/CarND-Catch-Run-Away-Car-UKF

In this Bonus Challenge an Unscented Kalman Filter is used to try and catch a car moving in a continuous circle at constant velocity.

Primary LanguageC++

Run Away Robot with Unscented Kalman Filter Bonus Challenge

Self-Driving Car Engineer Nanodegree Program

Overview

This repository contains all the code for the Bonus Challenge: Catch the Run Away Car with Unscented Kalman Filter.

Project Introduction

In this project an UKF is used to catch an escaped car driving in a circular path. The run away car is sensed by a stationary sensor, that is able to measure both noisy lidar and radar data. The capture vehicle needs to use these measurements to close in on the run away car. To capture the run away car the capture vehicle needs to come within .1 unit distance of its position. However the capture car and the run away car have the same max velocity, so if the capture vehicle wants to catch the car, it will need to predict where the car will be ahead of time. This is in this implementation achived by aiming for the predicted run away car state a certain number of time steps into the future. The number of time steps used is determined depending on the distance between the vehicles.

Running the Code

This project involves the Term 2 Simulator which can be downloaded here.

This repository includes two files that can be used to set up and intall uWebSocketIO for either Linux or Mac systems. For windows you can use either Docker, VMware, or even Windows 10 Bash on Ubuntu to install uWebSocketIO.

Once the install for uWebSocketIO is complete, the main program can be built and ran by doing the following from the project top directory.

mkdir build

cd build

cmake .. make

./UnscentedKF

Here is the main protcol that main.cpp uses for uWebSocketIO in communicating with the simulator.

INPUT: values provided by the simulator to the c++ program

// current noiseless position state of the capture vehicle, called hunter

["hunter_x"]

["hunter_y"]

["hunter_heading"]

// get noisy lidar and radar measurments from the run away car.

["lidar_measurement"]

["radar_measurement"]

OUTPUT: values provided by the c++ program to the simulator

// best particle values used for calculating the error evaluation

["turn"] <= the desired angle of the capture car "hunter" no limit for the anlge

["dist"] <= the desired distance to move the capture car "hunter" can't move faster than run away car

Dependencies

  • cmake >= v3.5
  • make >= v4.1
  • gcc/g++ >= v5.4
  • uWebSocketIO

Basic Build Instructions

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