic area may be generated based on the aligning. Related systems and computer program products are also provided.

Abstract: A method for semantic annotation of sensor data may include obtaining sensor data representing an image of a geographic area. The boundary points defining a first polygon in the image of the geographic area may be determined based on the sensor data. An overlap between the first polygon and a second polygon in the image of the geographic area may be detected based at least on the boundary points defining the first polygon. At least one of the first polygon or the second polygon may be modified to remove the overlap between the first polygon and the second polygon. An annotation corresponding to the first polygon may be generated based on the modifying of at least one of the first polygon or the second polygon. The annotation may identify a physical feature within the geographic area. Related systems and computer program products are also provided.

Abstract: Provided are methods, systems, and computer program products for machine-learning based point cloud alignment classification. An example method may include: obtaining at least two light detection and ranging (LiDAR) point clouds; processing the at least two LiDAR point clouds using at least one classifier network; obtaining at least one output dataset from the at least one classifier network; determining that the at least two LiDAR point clouds are misaligned based on the at least one output dataset; and performing a first action based on the determining that the at least two LiDAR point clouds are misaligned.

Abstract: Among other things, techniques are described for operating an autonomous vehicle station. One technique involves receiving information indicating arrival of a vehicle at a station designated for a primary service. The technique further involves measuring, using at least one sensor located in the station, a first parameter associated with the vehicle. Also, the technique involves performing, based on the information and the first parameter, a first action to provide the primary service to the vehicle. Additionally, the technique involves determining, while performing the first action, a secondary service to provide to the vehicle.

Abstract: Techniques are disclosed for utilizing passenger attention data captured in vehicles for vehicle localization and location-based services. In an embodiment, a method includes receiving sensor data from one or more sensors of an autonomous vehicle operating in an environment, and generating passenger attention data for a passenger of the autonomous vehicle using the sensor data. A processing circuit determines one or more physical features in the environment based on the passenger attention data. The processing circuit obtains physical feature data associated with the physical feature(s) and initiates one or more actions on the AV based at least in part on the physical feature data. The actions include but are not limited to requesting content for physical features(s) and assisting in localization of the autonomous vehicle.

Abstract: The present disclosure is directed to a computer system and techniques for updating map data used for navigating an autonomous vehicle. In some embodiments, the computer system is configured to obtain map data including a starting location and a destination location; obtain a plurality of travel times corresponding to a plurality of respective possible routes for traveling from the starting location to the destination location; obtain benefit information for at least a first respective possible route; and determine a selected route based on the travel times and the benefit information. In some embodiments, the computer system is configured to obtain a route between a starting location and a destination location; obtain map-age information for the route; determine a first set of driving parameters for the autonomous vehicle based on the map-age information; and navigate the autonomous vehicle along the route using the first set of driving parameters.

Abstract: Techniques are disclosed for utilizing passenger attention data captured in vehicles for vehicle localization and location-based services. In an embodiment, a method includes receiving sensor data from one or more sensors of an autonomous vehicle operating in an environment, and generating passenger attention data for a passenger of the autonomous vehicle using the sensor data. A processing circuit determines one or more physical features in the environment based on the passenger attention data. The processing circuit obtains physical feature data associated with the physical feature(s) and initiates one or more actions on the AV based at least in part on the physical feature data. The actions include but are not limited to requesting content for physical features(s) and assisting in localization of the autonomous vehicle.

Abstract: Among other things, methods for generating maps using hyper-graph data structures are disclosed. The method can include receiving and storing data from at least one sensor of a vehicle in an environment. The method can include generating, based on the received data, a graph, having at least one node corresponding to at least one subgraph. The at least one subgraph can include subgraph nodes corresponding to geographical and/or logical positions. The subgraph nodes can be connected by subgraph edges representing spatial constraints and/or logical connections. The at least one subgraph can include contextual data classifying each of the subgraph nodes according to a property of the environment associated with the subgraph.