Self-Driving Car Engineer Nanodegree Program

This project implements unscented kalman filter to estimate the state of a moving object of interest with noisy lidar and radar measurements.

1. Initialize with the very first measurement.
2. On every incoming measurement from LIDAR/RADAR sensor, update prediction matrices using unscented kalman filter and new system state.
3. Compute RMSE, repeat Step 1 with the new error values.

1. Updated install-mac.sh to use the correct openssl path
2. Implemented Unscented Kalman filter in the class UKF, in the file ukf.cpp
3. Implemented RMSE calculation function in tools.cpp.

Dataset 1

Dataset 2

• The above diagrams show the results when executing the program against the simulator for two different datasets.
• The program has to be restarted when switching between the datasets. (Scope for improvement)

Optimization of standard deviation values for longitudinal & yaw acceleration values over Dataset 1

Install uWebSocketIO for the respective Operating System by following the documentation here

1. Clone this repo.
2. Make a build directory: mkdir build && cd build
3. Compile: cmake .. && make
   • On windows, you may need to run: cmake .. -G "Unix Makefiles" && make
4. Run it: ./UnscentedKF