Authors:
Stephan Pareigis
and
Fynn Luca Maaß
Affiliation:
Department of Computer Science, HAW Hamburg, Berliner Tor 7, 20099 Hamburg, Germany
Keyword(s):
Sim-to-Real Gap, End-to-End Learning, Autonomous Driving, Artificial Neural Network, CARLA Simulator, Robust Control, PilotNet.
Abstract:
A neural network architecture for end-to-end autonomous driving is presented, which is robust against discrepancies in system dynamics during the training process and in application. The proposed network architecture
presents a first step to alleviate the simulation to reality gap with respect to differences in system dynamics.
A vehicle is trained to drive inside a given lane in the CARLA simulator. The data is used to train NVIDIA’s
PilotNet. When an offset is given to the steering angle of the vehicle while the trained network is being applied, PilotNet will not keep the vehicle inside the lane as expected. A new architecture is proposed called
PilotNet∆, which is robust against steering angle offsets. Experiments in the simulator show that the vehicle
will stay in the lane, although the steering properties of the vehicle differ