%0 Conference Proceedings
%T End-to-end Driving via Conditional Imitation Learning
%A Felipe Codevilla
%A Matthias Muller
%A Antonio Lopez
%A Vladlen Koltun
%A Alexey Dosovitskiy
%B IEEE International Conference on Robotics and Automation
%D 2018
%F Felipe Codevilla2018
%O ADAS; 600.116; 600.124; 600.118
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3108), last updated on Mon, 24 Jan 2022 12:31:53 +0100
%X Deep networks trained on demonstrations of human driving have learned to follow roads and avoid obstacles. However, driving policies trained via imitation learning cannot be controlled at test time. A vehicle trained end-to-end to imitate an expert cannot be guided to take a specific turn at an upcoming intersection. This limits the utility of such systems. We propose to condition imitation learning on high-level command input. At test time, the learned driving policy functions as a chauffeur that handles sensorimotor coordination but continues to respond to navigational commands. We evaluate different architectures for conditional imitation learning in vision-based driving. We conduct experiments in realistic three-dimensional simulations of urban driving and on a 1/5 scale robotic truck that is trained to drive in a residential area. Both systems drive based on visual input yet remain responsive to high-level navigational commands. The supplementary video can be viewed at this https URL
%U http://refbase.cvc.uab.es/files/CML2018.pdf
%U http://dx.doi.org/10.1109/ICRA.2018.8460487
%P 4693-4700