Detecting and responding to traffic redirection for autonomous vehicles

1. A method of controlling a vehicle in an autonomous driving mode, the method comprising:

maneuvering, by one or more processors, a vehicle in the autonomous driving mode using pre-stored map information identifying traffic lanes;

receiving, by the one or more processors, data from a perception system of the vehicle identifying objects in an external environment of the vehicle related to a traffic redirection at a given location different from the traffic lanes of the pre-stored map information;

using, by the one or more processors, the received data to identify two or more corridors of the traffic redirection;

determining, by the one or more processors, a traffic flow direction of a first corridor of the two or more corridors;

rejecting, by the one or more processors, the first corridor of the two or more corridors based at least in part on the traffic flow direction of the first corridor;

selecting, by the one or more processors, a second corridor of the two or more corridors; and

controlling, by the one or more processors, the vehicle in the autonomous driving mode to enter and follow the second corridor of the two or more corridors.

2. The method of claim 1 , wherein the second corridor is not defined by lane lines.

3. The method of claim 1 , further comprising determining, by the one or more processors, a traffic flow direction of the second corridor, and

wherein the second corridor corresponds to a path of a traffic lane identified in the pre-stored map information for the given location, but the traffic flow direction of the traffic lane as identified in the pre-stored map information for the given location is different than the determined traffic flow direction of the second corridor.

4. The method of claim 1 , wherein determining the traffic flow direction of the first corridor is based at least in part on a determination, by the one or more processors, that opposing traffic would choose the first corridor.

5. The method of claim 1 , wherein determining the traffic flow direction of the first corridor is based at least in part on an analysis, by the one or more processors, of one or more signs proximate to the first corridor.

6. The method of claim 5 , wherein the analysis of the one or more signs proximate to the first corridor includes performing, by the one or more processors, optical character recognition to identify text on the one or more signs.

7. The method of claim 5 , wherein the analysis of the one or more signs proximate to the first corridor includes determining, by the one or more processors, an orientation of the one or more signs relative to the first corridor.

8. The method of claim 1 , wherein determining the traffic flow direction of the first corridor is based at least in part on a determination, by the one or more processors, that opposing traffic is passing through the first corridor.

9. The method of claim 1 , further comprising determining, by the one or more processors, a road surface condition of the first corridor, and

wherein rejecting the first corridor of the two or more corridors is based at least in part on the road surface condition of the first corridor.

10. The method of claim 9 , wherein the road surface condition of the first corridor includes one or more of a trench, a drop-off of a predetermined height, or an unpaved road surface.

11. A system for controlling a vehicle in an autonomous driving mode, the system comprising one or more processors configured to:

maneuver a vehicle in the autonomous driving mode using pre-stored map information identifying traffic lanes;

receive data from a perception system of the vehicle identifying objects in an external environment of the vehicle related to a traffic redirection at a given location different from the traffic lanes of the pre-stored map information at the given location;

use the received data to identify two or more corridors of the traffic redirection;

determine a traffic flow direction of a first corridor of the two or more corridors;

reject the first corridor of the two or more corridors based at least in part on the traffic flow direction of the first corridor;

select a second corridor of the two or more corridors; and

control the vehicle in the autonomous driving mode to enter and follow the second corridor of the two or more corridors.

12. The system of claim 11 , wherein the one or more processors are further configured to determine the traffic flow direction of the first corridor based at least in part on a determination that opposing traffic would choose the first corridor.

13. The system of claim 11 , wherein the one or more processors are further configured to determine the traffic flow direction of the first corridor based at least in part on an analysis of one or more signs proximate to the first corridor.

14. The system of claim 13 , wherein, as a part of the analysis of the one or more signs proximate to the first corridor, the one or more processors are further configured to perform optical character recognition to identify text on the one or more signs.

15. The system of claim 13 , wherein, as a part of the analysis of the one or more signs proximate to the first corridor, the one or more processors are further configured to determine an orientation of the one or more signs relative to the first corridor.

16. The system of claim 11 , wherein the one or more processors are further configured to determine the traffic flow direction of the first corridor based at least in part on a determination that opposing traffic is passing through the first corridor.

17. The system of claim 11 , wherein the one or more processors are further configured to:

determine a road surface condition of the first corridor, and

reject the first corridor of the two or more corridors based at least in part on the road surface condition of the first corridor.

18. The system of claim 11 , further comprising the vehicle.