CarND-Controls-PID

Self-Driving Car Engineer Nanodegree Program

Demo

alt text

Description

The vehicle is controlled by two PID controllers. One of them takes the cross track error as an input and produces the correcting steering angle, while another one takes as an input maximum between absolute values of the cross track error and the steering angle and produces the throttle value. The latter should be responsive to changes of the parameters it depends on since it is reasonable to decrease speed either when the steering angle is steep or when there is a considerable cross track error.

P - the proportional component of the PID controller. It steers the car along to road center, reference line. The larger the corresponding coefficient (parameter of the PID controller) the steeper steering angles. When this component used alone, the car starts to oscillate, and the oscillation amplitude increases with the time until, finally, the car crashes or leaves the road.

I - the integral component of the PID controller. It is responsible for compensating the bias that the car's steering wheel might have. When this component used alone, the car leaves the road and starts the circular motion.

D - the differential component of the PID controller. It is responsible for smoothing the car's oscillations around the reference line. It compensates the steering angle when the car approaches the center of the road. When this component used alone, the car is irresponsive to the road steepness and reacts only to little changes in the steepness. The car leaves the road as soon as the steep enough turn occurs.

Parameter Tuning

Initially, the throttle was constant, and the parameters of the PID controller for steering were chosen to be P = 0.2, I = 0.004, D = 3.0. These parameters are given in video lessons. These parameters worked quite well, and the car was able to complete the full circle with no tire leaving the drivable portion of the track surface.

However, the driving was not smooth. There are still many oscillations in steep lane corner. The twiddle algorithm was utilized to tune the parameters of the PID controller for steering. After a few iterations, the PID controller for throttle was turned on. At that moment parameters for steering PID controller were P=0.64, I=0.0238, D=14.0 and for throttle PID controller -- P=2.0, I=0.0, D=3.0. Then, there were a few more iterations after which there was a manual fine tuning again. Basically, larger P for steer needs larger P for throttle so that the speed is low enough for relatively big steer angle. And although we use D to make steer smooth but we still need to choose relatively small P to reduce oscillations (for steer value). The result parameters for the PID controllers are as follows: steering PID controller -- P=0.15, I=0.0188, D=5.0; throttle PID controller -- P=6.0, I=0.0, D=2.0. With these parameters, the car can drive with the average speed close to 30 mph and smooth enough, without leaving the road surface.


Dependencies

Fellow students have put together a guide to Windows set-up for the project here if the environment you have set up for the Sensor Fusion projects does not work for this project. There's also an experimental patch for windows in this PR.

Basic Build Instructions

  1. Clone this repo.
  2. Make a build directory: mkdir build && cd build
  3. Compile: cmake .. && make
  4. Run it: ./pid.

Tips for setting up your environment can be found here

Editor Settings

We've purposefully kept editor configuration files out of this repo in order to keep it as simple and environment agnostic as possible. However, we recommend using the following settings:

  • indent using spaces
  • set tab width to 2 spaces (keeps the matrices in source code aligned)

Code Style

Please (do your best to) stick to Google's C++ style guide.

Project Instructions and Rubric

Note: regardless of the changes you make, your project must be buildable using cmake and make!

More information is only accessible by people who are already enrolled in Term 2 of CarND. If you are enrolled, see the project page for instructions and the project rubric.

Hints!

  • You don't have to follow this directory structure, but if you do, your work will span all of the .cpp files here. Keep an eye out for TODOs.

Call for IDE Profiles Pull Requests

Help your fellow students!

We decided to create Makefiles with cmake to keep this project as platform agnostic as possible. Similarly, we omitted IDE profiles in order to we ensure that students don't feel pressured to use one IDE or another.

However! I'd love to help people get up and running with their IDEs of choice. If you've created a profile for an IDE that you think other students would appreciate, we'd love to have you add the requisite profile files and instructions to ide_profiles/. For example if you wanted to add a VS Code profile, you'd add:

  • /ide_profiles/vscode/.vscode
  • /ide_profiles/vscode/README.md

The README should explain what the profile does, how to take advantage of it, and how to install it.

Frankly, I've never been involved in a project with multiple IDE profiles before. I believe the best way to handle this would be to keep them out of the repo root to avoid clutter. My expectation is that most profiles will include instructions to copy files to a new location to get picked up by the IDE, but that's just a guess.

One last note here: regardless of the IDE used, every submitted project must still be compilable with cmake and make./

How to write a README

A well written README file can enhance your project and portfolio. Develop your abilities to create professional README files by completing this free course.