Ground profile estimation for sensor data
Techniques for estimating a ground profile for an environment associated with a vehicle are described herein. Sensor data associated with a vehicle may be used to determine sensor data points associated with a path of the vehicle. Using a first metric and a second metric, such as a maximum slope and minimum slope based on the position of the vehicle and/or a previously-determined ground point, a region (e.g., search window) may be determined, and based on the region, a subset of sensor data points included in the region. The subset of sensor data points may be used to determine a ground point. In some instances, the ground point may be determined based on an average height of the sensor data points. A ground profile may be determined that at least partially includes the ground point.
1 . A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computer executable instructions that, when executed, cause the one or more processors to perform operations comprising:
receiving a path associated with controlling an autonomous vehicle through an environment;
receiving lidar data from a sensor associated with the autonomous vehicle;
associating the lidar data with a first bin associated with a distance along the path;
determining, based at least in part on a first metric, a first lower bound height associated with the first bin;
determining, based at least in part on a second metric, a first upper bound height associated with the first bin;
determining, as a first subset of data, a portion of the lidar data associated with the first bin that falls within the first lower bound height and the first upper bound height;
determining, based on the first subset of data, a first representative height associated with the first bin;
determining a second lower bound height and second upper bound height of a second bin;
determining, as a second subset of data, a portion of the lidar data associated with the second bin that falls within the second lower bound height and the second upper bound height;
determining, based on the second subset of data, a second representative height associated with the second bin;
determining, based at least in part on the first representative height and the second representative height, a ground surface; and
controlling the autonomous vehicle based on the ground surface.
2 . The system of claim 1 , wherein determining one or more of the first lower bound height or the first upper bound height is based at least in part on a position associated with the autonomous vehicle or a previous representative height associated with a previous bin associated with the distance along the path.
3 . The system of claim 1 , the operations further comprising:
determining a distance between a first point and the path;
determining a weight based on the distance; and
determining the first representative height associated with the first bin based at least in part on the weight.
4 . The system of claim 1 , the operations further comprising:
determining that a number of lidar points associated with the second bin is less than a threshold number of points;
determining a third upper bound height and a third lower bound height of a third bin based on the second lower bound height and the first metric and the second upper bound height and the second metric; and
determining, as a third subset of data, a portion of the lidar data associated with the third bin and that falls within the third lower bound height and the third upper bound height.
5 . The system of claim 1 , the operations further comprising:
detecting an object based on the ground surface; and
controlling the autonomous vehicle based on the object.
6 . One or more non-transitory computer-readable media storing instructions executable by one or more processors that, when executed, cause the one or more processors to perform operations comprising:
receiving sensor data from a sensor associated with a vehicle;
determining, based on the sensor data, sensor data points associated with a path of the vehicle;
determining, based on a first metric and a second metric, a first region;
determining, based at least in part on the first region, a first subset of the sensor data points;
determining, based on the first subset of the sensor data points, a first ground point;
determining, based on a third metric and a fourth metric, a second region, wherein the second region includes a second subset of the sensor data points;
determining, based on the second subset of the sensor data points, a second ground point;
determining a ground profile based at least in part on the first ground point and the second ground point; and
controlling the vehicle based on the ground profile.
7 . The one or more non-transitory computer-readable media of claim 6 , the operations further comprising:
excluding the sensor data points associated with the path of the vehicle;
identifying, based at least in part on the sensor data and the ground profile, a second subset of sensor data points;
detecting, based at least in part on the second subset of sensor data points, an object; and
controlling the vehicle based on the object.
8 . The one or more non-transitory computer-readable media of claim 6 , wherein the first metric comprises a first maximum slope and the second metric comprises a first minimum slope.
9 . The one or more non-transitory computer-readable media of claim 6 , the operations further comprising:
determining a distance between a first sensor data point and the path; and
determining a weight based on the distance,
wherein determining the first ground point is based at least in part on the weight.
10 . The one or more non-transitory computer-readable media of claim 6 , the operations further comprising:
determining that a second subset of sensor data points associated with the second region is less than a threshold number of points;
determining a fifth metric and a sixth associated with a third region based on the third metric and the fourth metric; and
determining, based on a third subset of the sensor data points included in the third region, a third ground point, wherein determining the ground profile is further based at least in part on the second ground point.
11 . The one or more non-transitory computer-readable media of claim 6 , wherein the sensor data points are within a threshold lateral distance of the path and within a threshold distance of the vehicle along the path.
12 . The one or more non-transitory computer-readable media of claim 6 , wherein the first region is laterally adjacent to the second region, the operations further comprising:
determining a roll constraint based on the first region and the second region; and
determining, based on the roll constraint, the first ground point of the first region and the second ground point of the second region.
13 . The one or more non-transitory computer-readable media of claim 6 , wherein determining the first region is based at least in part on a position associated with the vehicle or a previous ground point associated with a previous region associated with the path.
14 . A method comprising:
receiving sensor data from a sensor associated with a vehicle;
determining, based on the sensor data, sensor data points associated with a path of the vehicle;
determining, based on a first metric and a second metric, a first region;
determining, based at least in part on the first region, a first subset of the sensor data points;
determining, based on the first subset of the sensor data points, a first ground point;
determining, based on a third metric and a fourth metric, a second region, wherein the second region includes a second subset of the sensor data points;
determining, based on the second subset of the sensor data points, a second ground point;
determining a ground profile based at least in part on the first ground point and the second ground point; and
controlling the vehicle based on the ground profile.
15 . The method of claim 14 , further comprising:
excluding the sensor data points associated with the path of the vehicle;
identifying, based at least in part on the sensor data and the ground profile, a second subset of sensor data points;
detecting, based at least in part on the second subset of sensor data points, an object; and
controlling the vehicle based on the object.
16 . The method of claim 14 , wherein the first metric comprises a first maximum slope and the second metric comprises a first minimum slope.
17 . The method of claim 14 , further comprising:
determining a distance between a first sensor data point and the path; and
determining a weight based on the distance,
wherein determining the first ground point is based at least in part on the weight.
18 . The method of claim 14 , further comprising:
determining that a second subset of sensor data points associated with the second region is less than a threshold number of points;
determining a fifth metric and a sixth associated with a third region based on the third metric and the fourth metric; and
determining, based on a third subset of the sensor data points included in the third region, a third ground point, wherein determining the ground profile is further based at least in part on the second ground point.
19 . The method of claim 14 , wherein the first region is laterally adjacent to the second region, the method further comprising:
determining a roll constraint based on the first region and the second region; and
determining, based on the roll constraint, the first ground point of the first region and the second ground point of the second region.
20 . The method of claim 14 , wherein determining the first region is based at least in part on a position associated with the vehicle or a previous ground point associated with a previous region associated with the path.