A proportional–integral–derivative controller (PID controller) is a control loop feedback mechanism (controller) commonly used in industrial control systems. In this case the PID controller is used to control a vehicle steering according to cross track error (cte) provided by udacity simulator.
steering = -Kp * CTE - Kd * diff_CTE - Ki * int_CTE
TWIDDLE algorithm is also used here to get the optimized hyperparameters (P, I, D coefficients). After steering angle PID controller, a similar PID is applied to control vehicle throttle value and to maximum vehicle speed and keep the vehicle in the drivable portion.
Kp is the proportional gain, which produces an output value that is proportional to the current cross track error value. Steering is in proportional to cross track error is a effective solution to control cars while at same time generate oscillation.
Kd is the derivative gain, which multiply the derivative of the process error can improves settling time and stability of the system to beat oscillation.
Ki is the integral gain. The integral in a PID controller is the sum of the instantaneous error over time and gives the accumulated offset that should have been corrected previously. The accumulated error is then multiplied by the integral gain (Ki) and added to the controller output. The integral term accelerates the movement of the process towards setpoint and eliminates the residual steady-state error that occurs with a pure proportional controller. However, it can cause oscillation at same time.
More hyperparameters tuning can reference wikipedia
Sample hyperparameters in class Kp, Kd, Ki (0.2, 3, 0.004) is used to initialize here, then the twiddle will calculate the optimized hyperparameters later.
The cost function is defined and shown below. Target speed here is 100mph while speed difference with target speed is considered in cost functions.
if (n_step > n_thres) {
// cost error fuction.
t_error += cte*cte;
t_error += pow((speed-speed_limit)/speed_limit, 2);
}
With cte from simulator each step, PID first update all related errors including p_error, d_error and i_error, then use twiddle function to iterate hyperparameters and return steering angle with PID equations mentioned above.
A similar PID is applied here to control throttle value here and initialized as below.
pid_thro.Init(0.1, 0.002, 12);
Same twiddle to optimize hyperparameters for throttle value. Contrary to steering angle PID equations, these following PID equations is used to determine throttle value and return to simulator.
double throttle_position = 1.0-Kp*fabs(p_error) - Kd*fabs(d_error) - Ki*fabs(i_error);
throttle_position = throttle_position > 1? 1:throttle_position;
throttle_position = throttle_position <-1? -1:throttle_position;
As video shows, the vehicle successfully drive a lap around the track.
The maximum speed is about 50 mph before bridge.
Cost function definition is very important in this case while have to ignore n_thres steps.
Through twiddle can scan and find the optimized hyperparameters to some extend, the initialization is still a key factor to make it works since this case is a real time system.
Throttle PID almost is optimized manually.
Self-Driving Car Engineer Nanodegree Program
- cmake >= 3.5
- All OSes: click here for installation instructions
- make >= 4.1
- 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 == 0.13, but the master branch will probably work just fine
- Follow the instructions in the uWebSockets README to get setup for your platform. You can download the zip of the appropriate version from the releases page. Here's a link to the v0.13 zip.
- If you run OSX and have homebrew installed you can just run the ./install-mac.sh script to install this
- Simulator. You can download these from the project intro page in the classroom.
- Clone this repo.
- Make a build directory:
mkdir build && cd build
- Compile:
cmake .. && make
- Run it:
./pid
.
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./