Detecting and responding to processions for autonomous vehicles
The technology relates to detecting and responding to processions. For instance, sensor data identifying two or more objects in an environment of a vehicle may be received. The two or more objects may be determined to be disobeying a predetermined rule in a same way. Based on the determination that the two or more objects are disobeying a predetermined rule, that the two or more objects are involved in a procession may be determined. The vehicle may then be controlled autonomously in order to respond to the procession based on the determination that the two or more objects are involved in a procession.
1. A method of detecting and responding to processions, the method comprising:
receiving, by one or more processors, sensor data identifying two or more objects in an environment of a vehicle;
determining, by the one or more processors, results indicating a number of predetermined traffic rules being violated that the two or more objects are disobeying in a same way and an amount of time that the two or more objects are disobeying each of the predetermined traffic rules;
based on the results, determining, by the one or more processors, that the two or more objects are involved in a procession; and
controlling, by the one or more processors, the vehicle autonomously in order to respond to the procession based on the determination that the two or more objects are involved in a procession.
2. The method of claim 1 , wherein one of the predetermined traffic rules defines a traffic precedence that the two or more objects are disobeying.
3. The method of claim 1 , wherein the results further indicate a threshold minimum number of objects determined to be disobeying at least one of the predetermined traffic rules.
4. The method of claim 3 , wherein the results further indicate the threshold minimum number of objects disobeying the at least one of the predetermined traffic rules over at least a threshold minimum period of time.
5. The method of claim 1 , wherein the results further indicate objects determined to be disobeying at least one of the predetermined traffic rules over at least a threshold minimum period of time.
6. The method of claim 1 , further comprising determining that the procession is a motorcade or a funeral procession.
7. The method of claim 1 , further comprising determining that the procession is a parade or march.
8. The method of claim 1 , wherein at least one of the predetermined traffic rules includes one of stopping for a red traffic light signal or stopping for a stop sign.
9. The method of claim 1 , wherein the results further indicate a number of additional objects each disobeying at least one of the predetermined traffic rules.
10. The method of claim 1 , wherein the results further indicate an amount of time during which additional objects also disobey at least one of the predetermined traffic rules.
11. The method of claim 1 , further comprising identifying an emergency vehicle from the sensor data, wherein the determining, by the one or more processors, that the two or more objects are involved in the procession is further based on the emergency vehicle.
12. The method of claim 11 , wherein the determining, by the one or more processors, that the two or more objects are involved in the procession is further based on a location of the emergency vehicle relative to the two or more objects.
13. The method of claim 11 , wherein the determining, by the one or more processors, that the two or more objects are involved in the procession is further based on whether the emergency vehicle is stopped in an intersection.
14. The method of claim 1 , further comprising identifying a pedestrian directing traffic from the sensor data, wherein the determining, by the one or more processors, that the two or more objects are involved in the procession is further based on the identified pedestrian directing traffic.
15. The method of claim 1 , further comprising identifying a pedestrian holding a flag, a sign, or a banner from the sensor data, wherein the determining, by the one or more processors, that the two or more objects are involved in the procession is further based on the identified pedestrian holding the flag, the sign or the banner.
16. The method of claim 1 , further comprising identifying that at least one of the two or more objects has a flag or badge, wherein the determining, by the one or more processors, that the two or more objects are involved in the procession is further based on the identification that the at least one of the two or more objects has a flag or badge.
17. The method of claim 1 , further comprising determining that an additional object between two of the two or more objects is not disobeying at least one of the predetermined traffic rules, wherein the determining, by the one or more processors, that the two or more objects are involved in the procession is further based on the determination that the additional object between two of the two or more objects is not disobeying the at least one of the predetermined traffic rules.
18. The method of claim 1 , further comprising determining a gap in time between two of the two or more objects, wherein the determining, by the one or more processors, that the two or more objects are involved in the procession is further based on the gap in time.
19. The method of claim 1 , wherein the determining, by the one or more processors, that the two or more objects are involved in the procession is further based on local regulations for processions.
20. The method of claim 1 , wherein the controlling, by the one or more processors, the vehicle includes yielding to the two or more objects involved in the procession as a group.
21. The method of claim 1 , wherein the amount of time is based on how much time the two or more objects disobey a same one of the predetermined traffic rules in the same way.
22. The method of claim 21 , wherein the amount of time is further based on how much time the two or more objects disobey an additional predetermined traffic rule.