Handling sensor occlusions for autonomous vehicles
The technology relates to identifying sensor occlusions due to the limits of the ranges of a vehicle's sensors and using this information to maneuver the vehicle. As an example, the vehicle is maneuvered along a route that includes traveling on a first roadway and crossing over a lane of a second roadway. A trajectory is identified from the lane that will cross with the route during the crossing at a first point. A second point beyond a range of the vehicle's sensors is selected. The second point corresponds to a hypothetical vehicle moving towards the route along the lane. A distance between the first point and the second point is determined. An amount of time that it would take the hypothetical vehicle to travel the distance is determined and compared to a threshold amount of time. The vehicle is maneuvered based on the comparison to complete the crossing.
1. A method for maneuvering an autonomous vehicle, the method comprising:
maneuvering, by one or more processors of one or more computing devices, the autonomous vehicle along a route by generating trajectories for the autonomous vehicle to follow the route;
selecting, by the one or more processors, a first point at a location that is occluded with respect to sensors of a perception system of the autonomous vehicle;
determining, by the one or more processors, an amount of time for a hypothetical occluded object to travel between the first point and a second point on one of the trajectories; and
maneuvering, by the one or more processors, the autonomous vehicle based on the amount of time.
2. The method of claim 1 , wherein maneuvering the autonomous vehicle includes completing an unprotected turn where the autonomous vehicle does not have a right of way over at least one lane of traffic at an intersection.
3. The method of claim 1 , wherein determining the amount of time is based on a distance the hypothetical occluded object would travel to reach the second point from the first point.
4. The method of claim 1 , wherein determining the amount of time is based on a speed of the hypothetical occluded object.
5. The method of claim 1 , wherein determining the amount of time is based on whether a speed bump is in a path the hypothetical occluded object would travel.
6. The method of claim 1 , wherein determining the amount of time is based on a limit on one of at least one of an acceleration or a deceleration for the hypothetical occluded object.
7. The method of claim 1 , wherein determining the amount of time is based on an assumption as to whether the hypothetical occluded object is able to perceive the autonomous vehicle.
8. The method of claim 1 , further comprising identifying a path between the first point and the second point based on whether a portion of a lane detected by one or more of the sensors is occupied by an object, and wherein determining the amount of time is further based on the path.
9. The method of claim 8 , wherein the amount of time is measured along the path.
10. A system for maneuvering an autonomous vehicle,
the system comprising one or more computing devices including one or more processors configured to:
maneuver the autonomous vehicle along a route by generating trajectories for the autonomous vehicle to follow the route;
select a first point at a location that is occluded with respect to sensors of a perception system of the autonomous vehicle;
determine an amount of time for a hypothetical occluded object to travel from the first point to a second point on one of the trajectories; and
maneuver the autonomous vehicle based on the amount of time.
11. The system of claim 10 , wherein the one or more processors are configured to maneuver the autonomous vehicle by completing an unprotected turn where the autonomous does not have a right of way over at least one lane of traffic at an intersection.
12. The system of claim 10 , wherein the one or more processors are configured to determine the amount of time further based on a distance the hypothetical occluded object would travel to reach the second point from the first point.
13. The system of claim 10 , wherein the one or more processors are configured to determine the amount of time further based on a speed of the hypothetical occluded object.
14. The system of claim 10 , wherein the one or more processors are configured to determine the amount of time further based on whether a speed bump is in a path the hypothetical occluded object would travel.
15. The system of claim 10 , wherein the one or more processors are configured to determine the amount of time further based on a limit on one of at least one of an acceleration or a deceleration for the hypothetical occluded object.
16. The system of claim 10 , wherein the one or more processors are configured to determine the amount of time further based on an assumption as to whether the hypothetical occluded object is able to perceive the autonomous vehicle.
17. The system of claim 10 , wherein the one or more processors are configured to identify a path between the occluded location and the one of the trajectories based on whether a portion of a lane detected by one or more of the sensors is occupied by an object, and to determine the amount of time is further based on the path.
18. The system of claim 17 , wherein the object is a stopped vehicle.
19. An autonomous vehicle, comprising:
one or more computing devices including one or more processors configured to:
maneuver the autonomous vehicle along a route by generating trajectories for the autonomous vehicle to follow the route;
select a first point at a location that is occluded with respect to sensors of a perception system of the autonomous vehicle;
determine an amount of time for a hypothetical occluded object to travel from the first point to a second point on one of the trajectories; and
maneuver the autonomous vehicle based on the amount of time.
20. The autonomous vehicle of claim 19 , wherein the one or more processors are configured to maneuver the autonomous vehicle by completing an unprotected turn where the autonomous vehicle does not have a right of way over at least one lane of traffic at an intersection.