If a sensor’s position or inherent properties deviate from nominal/assumed parameters, then any downstream processing may be faulty, whether it’s for self-driving or data collection. NVIDIA DRIVE™ Calibration gives you a reliable foundation for building autonomous vehicle (AV) solutions with the assurance that they’ll achieve high fidelity, consistent, up-to-date sensor data. DRIVE Calibration supports calibration of the vehicle’s camera, LIDAR, radar, and Inertial Measurement Unit (IMU) sensors that are compatible with the DriveWorks Sensor Abstraction Layer.

DRIVE Calibration is open and modular, so AV developers can find the ideal capabilities for their application.

  • One-time calibration of sensors (such as a manufacturing facility)
  • Continuous calibration of sensors
  • Estimating odometric and inertial information about an ego-vehicle

Details


Static Calibration Tools

Static Calibration usually takes place at the factory or in service centers and is ideal for initial calibration or re-calibrating after major changes on the vehicle like bodywork. Benefits include generalized techniques for calibrating AV sensors, minimization of floorspace, time, and costs of static calibration, and more accurate self-calibration.

DriveWorks Static Calibration Tools provide ground truth for AV sensors by measuring manufacturing variation to a high degree of accuracy. Camera Calibration includes both extrinsic and intrinsic calibration, while the IMU Calibration Tool calibrates vehicle orientation with respect to the coordinate system.



Self-Calibration

Self-Calibration provides real-time compensation for environmental changes or mechanical stress on sensors caused by events such as changes in road gradient, tire pressure, vehicle passenger loading, and other minor changes. It corrects nominal calibration parameters (captured using the Static Calibration Tools) based on current sensor measurements in real-time, meaning that the algorithms are performant, safety-compliant, and optimized for the platform.


Egomotion Module

The DriveWorks Egomotion module uses a motion model to track and predict a vehicle’s pose. DriveWorks uses two types of motion models: an odometry-only model and, if an IMU is available, a model based on IMU and odometry.






Developing with DRIVE Calibration


How to set up

You will need:

Steps:

  • Install DRIVE Calibration using the SDK Manager.
  • Refer to the DRIVE Core "How to setup" section to prepare your development environment and familiarize yourself with DriveWorks samples.

How to develop

Development Tasks Getting Started
One-time calibration of sensors mounted on a vehicle i.e. measure and record nominal calibration parameters using Static Calibration Tools

DRIVE Hyperion is recommended but not required.

Follow the “Camera Calibration Tutorial” in the "Tutorials" section of the DriveWorks SDK Reference Guide contained in the DRIVE Software Documentation

For IMU Calibration and additional information, refer to "Calibration Tools" under the "Tools" section of the DriveWorks SDK Reference Guide contained in the DRIVE Software Documentation

Dynamic calibration of sensors to help algorithms converge before driving an AV. Develop self-calibration capabilities for your solution using DRIVE Calibration.

There are several samples included in the “samples” section of DriveWorks SDK Reference guide contained in the DRIVE Software Documentation.

For more detail and examples on how to use the DRIVE Calibration self-calibration modules, please refer to the following samples:

Camera Self-Calibration: includes methods for dynamically estimating the pitch, roll, yaw, and height of all of the vehicle’s externally facing cameras. These modules are required for applications such as consistent lane holding and accurate distance estimation

  • Camera Calibration Sample: Demonstrates the ability to estimate camera extrinsics using the DriveWorks Calibration Engine.

IMU Self-Calibration uses a robust algorithm to estimate the extrinsic parameters of the IMU sensor with respect to the vehicle’s coordinate frame as the vehicle is driving. It is used to accurately estimate and predict the vehicle’s pose.

  • IMU Calibration Sample: Demonstrates the ability to estimate IMU extrinsics using the DriveWorks Calibration Engine

LIDAR Self-Calibration estimates the current lidar orientation (roll, pitch, yaw, height) with respect to the vehicle’s coordinate system and is used in downstream perception and mapping applications.

  • LIDAR Calibration Sample: Demonstrates the ability to estimate LIDAR extrinsics using the DriveWorks Calibration Engine.

Radar Self-Calibration.

  • Radar Calibration Sample: Demonstrates how to use the radar self-calibration module.
Use the DRIVE Calibration Egomotion module to model and predict the vehicle’s motion

There are several samples included in the “samples” section of DriveWorks SDK Reference guide contained in the DRIVE Software Documentation.

For more details and examples on how to use the DRIVE Calibration Egomotion module, please refer to the following sample:

  • Egomotion Sample: Uses CAN measurements of steering angle and velocity to compute the position of the car in the world coordinate system.


Additional Development Resources:

Documentation