This is the project repo for the final project of the Udacity Self-Driving Car Nanodegree: Programming a Real Self-Driving Car. For more information about the project, see the project introduction here.
Yuan (Jack) Li (yuanli12139@gmail.com)
Peng Zhang (pengzhang40@gmail.com)
We use YOLO v2 tiny detector as our traffic light detector (https://pjreddie.com/darknet/yolov2/) for its real-time efficiency. We download the cfg file and weights pretrained on COCO dataset as our baseline.
We combine the Udacity Autonomous Driving Dataset 2 (https://github.com/udacity/self-driving-car/tree/master/annotations) and the traffic light dataset collected by https://github.com/coldKnight/TrafficLight_Detection-TensorFlowAPI, and then use sort_data.py
to convert the annotations into trainable .xml files.
Follow the instructions of darkflow (https://github.com/thtrieu/darkflow) and modify labels and config file accordingly.
./flow --model cfg/yolov2-tiny_ft.cfg --train --load bin/yolov2-tiny.weights --dataset "/mnt/data/datasets/CarND-Capstone/Data" --annotation "/mnt/data/datasets/CarND-Capstone/Annotations" --gpu 1.0 --lr 5e-4 --epoch 10 --save 1000 --trainer adam
We also trained YOLO v2 full version but it underperforms the Tiny YOLO v2. This is potentially due to overfitting with the limited training data.
Our checkpoint files can be found at
https://drive.google.com/open?id=1Z5EbbLe9BPH5O4FQWEWn41-uw8KBkoXC
https://drive.google.com/open?id=1JniOI-5w8npWoqUHZaGepMcaIGj5mbmj
Please use one of the two installation options, either native or docker installation.
-
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.
-
- Use this option to install the SDK on a workstation that already has ROS installed: One Line SDK Install (binary)
-
Download the Udacity Simulator.
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
To set up port forwarding, please refer to the instructions from term 2
- Clone the project repository
git clone https://github.com/udacity/CarND-Capstone.git
- Install python dependencies
cd CarND-Capstone
pip install -r requirements.txt
- Make and run styx
cd ros
catkin_make
source devel/setup.sh
roslaunch launch/styx.launch
- Run the simulator
- Download training bag that was recorded on the Udacity self-driving car.
- Unzip the file
unzip traffic_light_bag_file.zip
- Play the bag file
rosbag play -l traffic_light_bag_file/traffic_light_training.bag
- Launch your project in site mode
cd CarND-Capstone/ros
roslaunch launch/site.launch
- Confirm that traffic light detection works on real life images