Abstract: Scheduling state transitions in an autonomous vehicle, including: detecting a transition signal for transitioning from a first state associated with a first machine learning model to a second state associated with a second machine learning model; determining whether a precondition for generating output by the second machine learning model has been satisfied; and delaying, in response for the precondition not being satisfied, a transition from the first state to the second state.

Abstract: Processing predictive input data in an autonomous vehicle, including: receiving input data for a model; determining whether the input data for the model comprises an indication that the input data was generated based on some amount of predicted data; generating, by the model and based on the input data, output data by modifying, in response to the input data comprising the indication, one or more thresholds or one or more confidence scores of the model used in generating output data; and causing an autonomous vehicle to perform one or more driving decisions based on the output data of the model.

Abstract: Modifying autonomous vehicle sensors cameras based on detected lighting boundaries, including: determining, based on video data, that a vehicle will pass through a lighting boundary; determining, based on the video data, that an illumination of a predicted input to a camera of the vehicle after passing the lighting boundary falls outside a range of illumination based on a current exposure setting of the camera; and modifying, in response to determining that the illumination of the predicted input falls outside the range of illumination, an exposure setting of one or more cameras.

Abstract: Reducing camera throughput to downstream systems using an intermediary device, including: receiving, by a device and from a camera via a first data link between the device and the camera, a frame; selecting, by the device, an area of focus for the frame; generating, by the device from the frame, a downsampled frame and a cropped frame, wherein the cropped frame is based on the area of focus; and providing, by the device to a computing system of an autonomous vehicle via a second data link between the device and the computing system, the downsampled frame and the cropped frame instead of the frame, wherein the second data link has a lower bandwidth than the first data link.

Abstract: According to an aspect of an embodiment, a method may include obtaining map data of a physical area. The map data may include surface data included in the physical area. The surface data may include locations of one or more objects at the surface. The method may also include identifying a first relationship between the map data and sensor information used by autonomous-vehicle software of an autonomous vehicle for navigation. The method may also include generating a three-dimensional environmental representation that represents the physical area based on the map data and the first relationship between the map data and the sensor information. The three-dimensional environmental representation may be configurable as a simulation environment with respect to testing the autonomous-vehicle software.

Abstract: This disclosure relates to methods and systems for vehicle simulation, testing, and validation. The method may include defining one or more test cases for a vehicle stack based on system requirements; linking the one or more test cases to one or more parameterized scenarios, where the one or more parameterized scenarios include one or more parameter permutations; and testing the vehicle stack using the one or more test cases and the one or more parameterized scenarios.

Abstract: According to an aspect of an embodiment, a method may include obtaining map data of a physical area. The map data may include surface data included in the physical area. The surface data may include locations of one or more objects at the surface. The method may also include identifying a first relationship between the map data and sensor information used by autonomous-vehicle software of an autonomous vehicle for navigation. The method may also include generating a three-dimensional environmental representation that represents the physical area based on the map data and the first relationship between the map data and the sensor information. The three-dimensional environmental representation may be configurable as a simulation environment with respect to testing the autonomous-vehicle software.

Abstract: A method may include obtaining HD mapping data including multiple data topics with one or more distinct instances. The method may include creating multiple meshes from corresponding distinct instances. The method may include defining multiple textures for each data topic. The method may include selecting a first data topic and a first distinct instance of the first data topic. The method may include selecting a first texture for the first data topic and applying the first texture to a first mesh corresponding with the first distinct instance. The method may include selecting a second distinct instance of the first data topic. The method may include selecting a second texture and applying the second texture to a second mesh corresponding with the second distinct instance. The method may also include combining the first mesh and the first texture with the second mesh and the second texture to generate a combined mesh.

Abstract: According to an aspect of an embodiment, a method may include obtaining road data and general area data of a geographic area. The method may also include obtaining filtered road data according to a first degree of accuracy based on a first relationship between the road data and sensor information used by autonomous-vehicle software of an autonomous vehicle to navigate roadways. The method may also include obtaining filtered general area data according to a second degree of accuracy based on a second relationship between the sensor information used by the autonomous-vehicle software and the general area data. The method may also include generating a three-dimensional environmental representation representing the geographic area based on the filtered road data and the filtered general area data. The three-dimensional environmental representation may be for testing the autonomous-vehicle software.