This Project is first project of second term of Udacity Self-Driving Car Nanodegree program. The goal is to apply Extended Kalman Filter to data from LIDAR and RADAR sensors by C++.

• scr contains source code:
  • main.cpp - loads data, calls a function to run the Kalman filter, calls a function to calculate RMSE
  • data_source.cpp - load input data into measurement and ground truth vectors
  • fusion_ekf.cpp - initializes the filter, calls the predict function, calls the update function
  • kalman_filter.cpp- defines the predict function, the update function for lidar, and the update function for radar
  • tools.cpp - a function to calculate RMSE and the Jacobian matrix
• data a directory with two input files, provided by Udacity
• result a directory with output files, log files and output charts
• docs a directory with files formats description

In order to see how sensor data impact accuracy of Kalman Filter, I run the algorithm on two data input (porvided by Udacity) with three calculations:

1. Lidar and Radar measurements are considered
2. Only Lidar measurements are considered
3. Only Radar measurements are considered

Here is the RMSEs comparion of expected and above calculations:

The results were visualized with Sensor Fusion utilities.

• Considering both sensor data (LIDAR and RADAR) give much better accuracy. You can see in RSME table that when we are considering both sensor data, we have acceptable RMSE.
• Lidar sensor give more accurate measurement than radar

1. Clone this repo.
2. Make a build directory: mkdir build && cd build
3. Compile: cmake ../src && make
   • On windows, you may need to run: cmake ../src -G "Unix Makefiles" && make
4. Run it: ./ExtendedKF path/to/input.txt path/to/output.txt. You can find some sample inputs in 'data/'.
   • eg. ./ExtendedKF ../data/sample-laser-radar-measurement-data-1.txt output.txt true|false true|false