Abstract: An imaging system and method of providing localization data to a vehicle using the imaging system is disclosed. The method may comprise: capturing, from an electronic depth camera, one or more images, wherein the one or more images include at least a portion of the vehicle; and using a deep neural network and the one or more images, determining a multi-degree of freedom (MDF) pose of the vehicle, wherein an optical axis of the electronic depth camera is oriented along a Z-axis according to a Cartesian coordinate system (comprising an X-axis, a Y-axis, and the Z-axis), wherein the Z-axis is plumb with respect to Earth.

Abstract: A system, comprising a computer that includes a processor and a memory, the memory storing instructions executable by the processor to input a red-green-blue (RGB) image and an eccentricity image to a neural network which outputs a located object based on combining the RGB image and the eccentricity image, wherein the eccentricity image is based on a per-pixel rolling average and a per-pixel rolling variance over a moving window of k video frames. The memory can further include instructions executable by the processor to receive the located object at a computing device included in one or more of a vehicle or a traffic information system.

Abstract: Detection of an impact to a vehicle is based on data received from one of (a) one or more infrastructure sensors included in an infrastructure element or (b) the vehicle. Verification of the impact is determined by determining that data received from the other of the infrastructure sensors or the vehicle (a) detects the impact and is verified or (b) does not detect the impact and is unverified. A message is transmitted to the vehicle including the verification of the impact and one of (a) a request to operate to a predetermined location based on the impact being verified or (b) a notification to continue a current operation based on the impact being unverified.

Abstract: An imaging system and method of providing localization data to a vehicle using the imaging system is disclosed. The method may comprise: capturing, from an electronic depth camera, one or more images, wherein the one or more images include at least a portion of the vehicle; and using a deep neural network and the one or more images, determining a multi-degree of freedom (MDF) pose of the vehicle, wherein an optical axis of the electronic depth camera is oriented along a Z-axis according to a Cartesian coordinate system (comprising an X-axis, a Y-axis, and the Z-axis), wherein the Z-axis is plumb with respect to Earth.

Abstract: Detection of an impact to a vehicle is based on data received from one of (a) one or more infrastructure sensors included in an infrastructure element or (b) the vehicle. Verification of the impact is determined by determining that data received from the other of the infrastructure sensors or the vehicle (a) detects the impact and is verified or (b) does not detect the impact and is unverified. A message is transmitted to the vehicle including the verification of the impact and one of (a) a request to operate to a predetermined location based on the impact being verified or (b) a notification to continue a current operation based on the impact being unverified.

Abstract: A ride-share system is disclosed. The system may comprise: one or more processors and memory storing instructions that are executable by the one or more processors, the instructions comprising: while operating a vehicle in an autonomous mode, determine a transit stop; based on the determination, attempt to establish communication with a smart node; when communication is established with the smart node, query the smart node regarding whether to actuate a vehicle door to an open position; and when communication is not established with the smart node, determine whether to actuate the vehicle door to the open position.

Abstract: A ride-share system is disclosed. The system may comprise: one or more processors and memory storing instructions that are executable by the one or more processors, the instructions comprising: while operating a vehicle in an autonomous mode, determine a transit stop; based on the determination, attempt to establish communication with a smart node; when communication is established with the smart node, query the smart node regarding whether to actuate a vehicle door to an open position; and when communication is not established with the smart node, determine whether to actuate the vehicle door to the open position.

Abstract: A system, comprising a computer that includes a processor and a memory, the memory storing instructions executable by the processor to input a red-green-blue (RGB) image and an eccentricity image to a neural network which outputs a located object based on combining the RGB image and the eccentricity image, wherein the eccentricity image is based on a per-pixel rolling average and a per-pixel rolling variance over a moving window of k video frames. The memory can further include instructions executable by the processor to receive the located object at a computing device included in one or more of a vehicle or a traffic information system.