Stop location change detection
The technology relates to approaches for determining appropriate stopping locations at intersections for vehicles operating in a self-driving mode. While many intersections have stop lines painted on the roadway, many others have no such lines. Even if a stop line is present, the physical location may not match what is in store map data, which may be out of date due to construction or line repainting. Aspects of the technology employ a neural network that utilizes input training data and detected sensor data to perform classification, localization and uncertain estimation processes. Based on these processes, the system is able to evaluate distribution information for possible stop locations. The vehicle uses such information to determine an optimal stop point, which may or may not correspond to a stop line in the map data. This information is also used to update the existing map data, which can be shared with other vehicles.
1. A method of controlling a vehicle operating in an autonomous driving mode, the method comprising:
receiving, by one or more sensors of a perception system of the vehicle, sensor data associated with objects in an external environment of the vehicle;
determining, by one or more processors of the vehicle, whether the vehicle is within a threshold distance of a lane endpoint along a portion of a roadway;
performing, by the one or more processors upon determining that the vehicle is within the threshold distance of the lane endpoint, stop location detection, wherein performing the stop location detection includes:
mapping a set of stop line points closest to an expected stop line;
discarding any of the set of stop line points not located within a region of interest associated with the lane endpoint; and
projecting any remaining stop line points of the set onto a lane tangent to identify a mapped stopping location; and
causing, by the one or more processors, the vehicle to stop along the roadway according to the mapped stopping location.
2. The method of claim 1 , wherein the set of stop line points is mapped based on (i) a heat map according to the received sensor data and (ii) a vector field including a set of vectors, each vector being associated with a corresponding given pixel of a set of pixels in the heat map.
3. The method of claim 2 , wherein the stop line points are weighted by scores at corresponding ones of the given pixels.
4. The method of claim 1 , wherein the threshold distance is selected in accordance with sensor visibility for the one or more sensors of the perception system.
5. The method of claim 4 , wherein the threshold distance is selected according to one or more of vehicle size, vehicle type or sensor configuration.
6. The method of claim 1 , further comprising augmenting map information in accordance with the mapped stopping location.
7. A vehicle configured to operate in an autonomous driving mode, the vehicle comprising:
a perception system including one or more sensors, the one or more sensors being configured to receive sensor data associated with objects in an external environment of the vehicle;
a driving system including a steering subsystem, an acceleration subsystem and a deceleration subsystem to control driving of the vehicle;
a positioning system configured to determine a current position of the vehicle; and
a control system including one or more processors, the control system operatively coupled to the driving system, the perception system and the positioning system, the control system being configured to:
determine whether the vehicle is within a threshold distance of a lane endpoint along a portion of a roadway;
perform, upon determining that the vehicle is within the threshold distance of the lane endpoint, stop location detection, wherein the stop location detection includes:
mapped of a set of stop line points closest to an expected stop line;
discarding any of the set of stop line points not located within a region of interest associated with the lane endpoint; and
projection of any remaining stop line points of the set onto a lane tangent to identify a mapped stopping location; and
cause the vehicle to stop along the roadway according to the mapped stopping location.
8. The vehicle of claim 7 , wherein mapping of the set of stop line points is based on (i) a heat map according to the received sensor data and (ii) a vector field including a set of vectors, each vector being associated with a corresponding given pixel of a set of pixels in the heat map.
9. The vehicle of claim 7 , wherein the threshold distance is selected in accordance with sensor visibility for the one or more sensors of the perception system.
10. The vehicle of claim 9 , wherein the threshold distance is selected according to one or more of vehicle size, vehicle type or sensor configuration.