Udacity Self-Driving Car Engineer Nanodegree

Term 2 P3: Kidnapped Vehicle Project

Overview

This repository contains all the code for the final project for the Localization course in Udacity's Self-Driving Car Nanodegree.

Project Introduction

Your robot has been kidnapped and transported to a new location! Luckily it has a map of this location, a (noisy) GPS estimate of its initial location, and lots of (noisy) sensor and control data.

In this project you will implement a 2 dimensional particle filter in C++. Your particle filter will be given a map and some initial localization information (analogous to what a GPS would provide). At each time step your filter will also get observation and control data.

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.

1. mkdir build
2. cd build
3. cmake ..
4. make
5. ./particle_filter

Alternatively some scripts have been included to streamline this process, these can be leveraged by executing the following in the top directory of the project:

1. ./clean.sh
2. ./build.sh
3. ./run.sh

Tips for setting up your environment can be found here

Note that the programs that need to be written to accomplish the project are src/particle_filter.cpp, and particle_filter.h

The program main.cpp has already been filled out, but feel free to modify it.

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

// sense noisy position data from the simulator

["sense_x"]

["sense_y"]

["sense_theta"]

// get the previous velocity and yaw rate to predict the particle's transitioned state

["previous_velocity"]

["previous_yawrate"]

// receive noisy observation data from the simulator, in a respective list of x/y values

["sense_observations_x"]

["sense_observations_y"]

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

// best particle values used for calculating the error evaluation

["best_particle_x"]

["best_particle_y"]

["best_particle_theta"]

//Optional message data used for debugging particle's sensing and associations

// for respective (x,y) sensed positions ID label

["best_particle_associations"]

// for respective (x,y) sensed positions

["best_particle_sense_x"] <= list of sensed x positions

["best_particle_sense_y"] <= list of sensed y positions

Your job is to build out the methods in particle_filter.cpp until the simulator output says:

Success! Your particle filter passed!

Implementing the Particle Filter

The directory structure of this repository is as follows:

root
|   build.sh
|   clean.sh
|   CMakeLists.txt
|   README.md
|   run.sh
|
|___data
|   |
|   |   map_data.txt
|
|
|___src
    |   helper_functions.h
    |   main.cpp
    |   map.h
    |   particle_filter.cpp
    |   particle_filter.h

The only file modified is particle_filter.cpp in the src directory. The file contains the scaffolding of a ParticleFilter class and some associated methods. Read through the code, the comments, and the header file particle_filter.h to get a sense for what this code is expected to do.

The src/main.cpp file contains the code that will actually be running of the particle filter and calling the associated methods.

Inputs to the Particle Filter

The inputs to the particle filter are in the data directory.

The Map*

map_data.txt includes the position of landmarks (in meters) on an arbitrary Cartesian coordinate system. Each row has three columns

1. x position
2. y position
3. landmark id

All other data the simulator provides, such as observations and controls

• Map data provided by 3D Mapping Solutions GmbH.

Success Criteria

If your particle filter passes the current grading code in the simulator (you can make sure you have the current version at any time by doing a git pull), then you should pass!

The things the grading code is looking for are:

1. Accuracy: your particle filter should localize vehicle position and yaw to within the values specified in the parameters max_translation_error and max_yaw_error in src/main.cpp.

2. Performance: your particle filter should complete execution within the time of 100 seconds.

Algorithm Overview

In this C++ project, a two-dimensional particle filter is used to help localize a car placed in an unknown location. I began by using less accurate map data to initialize the car's location. The new location is predicted based on velocity and yaw rate. The landmarks observed by the sensor are converted into map coordinates. These landmarks are then associated with landmarks on the map, and then the likelihood that a given particle made those observation based off of the landmark positions in the map is calculated. The particles were then re-sampled based on how likely a given particle was to have made the observations of the landmarks, which helps to more accurately localize the vehicle.

Real world implementation

In this project the GPS information is only used at the beginning to get the ball rolling. After this point only observations and map landmarks are used to localize. A possiblity here would be to initiate a few particles with the new GPS information we get with reasonably high weights for them to get through resampling also.

For further information on landmarks in real world scenarios watch: https://youtu.be/n8T7A3wqH3Q?t=2481

Difference between UKF and PF

Look at the following information:

• https://discussions.udacity.com/t/difference-between-ukf-and-particle-filter/299290/3
• https://www.quora.com/What-is-the-difference-between-a-particle-filter-and-a-Kalman-filter/answer/Jim-Reich?srid=ohBJ