Self-Driving Car Engineer Nanodegree Program

You can watch the video of the resulting performance of the controller here.

In this project, a PID algorithm is implemented to follow a given trajectory on a self-driving car. The PID controller is an algorithm used to follow a reference through a closed loop system that calculates the error from a setpoint and the actual state of the system and set the control input as a proportion of this cross-track error or CTE. The setpoint is the x and y coordinates at the center of the road of the desired trajectory of the car.

In the PID algorithm, the P stands for proportional, the I for integral and the D for differential. Each part of the algorithm plays an important role to control the position of the car and how it reaches the goal position. The P and D modifies the transient response of the system and the I eliminates the steady state error. These gains do this job through the error of the system. The proportional gain means that the steering angle of the car will be set in the proportion of the CTE. The integral part accumulates the CTE up to the current point. The sign of that accumulative error means which side of the road the car has been for a while in. The D part takes the rate of change of CTE and a high value will result in high overshooting.

In the PID algorithm, the P stands for proportional, the I for integral and the D for differential. Each part of the algorithm plays an important role to control the postion of the car and how it reaches the goal position. The P and D modifies the transient response of the system and the I eliminates the steady state error. These gains do this job through the error of the system. The proportional gain means that the steering angle of the car will be set in proportion of the CTE. The integral part accumulate the CTE up to the current point. The sign of that accumulative error means which side of the road the car has been for a while in. The D parte takes the rate of change of CTE and a high value will result in high overshooting.

The architecture of the controller is:

steering_angle = P*cte + I*cte_integral + D*cte_differential

Tunning the gains is not an easy task. A high I gain turns into sharp oscilations and the car will roll out of the road. Similarly, finding the right P and D should be done also carfully to improve the transient response. If the P gain is to high, the car will overcorrect the CTE and improve amplitud of oscilations or if it is to low, it will have a really slow reaction, which is not a good scenario when refering to curves.

The strategy that I followed was, first by hand, I chose gains and saw how the system behaved. The values selected for P, I and D were -0.16, 0.0 and -2.5, respectively. Then, I used Twiddle to fine tune the controller. You can see the code of the Twiddle algorithm at the PID.cpp from line 60 to 109. On the main file I set to false the variable do_twiddle due to the fact that my controller is already tune. If you want to do_twiddle, set this boolean variable to true on line 90.

The final gains are:

• Kp = -0.161991
• Ki = -0.000008
• Kd = -2.49979

• cmake >= 3.5
• All OSes: click here for installation instructions
• make >= 4.1(mac, linux), 3.81(Windows)
  • Linux: make is installed by default on most Linux distros
  • Mac: install Xcode command line tools to get make
  • Windows: Click here for installation instructions
• gcc/g++ >= 5.4
  • Linux: gcc / g++ is installed by default on most Linux distros
  • Mac: same deal as make - [install Xcode command line tools]((https://developer.apple.com/xcode/features/)
  • Windows: recommend using MinGW
• uWebSockets
  • Run either ./install-mac.sh or ./install-ubuntu.sh.
  • If you install from source, checkout to commit e94b6e1, i.e.

    git clone https://github.com/uWebSockets/uWebSockets 
    cd uWebSockets
    git checkout e94b6e1
    

    Some function signatures have changed in v0.14.x. See this PR for more details.
• Simulator. You can download these from the project intro page in the classroom.

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.

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

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)

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

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.

• 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.

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./

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