End-to-End Driving Via Conditional Imitation Learning
Top Cited Papers
- 1 May 2018
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
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.Keywords
This publication has 12 references indexed in Scilit:
- Autonomous DrivingPublished by Wiley ,2017
- A Survey of Motion Planning and Control Techniques for Self-Driving Urban VehiclesIEEE Transactions on Intelligent Vehicles, 2016
- A Machine Learning Approach to Visual Perception of Forest Trails for Mobile RobotsIEEE Robotics and Automation Letters, 2015
- Reinforcement learning in robotics: A surveyThe International Journal of Robotics Research, 2013
- Reinforcement learning to adjust parametrized motor primitives to new situationsAutonomous Robots, 2012
- Robot learning from demonstration by constructing skill treesThe International Journal of Robotics Research, 2011
- Autonomous Helicopter Aerobatics through Apprenticeship LearningThe International Journal of Robotics Research, 2010
- Learning from Demonstration for Autonomous Navigation in Complex Unstructured TerrainThe International Journal of Robotics Research, 2010
- A survey of robot learning from demonstrationRobotics and Autonomous Systems, 2009
- Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learningArtificial Intelligence, 1999