Git Product home page Git Product logo

pid-for-self-driving-cars's Introduction

CarND-Controls-PID

Self-Driving Car Engineer Nanodegree Program


Description

In this project, a PID controller is implemented to control a self-driving car on a simulated track.

Parameter Tuning

I follow the tuning procedure on Wiki:

pid

  • First increase Kp to let the car have a steady oscillation around the desired trajectory.
  • Increase Kd until the oscillation goes away.
  • Slightly increase the Ki to bring the system to desired trajectory(with cte around 0). This would introduce some overshot but give the system a quicker response.

I tuned the controller manually. Initially I first use [0.1,0,0] (Kp,Ki,Kd) and slightly increase Kp to 0.13 to have a steady oscilation, then I increased the Kd term to 2.6 to stop the oscilation. I tried to increase Ki to have a quicker response but it introduce more oscilation. Therefore I set it to 0.

Effect of P, I, D

  • The proportional gain Kp would steer the car towards the center line. But this would always overshoot.
  • The integral portion would eliminate a possible bias on the controlled system. Normally it would lead to a quicker response but alse introduce a little bit oscillations.
  • The differential portion helps to smooth the oscillation introduced by the Kp. But if it is too large the car would start to chatter.

Dependencies

pid-for-self-driving-cars's People

Contributors

domluna avatar wpihwzhao avatar baumanab avatar mvirgo avatar swwelch avatar davidobando avatar citlaligm avatar htuennermann avatar

Watchers

James Cloos avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.