Automated bump and/or depression detection in a roadway

1 . A computer-implemented method comprising:

obtaining, with a computing system comprising one or more processors, sensor data captured by at least one sensor of an autonomous vehicle, the sensor data describing a plurality of return points that indicate heights of a plurality of locations on a roadway in a geographic location, each return point of the plurality of return points describing a height of a respective location of the plurality of locations;

determining, with the computing system and using the sensor data, a change in height over the plurality of locations;

determining, with the computing system, a beginning location in the plurality of locations, the beginning location being a location of the plurality of locations having a greatest change in height in a first direction;

determining, with the computing system, an ending location in the plurality of locations, the ending location being a location of the plurality of locations having a greatest change in height in a second direction different than the first direction;

determining, with the computing system, at least one of a highest location positioned at least in part on a line from the beginning location to the ending location or a lowest location positioned at least in part on a line from the beginning location to the ending location;

selecting, with the computing system, a centerline from a plurality of lines projecting through the highest location or the lowest location, the centerline being selected from the plurality of lines to have a minimum change in height between the highest location or the lowest location and a remainder of locations from the plurality of locations that are on the centerline;

generating, with the computing system, a beginning line projecting parallel to the centerline through the beginning location and an ending line projecting parallel to the centerline through the ending location;

identifying, with the computing system, at least one of a bump in the roadway or a depression in the roadway based at least in part on the beginning line; and

modifying, before the autonomous vehicle reaches the bump in the roadway or the depression in the roadway, at least one control of the autonomous vehicle based on the bump in the roadway or the depression in the roadway.

2 . The computer-implemented method of claim 1 , further comprising:

generating, with the computing system, a right edge connecting the beginning line and the ending line based on at least one of a first edge of the roadway or a first edge of an intersection of the roadway; and

generating, with the computing system, a left edge connecting the beginning line and the ending line based on at least one of a second edge of the roadway or a second edge of the intersection of the roadway.

3 . The computer-implemented method of claim 1 , further comprising:

generating, with the computing system, a right edge connecting the beginning line and the ending line based on a portion of the plurality of locations that are between the beginning line and the ending line; and

generating, with the computing system, a left edge connecting the beginning line and the ending line based on the portion of the plurality of locations between the beginning line and the ending line.

4 . The computer-implemented method of claim 1 , wherein the plurality of locations correspond to a plurality of map areas of a map of the geographic location.

5 . The computer-implemented method of claim 4 , further comprising generating a probability map associated with a probability of the bump in the roadway or the depression in the roadway being in a first map area of the plurality of map areas, the probability map being generated based at least in part on a first portion of the plurality of locations in the first map area and at least in part on a second portion of the plurality of locations that overlap at least one location of the first portion of the plurality of locations.

6 . The computer-implemented method of claim 5 , further comprising generating, with the computing system, the map comprising a region having a selectable factor in the map for indicating the location of the bump in the roadway or the depression in the roadway in the map of the geographic location.

7 . The computer-implemented method of claim 1 , a height at the beginning location being determined based at least in part on a parameter selected from a z-value, a pitch, a pitch rate, a longitudinal speed, a longitudinal acceleration, a yaw, a yaw rate, a latitudinal speed, a latitudinal acceleration, an x-value, a y-value, a roll, or a roll rate.

8 . The computer-implemented method of claim 1 , the second direction being opposite the first direction.

9 . A computing system comprising:

one or more processors programmed to perform operations comprising:

obtaining sensor data captured by at least one sensor of an autonomous vehicle, the sensor data describing a plurality of return points that indicate heights of a plurality of locations on a roadway in a geographic location, each return point of the plurality of return points describing a height of a respective location of the plurality of locations;

determining, using the sensor data, a change in height over the plurality of locations;

determining a beginning location in the plurality of locations, the beginning location being a location of the plurality of locations having a greatest change in height in a first direction;

determining an ending location in the plurality of locations, the ending location being a location of the plurality of locations having a greatest change in height in a second direction different than the first direction;

determining at least one of a highest location positioned at least in part on a line from the beginning location to the ending location or a lowest location positioned at least in part on a line from the beginning location to the ending location;

selecting a centerline from a plurality of lines projecting through the highest location or the lowest location, the centerline being selected from the plurality of lines to have a minimum change in height between the highest location or the lowest location and a remainder of locations from the plurality of locations that are on the centerline;

generating a beginning line projecting parallel to the centerline through the beginning location and an ending line projecting parallel to the centerline through the ending location;

identifying at least one of a bump in the roadway or a depression in the roadway based at least in part on the beginning line; and

modifying, before the autonomous vehicle reaches the bump in the roadway or the depression in the roadway, at least one control of the autonomous vehicle based on the bump or depression in the roadway.

10 . The computing system of claim 9 , the operations further comprising:

generating a right edge connecting the beginning line and the ending line based on at least one of a first edge of the roadway and a first edge of an intersection of the roadway; and

generating a left edge connecting the beginning line and the ending line based on at least one of a second edge of the roadway and a second edge of the intersection of the roadway.

11 . The computing system of claim 9 , the operations further comprising:

generating a right edge connecting the beginning line and the ending line based on a portion of the plurality of locations that are between the beginning line and the ending line; and

generating a left edge connecting the beginning line and the ending line based on the portion of the plurality of locations between the beginning line and the ending line.

12 . The computing system of claim 9 , wherein the plurality of locations correspond to a plurality of map areas of a map of the geographic location.

13 . The computing system of claim 12 , the operations further comprising generating a probability map associated with a probability of the bump in the roadway or the depression in the roadway in a first map area of the plurality of map areas, the probability map being generated based at least in part on a first portion of the plurality of locations in the first map area and on at least in part on a second portion of the plurality of locations that overlap at least one location of the first portion of the plurality of locations.

14 . The computing system of claim 13 , the operations further comprising generating the map comprising a region having a selectable factor in the map for indicating the location of the bump in the roadway or the depression in the roadway in the map of the geographic location.

15 . The computing system of claim 9 , a height at the beginning location being determined based at least in part on a parameter selected from a z-value, a pitch, a pitch rate, a longitudinal speed, a longitudinal acceleration, a yaw, a yaw rate, a latitudinal speed, a latitudinal acceleration, an x-value, a y-value, a roll, or a roll rate.

16 . A computer program product comprising at least one non-transitory computer-readable medium including program instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:

obtaining sensor data captured by at least one sensor of an autonomous vehicle, the sensor data describing a plurality of return points that indicate heights of a plurality of locations on a roadway in a geographic location, each return point of the plurality of return points describing a height of a respective location of the plurality of locations;

determining, using the sensor data, a change in height over the plurality of locations;

determining a beginning location in the plurality of locations, the beginning location being a location of the plurality of locations having a greatest change in height in a first direction;

determining an ending location in the plurality of locations, the ending location being a location of the plurality of locations having a greatest change in height in a second direction different than the first direction;

determining at least one of a highest location positioned at least in part on a line from the beginning location to the ending location or a lowest location positioned at least in part on a line from the beginning location to the ending location;

selecting a centerline from a plurality of lines projecting through the highest location or the lowest location, the centerline being selected from the plurality of lines to have a minimum change in height between the highest location or the lowest location and a remainder of locations from the plurality of locations that are on the centerline;

generating a beginning line projecting parallel to the centerline through the beginning location and an ending line projecting parallel to the centerline through the ending location;

identifying at least one of a bump in the roadway or a depression in the roadway based at least in part on the beginning line; and

modifying, before the autonomous vehicle reaches the bump in the roadway or the depression in the roadway, at least one control of the autonomous vehicle based on the bump in the roadway or the depression in the roadway.