End-to-end Driving via Conditional Imitation Learning

TL;DR

This paper introduces a conditional imitation learning approach enabling end-to-end autonomous driving systems to follow high-level navigational commands, improving control and flexibility in urban and robotic driving scenarios.

Contribution

It proposes a novel conditional imitation learning framework that allows end-to-end driving models to incorporate high-level commands, enhancing controllability during testing.

Findings

Effective in urban simulation environments

Successful deployment on a 1/5 scale robotic truck

Maintains responsiveness to navigational commands

Abstract

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 https://youtu.be/cFtnflNe5fM