Automatic optimization of obstacle detection
AssigneeTrimble Inc.
InventorsJuan Cheng, Thomas Sterling, Ulrich Vollath, Brandon Sights
Life of this patent
Estimating the term…
Abstract
Disclosed are techniques for automatically optimizing radar filter parameters. In embodiments, radar sensor data is captured from a radar sensor on a moving machine/vehicle. The radar sensor data is filtered using radar filter parameters to produce filtered radar sensor data. Radar obstacle points are produced from the filtered radar sensor data. Lidar sensor data is captured from a lidar sensor on the moving machine. Lidar obstacle points are produced from the lidar sensor data. The radar filter parameters are optimized using the lidar obstacle points.
Claims20
A method comprising:
- capturing radar sensor data from a radar sensor;
- filtering the radar sensor data using radar filter parameters to produce filtered radar sensor data;
- producing radar obstacle points from the filtered radar sensor data;
- capturing lidar sensor data from a lidar sensor;
- producing lidar obstacle points from the lidar sensor data;
- and
- optimizing the radar filter parameters using the lidar obstacle points.
A method comprising:
- capturing radar sensor data from a radar sensor on a moving machine;
- filtering the radar sensor data using radar filter parameters to produce filtered radar sensor data;
- producing radar obstacle points from the filtered radar sensor data;
- capturing lidar sensor data from a lidar sensor on the moving machine;
- producing lidar obstacle points from the lidar sensor data;
- and
- optimizing the radar filter parameters using the lidar obstacle points, by tuning the radar filter parameters to maximize the number of true positives;
- wherein the optimizing further includes:
- determining spatial filter bounding areas for obstacles identified by the lidar obstacle points, and
- identifying radar obstacle points inside the spatial filter bounding areas as true positives;
- and
- wherein the radar sensor filter parameters are optimized for a signal-to-noise (SNR) filter and a spatial-temporal filter.
An apparatus comprising:
- a radar sensor mounted on a moving machine;
- a lidar sensor mounted on the moving machine;
- a processor mounted on the moving machine;
- a memory mounted on the moving machine and containing non-transitory, computer readable media with instructions for:
- capturing radar sensor data from a radar sensor;
- filtering the radar sensor data using radar filter parameters to produce filtered radar sensor data;
- producing radar obstacle points from the filtered radar sensor data;
- capturing lidar sensor data from a lidar sensor;
- producing lidar obstacle points from the lidar sensor data;
- and
- optimizing the radar filter parameters using the lidar obstacle points.
Dependencies are inferred from the claim text.