cybercoderbot / carnd-capstone Goto Github PK

This is the project repo for the final project of the Udacity Self-Driving Car Nanodegree: Programming a Real Self-Driving Car. This is a collaboration between four team members:

For this project, we are writing ROS nodes to implement core functionality of the autonomous vehicle system, including traffic light detection, control, and waypoint following. The code is tested using a simulator before submission.

The following is a system architecture diagram showing the ROS nodes and topics used in the project. The ROS nodes and topics shown in the diagram are described briefly in the Code Structure section below, and more detail is provided for each node in later classroom concepts of this lesson.

Below is a brief overview of the repo structure, along with descriptions of the ROS nodes. The code that you will need to modify for the project will be contained entirely within the ,(path_to_project_repo)/ros/src/ directory. Within this directory, you will find the following ROS packages:

(path_to_project_repo)/ros/src/tl_detector/ This package contains the traffic light detection node: tl_detector.py. This node takes in data from the /image_color, /current_pose, and /base_waypoints topics and publishes the locations to stop for red traffic lights to the /traffic_waypoint topic.

The /current_pose topic provides the vehicle's current position, and /base_waypoints provides a complete list of waypoints the car will be following.

You will build both a traffic light detection node and a traffic light classification node. Traffic light detection should take place within tl_detector.py, whereas traffic light classification should take place within ../tl_detector/light_classification_model/tl_classfier.py.

(path_to_project_repo)/ros/src/waypoint_updater/ This package contains the waypoint updater node: waypoint_updater.py. The purpose of this node is to update the target velocity property of each waypoint based on traffic light and obstacle detection data. This node will subscribe to the /base_waypoints, /current_pose, /obstacle_waypoint, and /traffic_waypoint topics, and publish a list of waypoints ahead of the car with target velocities to the /final_waypoints topic.

(path_to_project_repo)/ros/src/twist_controller/ Carla is equipped with a drive-by-wire (dbw) system, meaning the throttle, brake, and steering have electronic control. This package contains the files that are responsible for control of the vehicle: the node dbw_node.py and the file twist_controller.py, along with a pid and lowpass filter that you can use in your implementation. The dbw_node subscribes to the /current_velocity topic along with the /twist_cmd topic to receive target linear and angular velocities. Additionally, this node will subscribe to /vehicle/dbw_enabled, which indicates if the car is under dbw or driver control. This node will publish throttle, brake, and steering commands to the /vehicle/throttle_cmd, /vehicle/brake_cmd, and /vehicle/steering_cmd topics.

Because we write code across several packages with some nodes depending on messages published by other nodes, we complete the project in the following order:

1. Waypoint Updater Node (Partial): Complete a partial waypoint updater which subscribes to /base_waypoints and /current_pose and publishes to /final_waypoints.

2. DBW Node: Once your waypoint updater is publishing /final_waypoints, the waypoint_follower node will start publishing messages to the/twist_cmd topic. At this point, you have everything needed to build the dbw_node. After completing this step, the car should drive in the simulator, ignoring the traffic lights.

3. Traffic Light Detection: This can be split into 2 parts:

   3.1 Detection: Detect the traffic light and its color from the /image_color. The topic /vehicle/traffic_lights contains the exact location and status of all traffic lights in simulator, so you can test your output.

   3.2 Waypoint publishing: Once you have correctly identified the traffic light and determined its position, you can convert it to a waypoint index and publish it.

4. Waypoint Updater (Full): Use /traffic_waypoint to change the waypoint target velocities before publishing to /final_waypoints. Your car should now stop at red traffic lights and move when they are green.

The waypoint_updater finds next waypoints from the closest waypoint based on the current position and the orientation of the vehicle. It then generates the final_waypoints with the velocity.

The dbw_node.py logic will call the Controller object with the current state information (speed, etc) to obtain throttle, brake, and steering commands if the manual mode is disabled. We implemented PID controller for generating steering and throttle commands.

For the traffic light detection we used Tensorflow's Object Detection API, which is an open source framework built on top of Tensorflow that makes it easy to construct, train and deploy object detection models. We implemented a pre-trained Faster R-CNN and retrained a model for simultion and a model for the real track as follows:

Simulator model:

1. Bosch Traffic Lights Dataset
2. Simulator images generated while driving

Real track model:

1. Bosch Traffic Lights Dataset
2. Real track images provided by the rosbag video

• Be sure that your workstation is running Ubuntu 16.04 Xenial Xerus or Ubuntu 14.04 Trusty Tahir. Ubuntu downloads can be found here.

• If using a Virtual Machine to install Ubuntu, use the following configuration as minimum:

  • 2 CPU
  • 2 GB system memory
  • 25 GB of free hard drive space

  The Udacity provided virtual machine has ROS and Dataspeed DBW already installed, so you can skip the next two steps if you are using this.

• Follow these instructions to install ROS

  • ROS Kinetic if you have Ubuntu 16.04.
  • ROS Indigo if you have Ubuntu 14.04.

• 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.

Install Docker

Build the docker container

docker build . -t capstone

Run the docker file

docker run -p 4567:4567 -v $PWD:/capstone -v /tmp/log:/root/.ros/ --rm -it capstone

1. Clone the project repository

git clone https://github.com/udacity/CarND-Capstone.git

2. Install python dependencies

cd CarND-Capstone
pip install -r requirements.txt

3. Make and run styx

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

4. Run the simulator

1. Download training bag that was recorded on the Udacity self-driving car (a bag demonstraing the correct predictions in autonomous mode can be found here)
2. Unzip the file

unzip traffic_light_bag_files.zip

3. Play the bag file

rosbag play -l traffic_light_bag_files/loop_with_traffic_light.bag

4. Launch your project in site mode

cd CarND-Capstone/ros
roslaunch launch/site.launch

5. Confirm that traffic light detection works on real life images