End-to-End Driving Via Conditional Imitation Learning

Citations Over TimeTop 1% of 2018 papers

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

Related Papers

• → ALVINN, an autonomous land vehicle in a neural network(2018)1,428 cited
• → End-to-End Learning of Driving Models from Large-Scale Video Datasets(2017)859 cited
• Off-Road Obstacle Avoidance through End-to-End Learning(2005)
• → End to End Learning for Self-Driving Cars(2016)3,101 cited
• → A Reduction of Imitation Learning and Structured Prediction to No-Regret\n Online Learning(2010)1,309 cited