Autonomous vehicle operation at blind intersections
View Patent ↗An automated driving system for an autonomous vehicle may include a perception system and a computing device for detecting and tracking a location of an object within an obstructed viewing region blocked from view of sensors associated with the perception system. The computing device and perception system may identify an obstructed viewing region and detect an external imaging assist device located within a sensor field of the perception system. The imaging assist device is capable of transmitting images of the obstructed viewing region to the perception system. The computing device analyzes the images received from the imaging assist device for purposes of detecting an object within the obstructed viewing region and tracking its location relative to the autonomous vehicle. The computing device may transmit a command to an autonomous vehicle system to implement an autonomous vehicle maneuver based at least in part on the tracked location of the hidden object.
1. A method for operating an autonomous vehicle, the method comprising:
identifying an obstructed viewing region blocked from a sensor field of a camera associated with the autonomous vehicle;
detecting a reflective surface of a structure located within image data acquired by the camera, the reflective surface having a reflected image of at least a portion of the obstructed viewing region;
detecting, using image data acquired by the camera, an object within the reflected image, at least a portion of the object being located within the obstructed viewing region;
tracking a location of the object within the obstructed viewing region relative to the autonomous vehicle; and
implementing an autonomous vehicle maneuver based at least in part on the tracked location of the object.
2. The method of claim 1 , wherein the structure is a convex mirror.
3. The method of claim 1 , wherein the structure is a building.
4. The method of claim 1 , wherein tracking the location of the object within the obstructed viewing region comprises detecting at least a first location of the object and a second location of the object and predicting movement of the object relative to the autonomous vehicle based on the first and second locations.
5. The method of claim 1 , wherein the structure is immobile.
6. The method of claim 1 , wherein the camera is attached to the autonomous vehicle.
7. The method of claim 1 , wherein the structure is a vehicle.
8. A method for operating an autonomous vehicle, the method comprising:
detecting a reflective surface of a structure located within image data acquired by a camera associated with the autonomous vehicle, the reflective surface having a reflected image;
detecting, using image data acquired by the camera, an object located within the reflected image;
determining if the object is directly viewable within a sensor field of the camera; and
tracking a location of the object relative to the autonomous vehicle based on the reflected image when the object is not located within the sensor field of the camera; and
implementing an autonomous vehicle maneuver based on the tracked location of the object.
9. The method of claim 8 , wherein the structure is a convex mirror.
10. The method of claim 8 , wherein the structure is a building.
11. The method of claim 8 , wherein the structure is immobile.
12. An automated driving system comprising:
a camera operable to capture an image of a region surrounding an autonomous vehicle; and
a computing device in communication with the camera, the computing device comprising:
one or more processors for controlling operation of the computing device;
a memory for storing data and program instructions used by the one or more processors, wherein the one or more processors are configured to execute instructions stored in the memory to:
analyze the image captured by the camera;
detect an external reflective surface within the captured image, the reflective surface having a reflected image of at least a portion of an obstructed viewing region;
detect an object within the reflected image;
track a location of the object based on the reflected image; and
implement a vehicle maneuver based at least in part on the tracked location of the object.
13. The automated driving system of claim 12 , wherein the reflective surface is a surface of a vehicle.
14. The automated driving system of claim 12 , wherein the reflective surface is a surface of a convex mirror.
15. The automated driving system of claim 12 , wherein the reflective surface is a surface of a building.