On-site notification from autonomous vehicle for traffic safety
A system included and a computer-implemented method performed in an autonomous-driving vehicle are described. The system performs: detecting one or more movable traffic objects; determining one or more target movable traffic objects from the one or more detected movable traffic objects; determining a type of the one or more target movable traffic objects and an traffic object that has a right of way (ROW) in a situation involving the autonomous-driving vehicle. The system further performs: determining a manner of generating a vehicle behavior notification to the target movable traffic object based on the type of the one or more target movable traffic objects and the ROW; and causing a vehicle behavior notification of the determined manner to be generated to the one or more target movable traffic objects.
1. A notification system for an autonomous-driving vehicle, comprising:
one or more processors; and
a memory storing instructions that, when executed by the one or more processors, cause the one or more processors to perform a method comprising:
determining a target traffic object from traffic objects in an environment within which the autonomous-driving vehicle operates, wherein determining the target traffic object from the traffic objects comprises:
determining a route associated with the autonomous-driving vehicle;
determining predicted routes associated with the traffic objects;
determining, based on the route and the predicted routes, at least one traffic object from the traffic objects that is predicted to be within a predetermined distance of the autonomous-driving vehicle within a predetermined period of time; and
identifying the at least one traffic object as the target traffic object;
determining, based at least in part on the target traffic object with respect to the environment, whether the autonomous-driving vehicle has a right of way in the environment; and
generating, based on the determination of whether the autonomous-driving vehicle has the right of way, a vehicle behavior notification—to indicate an intent of the autonomous-driving vehicle.
2. The notification system of claim 1 , wherein the target traffic object and the traffic objects are identified based on attributes of the target traffic object and the traffic objects.
3. The notification system of claim 2 , wherein the attributes of the target traffic object and the traffic objects are captured through sensors onboard the autonomous-driving vehicle, and wherein the sensors onboard the autonomous-driving vehicle include at least one of a Lidar or a camera.
4. The notification system of claim 1 , wherein the route associated with the autonomous-driving vehicle is determined based on two or more of a current location, a destination, traffic conditions, weather conditions, environmental conditions, or a number of turns in the route.
5. The notification system of claim 1 , wherein the right of way in the environment is determined based on one or more of traffic rules, traffic signals, or traffic signs associated with a location of the autonomous-driving vehicle and in relation to the target traffic object.
6. The notification system of claim 1 , wherein generating the vehicle behavior notification for the target traffic object comprises:
determining that the autonomous-driving vehicle has the right of way;
determining, based on traffic conditions, that the autonomous-driving vehicle is able to safely proceed; and
generating the vehicle behavior notification to indicate an intent of the autonomous-driving vehicle to proceed.
7. The notification system of claim 1 , wherein generating the vehicle behavior notification for the target traffic object comprises:
determining that the autonomous-driving vehicle has the right of way;
determining, based on traffic conditions, that the autonomous-driving vehicle is unable to safely proceed; and
generating the vehicle behavior notification to indicate an intent of the autonomous-driving vehicle not to proceed.
8. The notification system of claim 1 , wherein generating the vehicle behavior notification for the target traffic object comprises:
determining that the autonomous-driving vehicle does not have the right of way; and
generating the vehicle behavior notification to indicate an intent of the autonomous-driving vehicle to yield to the target traffic object.
9. The notification system of claim 1 , wherein the vehicle behavior notification is at least one of a visual or an acoustic notification, wherein the visual notification includes at least one of changing a color, a pattern, or brightness associated with light generated by at least one light emitting device associated with the autonomous-driving vehicle.
10. A computer-implemented method performed in an autonomous-driving vehicle comprising:
determining a target traffic object from traffic objects in an environment within which the autonomous-driving vehicle operates, wherein determining the target traffic object from the traffic objects comprises:
determining a route associated with the autonomous-driving vehicle;
determining predicted routes associated with the traffic objects;
determining, based on the route and the predicted routes, at least one traffic object from the traffic objects that is predicted to be within a predetermined distance of the autonomous-driving vehicle within a predetermined period of time; and
identifying the at least one traffic object as the target traffic object;
determining, based at least in part on the target traffic object with respect to the environment, whether the autonomous-driving vehicle has a right of way in the environment; and
generating, based on the determination of whether the autonomous-driving vehicle has the right of way, a vehicle behavior notification to indicate an intent of the autonomous-driving vehicle.
11. The computer-implemented method of claim 10 , wherein the target traffic object and the traffic objects are identified based on attributes of the target traffic object and the traffic objects.
12. The computer-implemented method of claim 11 , wherein the attributes of the target traffic object and the traffic objects is captured through sensors onboard the autonomous-driving vehicle, and wherein the sensors onboard the autonomous-driving vehicle include at least one of a Lidar or a camera.
13. The computer-implemented method of claim 10 , wherein the route associated with the autonomous-driving vehicle is determined based on two or more of a current location, a destination, traffic conditions, weather conditions, environmental conditions, or a number of turns in the route.
14. The computer-implemented method of claim 10 , wherein the right of way in the environment is determined based on one or more of traffic rules, traffic signals, or traffic signs associated with a location of the autonomous-driving vehicle and in relation to the target traffic object.
15. The computer-implemented method of claim 10 , wherein generating the vehicle behavior notification for the target traffic object comprises:
determining that the autonomous-driving vehicle has the right of way;
determining, based on traffic conditions, that the autonomous-driving vehicle is able to safely proceed; and
generating the vehicle behavior notification to indicate an intent of the autonomous-driving vehicle to proceed.
16. The computer-implemented method of claim 10 , wherein generating the vehicle behavior notification for the target traffic object comprises:
determining that the autonomous-driving vehicle has the right of way;
determining, based on traffic conditions, that the autonomous-driving vehicle is unable to safely proceed; and
generating the vehicle behavior notification to indicate an intent of the autonomous-driving vehicle not to proceed.
17. The computer-implemented method of claim 10 , wherein generating the vehicle behavior notification for the target traffic object comprises:
determining that the autonomous-driving vehicle does not have the right of way; and
generating the vehicle behavior notification to indicate an intent of the autonomous-driving vehicle to yield to the target traffic object.
18. The computer-implemented method of claim 10 , wherein the vehicle behavior notification is at least one of a visual or an acoustic notification, wherein the visual notification includes at least one of changing a color, a pattern, or brightness associated with light generated by at least one light emitting device associated with the autonomous-driving vehicle.