Reader small image

You're reading from  Hands-On Vision and Behavior for Self-Driving Cars

Product typeBook
Published inOct 2020
PublisherPackt
ISBN-139781800203587
Edition1st Edition
Tools
Right arrow
Authors (2):
Luca Venturi
Luca Venturi
author image
Luca Venturi

Luca Venturi has extensive experience as a programmer with world-class companies, including Ferrari and Opera Software. He has also worked for some start-ups, including Activetainment (maker of the world's first smart bike), Futurehome (a provider of smart home solutions), and CompanyBook (whose offerings apply artificial intelligence to sales). He worked on the Data Platform team at Tapad (Telenor Group), making petabytes of data accessible to the rest of the company, and is now the lead engineer of Piano Software's analytical database.
Read more about Luca Venturi

Krishtof Korda
Krishtof Korda
author image
Krishtof Korda

Krishtof Korda grew up in a mountainside home over which the US Navy's Blue Angels flew during the Reno Air Races each year. A graduate from the University of Southern California and the USMC Officer Candidate School, he set the Marine Corps obstacle course record of 51 seconds. He took his love of aviation to the USAF, flying aboard the C-5M Super Galaxy as a flight test engineer for 5 years, and engineered installations of airborne experiments for the USAF Test Pilot School for 4 years. Later, he transitioned to designing sensor integrations for autonomous cars at Lyft Level 5. Now he works as an applications engineer for Ouster, integrating LIDAR sensors in the fields of robotics, AVs, drones, and mining, and loves racing Enduro mountain bikes.
Read more about Krishtof Korda

View More author details
Right arrow

An example MPC in C++

A full implementation of MPC is beyond the scope of this chapter but you can review this example implementation written in C++ at https://github.com/Krishtof-Korda/CarND-MPC-Project-Submission/blob/master/src/MPC.cpp.

The following example will walk you through the implementation of an MPC module that you can use in place of a PID controller for both lateral and longitudinal control. Recall that MPC is a MIMO system, meaning you can control multiple outputs.

The following example shows all the basic components and code you'll need to build an MPC controller:

  1. First, use the following code to fit a polynomial to your prediction horizon waypoints:
    Main.cpp --> polyfit()

    Use the following code to calculate cross-tracking errors:

    Main.cpp --> polyeval()
    double cte = polyeval(coeffs, px) - py;

    Use the following code to calculate orientation errors:

    double epsi = psi - atan(coeffs[1] + 2*coeffs[2]*px + 3*coeffs[3]*px*px) ;
  2. Now, we use MPC.cpp...
lock icon
The rest of the page is locked
Previous PageNext Page
You have been reading a chapter from
Hands-On Vision and Behavior for Self-Driving Cars
Published in: Oct 2020Publisher: PacktISBN-13: 9781800203587

Authors (2)

author image
Luca Venturi

Luca Venturi has extensive experience as a programmer with world-class companies, including Ferrari and Opera Software. He has also worked for some start-ups, including Activetainment (maker of the world's first smart bike), Futurehome (a provider of smart home solutions), and CompanyBook (whose offerings apply artificial intelligence to sales). He worked on the Data Platform team at Tapad (Telenor Group), making petabytes of data accessible to the rest of the company, and is now the lead engineer of Piano Software's analytical database.
Read more about Luca Venturi

author image
Krishtof Korda

Krishtof Korda grew up in a mountainside home over which the US Navy's Blue Angels flew during the Reno Air Races each year. A graduate from the University of Southern California and the USMC Officer Candidate School, he set the Marine Corps obstacle course record of 51 seconds. He took his love of aviation to the USAF, flying aboard the C-5M Super Galaxy as a flight test engineer for 5 years, and engineered installations of airborne experiments for the USAF Test Pilot School for 4 years. Later, he transitioned to designing sensor integrations for autonomous cars at Lyft Level 5. Now he works as an applications engineer for Ouster, integrating LIDAR sensors in the fields of robotics, AVs, drones, and mining, and loves racing Enduro mountain bikes.
Read more about Krishtof Korda