Deep Learning Applications for Autonomous Driving

This thesis investigates the usefulness of deep learning methods for solving two important tasks in the field of driving automation: (i) Road detection, and (ii) driving path generation. Road detection was approached using two strategies: The first one considered a bird's-eye view of the driving scene obtained from LIDAR data, whereas the second carried out camera-LIDAR fusion in the camera perspective. In both cases, road detection was performed using fully convolutional neural networks (FCNs). These two approaches were evaluated on the KITTI road benchmark and achieved state-of-the-art performance, with MaxF scores of 94.07% and 96.03%, respectively. Driving path generation was accomplished with an FCN that integrated LIDAR top-views with GPS-IMU data and driving directions. This system was designed to simultaneously carry out perception and planning using as training data real driving sequences that were annotated automatically. By testing several combinations of input data, it was shown that the FCN having access to all the available sensors and the driving directions obtained the best overall accuracy with a MaxF score of 88.13%, about 4.7 percentage points better than the FCN that could use only LIDAR data.

[1]  Cristiano Premebida,et al.  Pedestrian detection combining RGB and dense LIDAR data , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  W S McCulloch,et al.  A logical calculus of the ideas immanent in nervous activity , 1990, The Philosophy of Artificial Intelligence.

[3]  Tammy E. Trimble,et al.  Automated Vehicle Crash Rate Comparison Using Naturalistic Data , 2016 .

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

[5]  Ankit Laddha,et al.  Map-supervised road detection , 2016, 2016 IEEE Intelligent Vehicles Symposium (IV).

[6]  Jian Yang,et al.  Lidar-histogram for fast road and obstacle detection , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[7]  Zhe Chen,et al.  RBNet: A Deep Neural Network for Unified Road and Road Boundary Detection , 2017, ICONIP.

[8]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[9]  J R Treat,et al.  TRI-LEVEL STUDY OF THE CAUSES OF TRAFFIC ACCIDENTS: FINAL REPORT , 1979 .

[10]  K. Mcmahon.  THE TRUE COST OF ROAD CRASHES , 2008 .

[11]  Zhidong Deng,et al.  Drivable Road Detection Based on Dilated FPN with Feature Aggregation , 2017, 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI).

[12]  Jannik Fritsch,et al.  A new performance measure and evaluation benchmark for road detection algorithms , 2013, 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013).

[13]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[14]  Wolfram Burgard,et al.  Efficient deep models for monocular road segmentation , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[15]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[16]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[17]  Ethan Fetaya,et al.  Real-Time Category-Based and General Obstacle Detection for Autonomous Driving , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[18]  Rahul Mohan,et al.  Deep Deconvolutional Networks for Scene Parsing , 2014, ArXiv.

[19]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling , 2015, CVPR 2015.

[20]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[21]  Andreas Geiger,et al.  Vision meets robotics: The KITTI dataset , 2013, Int. J. Robotics Res..

[22]  P. Lennie.  Receptive fields , 2003, Current Biology.