zeulus / carla-driver

The CarND Capstone Project

Carla Driver

• This is the capstone project for Udacity's Self Driving Car Nanodegree. This code is aimed to run in an actual physical self-drive vehicle.

Team Members

This repository is maintained by the following:

• Lukasz Janyst ([e-mail])
• Mithi Sevilla ([e-mail])
• Maurice Loskyll ([e-mail])
• Kostas Oreopoulos ([e-mail])

Installation

• Install ROS Kinetic
• Dataspeed DBW
  • Use this option to install the SDK on a workstation that already has ROS installed: One Line SDK Install (binary)
• Download the Udacity Simulator.

Usage

1. Clone the project repository

git clone https://github.com/udacity/carla-driver.git

2. Install python dependencies

cd carla-driver
pip install -r requirements.txt

3. Install ROS dependencies

sudo apt install ros-kinetic-pcl-ros

4. Download the TensorFlow models to your ~/.ros directory

• Classifier
• Detector

5. Make and run styx

cd ros
catkin_make
source devel/setup.sh
roslaunch launch/styx.launch

6. Run the simulator

unzip linux_sys_int.zip (if you use linux)
cd linux_sys_int
chmod +x system_integration.x86_64
./system_integration.x86_64