Oleg Zabluda's blog
Tuesday, January 17, 2017
 
"""
"""
Modern video-games like GTAV, present a world where you can test self-driving car AI’s in large complex urban areas replete with realistic roads, weather, pedestrians, cyclists, and vehicles with zero risk or cost. [...] you can quickly run the car through a barrage of safety critical situations, some of which may only occur every several million miles in reality.
[...]
An initial 8-layer neural net with the AlexNet architecture is being made available as well as the dataset it was trained on. Training was done on raw image input from a forward mounted camera regressed against steering, throttle, yaw, and forward-speed control values produced by an in-game AI. This model is able to steer the car to stay in the lane, stop for other cars, and works well in a variety of weather and lighting conditions
[...]
Tips and Tricks

Adding examples of course correction to the training data is crucial. NVIDIA does this by simulating rotation of real-world images, and ALVINN created its own simulation for adding variety to its training. Since we are already in simulation, course correction can be added by stopping recording, steering the car off course, and recording actions and images taken during course correction. This was done at three levels of severity. Levels one and two consisted of driving the car with a previous model for one and two seconds respectively, then recording corrective actions taken by the in-game AI. The most severe level consisted of performing a random action (hard right, hard left, brake, or strong accelerate) and relinquishing control to the in-game AI after 230ms.
[...]
Predicting steering, speed, etc.. ahead-of-time works by adding future targets to the last fully connected layer, but causes more overfitting (e.g. 2x worst test performance with 3 frames, or 775ms, of advance data). So if you predict the future, it's probably a good idea to add more regularization.

Seminal prior work
1988 - ALVINN
2005 - DAVE
2015 - DeepDriving [1]
2016 - NVIDIA DriveNet
"""
http://deepdrive.io/

[1] DeepDriving
https://plus.google.com/+OlegZabluda/posts/8yuuBLmJ4jw
http://deepdrive.io

Labels:


| |

Home

Powered by Blogger