Traffic light navigation based on worst time to red estimation
Systems and methods are provided for vehicle navigation. The systems and methods may detect traffic lights. For example, one or more traffic lights may be detected using detection-redundant camera detection paths, a fusion of information from a traffic light transmitter and one or more cameras, based on contrast enhancement for night images, and based on low resolution traffic light candidate identification followed by high resolution candidate analysis. Additionally, the systems and methods may navigation based on a worst time to red estimation.
1. A navigation system for a vehicle, the navigation system comprising:
at least one processor comprising circuitry and having access to a memory, wherein the memory includes instructions that when executed by the circuitry cause the at least one processor to:
receive at least one image acquired by a camera from an environment of the vehicle;
analyze the at least one image to identify a representation of a traffic light in the at least one image, wherein the traffic light is associated with an intersection;
determine a state of the traffic light based on the analysis of the at least one image;
determine a planned navigational action for the vehicle based on the determined state of the traffic light;
after a determination that the traffic light is in a green state, and where a time at which the traffic light transitioned to the green state is not known, cause the vehicle to implement the planned navigational action if the vehicle is projected to reach the traffic light or the intersection within a predetermined, next-time-to-red time interval, wherein the predetermined, next-time-to-red interval is based, at least in part, on state transition information stored in association with the traffic light in a map; and
cause the vehicle to implement a second navigational action, different from the planned navigational action, if the vehicle is projected to not reach the traffic light or the intersection within the predetermined, next-time-to-red time interval.
2. The system of claim 1 , wherein the next-time-to-red time interval is at least two seconds and less than six seconds.
3. The system of claim 1 , wherein the planned navigational action includes navigating the vehicle through the intersection while maintaining a current speed of the vehicle.
4. The system of claim 1 , wherein the second navigational action includes slowing the vehicle relative to its current speed.
5. The system of claim 1 , wherein the planned navigational action is determined based on map information.
6. The system of claim 1 , wherein the next-time-to-red time interval is less than an actual time duration to a next red state for the traffic light.
7. The system of claim 1 , wherein the predetermined, next-time-to-red time interval is based, at least in part, on historical state transition information for the traffic light collected from one or more other vehicles.
8. The system of claim 7 , wherein the historical state transition information is associated with the traffic light.
9. The system of claim 1 , wherein causing the vehicle to implement the planned navigational action or the second navigational action is further based on a speed of the vehicle.
10. The system of claim 1 , wherein causing the vehicle to implement the planned navigational action or the second navigational action is further based on a heading of the vehicle.
11. The system of claim 1 , wherein causing the vehicle to implement the planned navigational action or the second navigational action is further based on a location of the vehicle relative to the traffic light.
12. The system of claim 1 , wherein causing the vehicle to implement the planned navigational action or the second navigational action is further based on a location of the vehicle relative to an intersection.
13. The system of claim 12 , wherein causing the vehicle to implement the planned navigational action or the second navigational action is further based on a location of the vehicle relative to another vehicle approaching the intersection.
14. The system of claim 1 , wherein the planned navigational action is a traversal of an intersection associated with the traffic light.
15. The system of claim 14 , wherein causing the vehicle to implement the planned navigational action or the second navigational action includes determining whether a time period for accomplishing the traversal of the intersection is equal to or less than a predetermined state transition time.
16. The system of claim 15 , wherein execution of the instructions included in the memory further causes the at least one processor to analyze one or more images to identify a transition of the traffic light to a red state before the vehicle traverses the intersection.
17. The system of claim 16 , wherein execution of the instructions included in the memory further causes the at least one processor to cause the vehicle to stop prior to entering the intersection.
18. The system of claim 17 , wherein execution of the instructions included in the memory further causes the at least one processor to cause the vehicle to enter the intersection after the traffic light reverts to the green state.
19. The system of claim 15 , wherein execution of the instructions included in the memory further causes the at least one processor to analyze one or more images to confirm the green state of the traffic light before the vehicle traverses the intersection.
20. The system of claim 19 , wherein execution of the instructions included in the memory further causes the at least one processor to cause the vehicle to enter and traverse the intersection.
21. A method for navigating a vehicle, comprising
receiving at least one image acquired by a camera from an environment of a vehicle;
analyzing the at least one image to identify a representation of a traffic light in the at least one image, wherein the traffic light is associated with an intersection;
determining a state of the traffic light based on the analysis of the at least one image;
determining a planned navigational action for the vehicle based on the determined state of the traffic light;
after a determination that the traffic light is in a green state, and where a time at which the traffic light transitioned to the green state is not known, causing the vehicle to implement the planned navigational action if the vehicle is projected to reach the traffic light or the intersection within a predetermined, next-time-to-red time interval, wherein the predetermined, next-time-to-red interval is based, at least in part, on state transition information stored in association with the traffic light in a map; and
causing the vehicle to implement a second navigational action, different from the planned navigational action, if the vehicle is projected to not reach the traffic light or the intersection within the predetermined, next-time-to-red time interval.
22. A non-transitory computer-readable medium comprising instructions that, when executed by at least one processor, are configured to cause the at least one processor to:
receive at least one image acquired by a camera captured from an environment of a vehicle;
analyze the at least one image to identify a representation of a traffic light in the at least one image, wherein the traffic light is associated with an intersection;
determine a state of the traffic light based on the analysis of the at least one image;
determine a planned navigational action for the vehicle based on the determined state of the traffic light;
after a determination that the traffic light is in a green state, and where a time at which the traffic light transitioned to the green state is not known, cause the vehicle to implement the planned navigational action if the vehicle is projected to reach the traffic light or the intersection within a predetermined, next-time-to-red time interval, wherein the predetermined, next-time-to-red interval is based, at least in part, on state transition information stored in association with the traffic light in a map; and
cause the vehicle to implement a second navigational action, different from the planned navigational action, if the vehicle is projected to not reach the traffic light or the intersection within the predetermined, next-time-to-red time interval.
23. The navigation system of claim 1 , wherein the analysis of the at least one image includes comparing the at least one image to a stored image representing a traffic light having a particular state.
24. The navigation system of claim 1 , wherein the analysis of the at least one image includes:
generating a modified version of the captured image with an image resolution less than that of the captured image; and
analyzing the modified version of the captured image.
25. The method of claim 21 , wherein the next-time-to-red time interval is less than an actual time duration to a next red state for the traffic light.
26. The method of claim 21 , wherein the predetermined, next-time-to-red time interval is based, at least in part, on historical state transition information for the traffic light collected from one or more other vehicles.
27. The method of claim 21 , wherein the planned navigational action is a traversal of an intersection associated with the traffic light.
28. The method of claim 27 , wherein causing the vehicle to implement the planned navigational action or the second navigational action includes determining whether a time period for accomplishing the traversal of the intersection is equal to or less than a predetermined state transition time.
29. The non-transitory computer-readable medium of claim 22 , wherein the next-time-to-red time interval is less than an actual time duration to a next red state for the traffic light.
30. The non-transitory computer-readable medium of claim 22 , wherein the predetermined, next-time-to-red time interval is based, at least in part, on historical state transition information for the traffic light collected from one or more other vehicles.
31. The non-transitory computer-readable medium of claim 22 , wherein the planned navigational action is a traversal of an intersection associated with the traffic light.
32. The non-transitory computer-readable medium of claim 31 , wherein causing the vehicle to implement the planned navigational action or the second navigational action includes determining whether a time period for accomplishing the traversal of the intersection is equal to or less than a predetermined state transition time.