Learning to Drive from Simulation without Real World Labels

Simulation can be a powerful tool for under-standing machine learning systems and designing methods to solve real-world problems. Training and evaluating methods purely in simulation is often “doomed to succeed” at the desired task in a simulated environment, but the resulting models are incapable of operation in the real world. Here we present and evaluate a method for transferring a vision-based lane following driving policy from simulation to operation on a rural road without any real-world labels. Our approach leverages recent advances in image-to-image translation to achieve domain transfer while jointly learning a single-camera control policy from simulation control labels. We assess the driving performance of this method using both open-loop regression metrics, and closed-loop performance operating an autonomous vehicle on rural and urban roads.

[1]  Antonio M. López,et al.  The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Robert Bridson,et al.  Fast Poisson disk sampling in arbitrary dimensions , 2007, SIGGRAPH '07.

[3]  Rongrong Chen,et al.  Playing Action Video Games Improves Visuomotor Control , 2016, Psychological science.

[4]  Dean Pomerleau,et al.  ALVINN, an autonomous land vehicle in a neural network , 2015 .

[5]  R. Mazo.  On the theory of brownian motion , 1973 .

[6]  Vladlen Koltun,et al.  Playing for Benchmarks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[7]  Yann LeCun,et al.  Off-Road Obstacle Avoidance through End-to-End Learning , 2005, NIPS.

[8]  Qiao Wang,et al.  VirtualWorlds as Proxy for Multi-object Tracking Analysis , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Germán Ros,et al.  CARLA: An Open Urban Driving Simulator , 2017, CoRL.

[10]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[11]  Daniel Cremers,et al.  Modular Vehicle Control for Transferring Semantic Information to Unseen Weather Conditions using GANs , 2018, CoRL.

[12]  Andrea Vedaldi,et al.  Improved Texture Networks: Maximizing Quality and Diversity in Feed-Forward Stylization and Texture Synthesis , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Alex Bewley,et al.  Incremental Adversarial Domain Adaptation for Continually Changing Environments , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[14]  Wolfram Burgard,et al.  VR-Goggles for Robots: Real-to-Sim Domain Adaptation for Visual Control , 2018, IEEE Robotics and Automation Letters.

[15]  Vladlen Koltun,et al.  Playing for Data: Ground Truth from Computer Games , 2016, ECCV.

[16]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[17]  Jan Kautz,et al.  Unsupervised Image-to-Image Translation Networks , 2017, NIPS.

[18]  Zhang-Wei Hong,et al.  Virtual-to-Real: Learning to Control in Visual Semantic Segmentation , 2018, IJCAI.

[19]  Ming-Yu Liu,et al.  Coupled Generative Adversarial Networks , 2016, NIPS.

[20]  Ken Perlin,et al.  Improving noise , 2002, SIGGRAPH.

[21]  Taesung Park,et al.  CyCADA: Cycle-Consistent Adversarial Domain Adaptation , 2017, ICML.

[22]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Jan Kautz,et al.  Video-to-Video Synthesis , 2018, NeurIPS.

[24]  Alex Bewley,et al.  Addressing appearance change in outdoor robotics with adversarial domain adaptation , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[25]  Andrea Vedaldi,et al.  Neural Stethoscopes: Unifying Analytic, Auxiliary and Adversarial Network Probing , 2018, ArXiv.

[26]  Vladlen Koltun,et al.  On Offline Evaluation of Vision-based Driving Models , 2018, ECCV.

[27]  Xin Zhang,et al.  End to End Learning for Self-Driving Cars , 2016, ArXiv.

[28]  Alexey Dosovitskiy,et al.  End-to-End Driving Via Conditional Imitation Learning , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[29]  Wojciech Zaremba,et al.  Domain randomization for transferring deep neural networks from simulation to the real world , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[30]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[31]  Bernard Ghanem,et al.  Driving Policy Transfer via Modularity and Abstraction , 2018, CoRL.

[32]  Sergey Levine,et al.  Adapting Deep Visuomotor Representations with Weak Pairwise Constraints , 2015, WAFR.

[33]  Ashish Mehta,et al.  Learning End-to-end Autonomous Driving using Guided Auxiliary Supervision , 2018, ICVGIP.

[34]  Jan Kautz,et al.  Multimodal Unsupervised Image-to-Image Translation , 2018, ECCV.

[35]  Andrea Vedaldi,et al.  Semi-convolutional Operators for Instance Segmentation , 2018, ECCV.

[36]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[37]  David Janz,et al.  Learning to Drive in a Day , 2018, 2019 International Conference on Robotics and Automation (ICRA).