Systems and methods for calibration and validation of non-overlapping range sensors of an autonomous vehicle
AssigneeFord Global Technologies, LLC
InventorsHatem Alismail, Michael Schoenberg
Life of this patent
Estimating the term…
Abstract
Methods and systems for performing intrinsic calibration of a LiDAR sensor mounted on a vehicle are disclosed. The methods include collecting sensor data corresponding to a calibration environment from the LiDAR sensor, defining a model of one or more intrinsic parameters of the LiDAR sensor, solving the model to intrinsically calibrate the LiDAR sensor by optimizing an objective function, and generating calibrated sensor data for controlling navigation of the vehicle.
Claims18
A method for intrinsic calibration of a LiDAR sensor mounted on a vehicle, the method comprising:
- collecting, from the LiDAR sensor having a plurality of laser scanners to emit a plurality of beams, sensor data corresponding to a calibration environment having one or more calibration targets provided at known positions from the vehicle, the sensor data including measurements taken by plurality of laser scanners;
- defining a model of one or more intrinsic parameters of the LiDAR sensor using a linear model that includes a gain and a bias, the model representing, for each laser scanner, a position of a measurement taken by a respective laser scanner;
- solving, by optimizing an objective function, the model using the sensor data collected from the plurality of laser scanners of the LiDAR sensor to intrinsically calibrate the LiDAR sensor;
- and
- generating, from the calibrated LiDAR sensor, calibrated sensor data for controlling navigation of the vehicle.
A system for intrinsic calibration of a LiDAR sensor, the system comprising:
- a LiDAR sensor mounted on a vehicle and having a plurality of laser scanners to emit a plurality of beams;
- at least one processor;
- and
- programming instructions stored in a memory and configured to cause the processor to:
- collect, from the LiDAR sensor, sensor data corresponding to a calibration environment having one or more calibration targets provided at known positions from the vehicle, the sensor data including measurements taken by plurality of laser scanners,
- define a model of one or more intrinsic parameters of the LiDAR sensor using a linear model that includes a gain and a bias, the model representing, for each laser scanner, a position of a measurement taken by a respective laser scanner,
- solve, by optimizing an objective function, the model using the sensor data collected from the plurality of laser scanners of the LiDAR sensor to intrinsically calibrate the LiDAR sensor, and
- generate, from the calibrated LiDAR sensor, calibrated sensor data for controlling navigation of the vehicle.
A computer program product comprising a non-transitory computer-readable medium that stores instructions that, when executed by a computing device, will cause the computing device to perform operations comprising:
- collecting, from a LiDAR sensor having a plurality of laser scanners to emit a plurality of beams, sensor data corresponding to a calibration environment having one or more calibration targets provided at known positions from a vehicle, the sensor data including measurements taken by plurality of laser scanners;
- defining a model of one or more intrinsic parameters of the LiDAR sensor using a linear model that includes a gain and a bias, the model representing, for each laser scanner, a position of a measurement taken by a respective laser scanner;
- solving, by optimizing an objective function, the model using the sensor data collected from the plurality of laser scanners of the LiDAR sensor to intrinsically calibrate the LiDAR sensor to provide a calibrated LiDAR sensor;
- and
- generating, from the calibrated LiDAR sensor, calibrated sensor data for controlling navigation of the vehicle.
Dependencies are inferred from the claim text.