Behavioral Cloning

Self-driving cars faces numerous situations when drove on the road. Its essential that the car is trained on a real scenario with good driving behaviour. This will prepare the self-driving car to act correctly, independent of any instructions from a driver.

List of files in Repository:

1. model.py is the python script to create and train the model
2. drive.py is the python script for driving the car in autonomous mode on udacity simulator
3. video.py is the python script for creating the video out of images from the simulator.
4. model.h5 is the trained Keras model
5. video.mp4 is the video file output generated by running the car in simulator in autonomous mode.
6. writeup_report.md is the markdown for summarizing the methodology and results
7. Other Folders and files contains resources for the writeup.

This lab requires:

• Udacity Simulator for creating the training data and simulating the trained model
• CarND Term1 Starter Kit

Employed Neural Network Architecture, Training Data Set, and Methodology involved in training is thoroughly discussed in the writeup_report.md file.

Usage of model.py requires you have python with the pre-requisites from CarND Term1 Starter Kit and data extracted through run in udacity simulator.

To train the model with your data, make sure to place the images in IMG folder and the driving_log.csv file in the root directory of this project. Use the below command to train the model with your data.

python model.py

This will save the model as model.h5

Usage of drive.py requires you have saved the trained model as an h5 file, i.e. model.h5. Once the model has been saved, it can be used with drive.py using this command:

python drive.py model.h5

The above command will load the trained model and use the model to make predictions on individual images in real-time and send the predicted angle back to the server via a websocket connection.

Note: There is known local system's setting issue with replacing "," with "." when using drive.py. When this happens it can make predicted steering values clipped to max/min values. If this occurs, a known fix for this is to add "export LANG=en_US.utf8" to the bashrc file.

python drive.py model.h5 run1

The fourth argument, run1, is the directory in which to save the images seen by the agent. If the directory already exists, it'll be overwritten.

ls run1

[2017-01-09 16:10:23 EST]  12KiB 2017_01_09_21_10_23_424.jpg
[2017-01-09 16:10:23 EST]  12KiB 2017_01_09_21_10_23_451.jpg
[2017-01-09 16:10:23 EST]  12KiB 2017_01_09_21_10_23_477.jpg
[2017-01-09 16:10:23 EST]  12KiB 2017_01_09_21_10_23_528.jpg
[2017-01-09 16:10:23 EST]  12KiB 2017_01_09_21_10_23_573.jpg
[2017-01-09 16:10:23 EST]  12KiB 2017_01_09_21_10_23_618.jpg
[2017-01-09 16:10:23 EST]  12KiB 2017_01_09_21_10_23_697.jpg
[2017-01-09 16:10:23 EST]  12KiB 2017_01_09_21_10_23_723.jpg
[2017-01-09 16:10:23 EST]  12KiB 2017_01_09_21_10_23_749.jpg
[2017-01-09 16:10:23 EST]  12KiB 2017_01_09_21_10_23_817.jpg
...

The image file name is a timestamp of when the image was seen. This information is used by video.py to create a chronological video of the agent driving.

python video.py run1

Creates a video based on images found in the run1 directory. The name of the video will be the name of the directory followed by '.mp4', so, in this case the video will be run1.mp4.

Optionally, one can specify the FPS (frames per second) of the video:

python video.py run1 --fps 48

Will run the video at 48 FPS. The default FPS is 60.