Enhanced Transfer Learning for Autonomous Driving with Systematic Accident Simulation

Simulation data can be utilized to extend real-world driving data in order to cover edge cases, such as vehicle accidents. The importance of handling edge cases can be observed in the high societal costs in handling car accidents, as well as potential dangers to human drivers. In order to cover a wide and diverse range of all edge cases, we systemically parameterize and simulate the most common accident scenarios. By applying this data to autonomous driving models, we show that transfer learning on simulated data sets provide better generalization and collision avoidance, as compared to random initialization methods. Our results illustrate that information from a model trained on simulated data can be inferred to a model trained on real-world data, indicating the potential influence of simulation data in real world models and advancements in handling of anomalous driving scenarios.

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

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

[3]  Cewu Lu,et al.  Virtual to Real Reinforcement Learning for Autonomous Driving , 2017, BMVC.

[4]  Eric P. Xing,et al.  Unsupervised Real-to-Virtual Domain Unification for End-to-End Highway Driving , 2018, ArXiv.

[5]  Ashish Kapoor,et al.  AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles , 2017, FSR.

[6]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[7]  Kenneth Gillingham,et al.  The Effect of Fuel Economy Standards on Vehicle Weight Dispersion and Accident Fatalities , 2017 .

[8]  Alain L. Kornhauser,et al.  Beyond Grand Theft Auto V for Training, Testing and Enhancing Deep Learning in Self Driving Cars , 2017, ArXiv.

[9]  Daniel Szafir,et al.  Virtual-to-Real-World Transfer Learning for Robots on Wilderness Trails , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

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

[11]  Volkan Isler,et al.  Semantics-Aware Image to Image Translation and Domain Transfer , 2019, ArXiv.

[12]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  D. Manocha,et al.  AADS: Augmented autonomous driving simulation using data-driven algorithms , 2019, Science Robotics.

[14]  Xinming Huang,et al.  RoadNet-v2: A 10 ms Road Segmentation Using Spatial Sequence Layer , 2018, ArXiv.

[15]  Gerald Forbes,et al.  Methods and Practices for Setting Speed Limits: An Informational Report , 2012 .

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