Skip to content

Implementation of a simple 2D UKF and EKF using an CTRV kinematics model with lidar and radar measurements.

Notifications You must be signed in to change notification settings

da-phil/SDC-Unscented-Kalman-Filter

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

69 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Unscented Kalman Filter Project Starter Code

Self-Driving Car Engineer Nanodegree Program

In this project utilize an Unscented Kalman Filter to estimate the state of a moving object of interest with noisy lidar and radar measurements. Passing the project requires obtaining RMSE values that are lower that the tolerance outlined in the project rubric.

Installation / Requirements

This project can be either used with *.csv text files or with a visualization in a 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. Please see this concept in the classroom for the required version and installation scripts.

Other Important Dependencies

Basic Build Instructions

  1. Clone this repo.
  2. Make a build directory: mkdir build && cd build
  3. Compile: cmake .. && make
  4. Run it: ./UnscentedKF Previous versions use i/o from text files. The current state uses i/o from the simulator.

Running the program

Program documentation

Help:
  --verbose        <0|1>:    Turn on verbose output, default: 0
  --use_laser      <0|1>:    Turn on or off laser measurements, default: 1
  --use_radar      <0|1>:    Turn on or off radar measurements, default: 1
  --std_a          <num>:    Standard deviation for linear acceleration noise, default: 0.5
  --std_yawdd      <num>:    Standard deviation for angular acceleration noise, default: 0.2
  --use_simulator  <0|1>:    Use simulator for input and output or instead an input output csv file, default: 1
  --input_file     <path>:   Path to input csv file (only possible when simulator mode is not set), default: ../data/obj_pose-laser-radar-synthetic-input.txt
  --output_file    <path>:   Path to output csv file (only possible when simulator mode is not set), default: ../data/obj_pose-fused-output.txt
  --help:                    Show help

The program supports two modes: simulator backend (--use_simulator=1) and data files as in- and output (--use_simulator=0)

Simulator mode

When using the simulator mode the unity based udacity simulator mentioned above has to be started and the first menu option selected. Then the UKF can be started by invoking:

./UnscentedKF --use_simulator=1

Data file mode

Start the program using udacity provided data/obj_pose-laser-radar-synthetic-input.txt file as input and storing the filtered states, rmse and ground truth for evaluation and visualization in data/obj_pose-fused-output-all.txt:

./UnscentedKF --use_simulator=0 --input_file=../data/obj_pose-laser-radar-synthetic-input.txt --output_file=../data/obj_pose-fused-output-all.txt

Using the same input and output files but deactivating the laser scanner and only using the radar data for filtering (can't be called sensor fusion anymore, I guess):

./UnscentedKF --use_simulator=0 --use_laser=0 --input_file=../data/obj_pose-laser-radar-synthetic-input.txt --output_file=../data/obj_pose-fused-output-all.txt

Results

The following plot shows how the UFK filter compares using data from both lidar and radar sensor and having ony either as input.

As cartesian positions are directly observable by the lidar sensor the accuracy is pretty good. It will be more interesting to see how well the filter performes at predicting hidden states such as cartesian velocities. In the following plot we look at how well cartesian velocities are being predicted, just in the same manner as above, one plot is with both sensor inputs and in the other plots only either sensor being used.

In this plot we see the RMSE in cartesian position and velocity over time. It's interesting to see how the error in the velocities seems to have asymptotic behaviour towards the end of the dataset.

About

Implementation of a simple 2D UKF and EKF using an CTRV kinematics model with lidar and radar measurements.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published