Abstract: The present invention extends to methods, systems, and computer program products for using Unmanned Aerial Vehicles (UAVs) to inspect autonomous vehicles. An autonomous vehicle carries a UAV (or “drone”) in a protected area, for example, in a glove compartment, trunk, etc. Between rides, the UAV can be deployed to inspect the autonomous vehicle. Images from the UAV can be sent to other components for image analysis. When an inspection is completed, the UAV can return to the protected area. The UAV can inspect both the interior and exterior of an autonomous vehicle. When an inspection is passed, the autonomous vehicle can begin a new ride. When an inspection is failed, the autonomous vehicle can report for repairs or summon a tow vehicle.

Abstract: A vehicle is disclosed that includes systems for adjusting the transmittance of one or more windows of the vehicle. The vehicle may include a camera outputting images taken of an occupant within the vehicle. The vehicle may also include an artificial neural network running on computer hardware carried on-board the vehicle. The artificial neural network may be trained to classify the occupant of the vehicle using the images captured by the camera as input. The vehicle may further include a controller controlling transmittance of the one or more windows based on classifications made by the artificial neural network. For example, if the artificial neural network classifies the occupant as squinting or shading his or her eyes with a hand, the controller may reduce the transmittance of a windshield, side window, or some combination thereof.

Abstract: A method for determining lane information includes receiving perception data from at least two sensors, the at least two sensors including a rear facing camera of a vehicle. The method includes determining, based on the perception data, a number of lanes on a roadway within a field of view captured by the perception data using a neural network. The method includes providing an indication of the number of lanes to an automated driving system or driving assistance system.

Abstract: The present invention extends to methods, systems, and computer program products for using Unmanned Aerial Vehicles (UAVs) to inspect autonomous vehicles. An autonomous vehicle carries a UAV (or “drone”) in a protected area, for example, in a glove compartment, trunk, etc. Between rides, the UAV can be deployed to inspect the autonomous vehicle. Images from the UAV can be sent to other components for image analysis. When an inspection is completed, the UAV can return to the protected area. The UAV can inspect both the interior and exterior of an autonomous vehicle. When an inspection is passed, the autonomous vehicle can begin a new ride. When an inspection is failed, the autonomous vehicle can report for repairs or summon a tow vehicle.

Abstract: A method for detecting stubs or intersecting roadways includes receiving perception data from at least two sensors. The at least two sensors include a rear facing camera of a vehicle and another sensor. The perception data includes information for a current roadway on which the vehicle is located. The method includes detecting, based on the perception data, an intersecting roadway connecting with the current roadway. The method also includes storing an indication of a location and a direction of the intersecting roadway with respect to the current roadway.

Abstract: A vehicle is disclosed that includes systems for adjusting the transmittance of one or more windows of the vehicle. The vehicle may include a camera outputting images taken of an occupant within the vehicle. The vehicle may also include an artificial neural network running on computer hardware carried on-board the vehicle. The artificial neural network may be trained to classify the occupant of the vehicle using the images captured by the camera as input. The vehicle may further include a controller controlling transmittance of the one or more windows based on classifications made by the artificial neural network. For example, if the artificial neural network classifies the occupant as squinting or shading his or her eyes with a hand, the controller may reduce the transmittance of a windshield, side window, or some combination thereof.

Abstract: A vehicle is disclosed that includes systems for adjusting the transmittance of one or more windows of the vehicle. The vehicle may include a camera outputting images taken of an occupant within the vehicle. The vehicle may also include an artificial neural network running on computer hardware carried on-board the vehicle. The artificial neural network may be trained to classify the occupant of the vehicle using the images captured by the camera as input. The vehicle may further include a controller controlling transmittance of the one or more windows based on classifications made by the artificial neural network.

Abstract: A vehicle is disclosed that includes systems for adjusting the transmittance of one or more windows of the vehicle. The vehicle may include a camera outputting images taken of an occupant within the vehicle. The vehicle may also include an artificial neural network running on computer hardware carried on-board the vehicle. The artificial neural network may be trained to classify the occupant of the vehicle using the images captured by the camera as input. The vehicle may further include a controller controlling transmittance of the one or more windows based on classifications made by the artificial neural network. For example, if the artificial neural network classifies the occupant as squinting or shading his or her eyes with a hand, the controller may reduce the transmittance of a windshield, side window, or some combination thereof.

Abstract: A method for determining lane information includes receiving perception data from at least two sensors, the at least two sensors including a rear facing camera of a vehicle. The method includes determining, based on the perception data, a number of lanes on a roadway within a field of view captured by the perception data using a neural network. The method includes providing an indication of the number of lanes to an automated driving system or driving assistance system.

Abstract: A method for detecting stubs or intersecting roadways includes receiving perception data from at least two sensors. The at least two sensors include a rear facing camera of a vehicle and another sensor. The perception data includes information for a current roadway on which the vehicle is located. The method includes detecting, based on the perception data, an intersecting roadway connecting with the current roadway. The method also includes storing an indication of a location and a direction of the intersecting roadway with respect to the current roadway.