A Large-Scale Mapping Method Based on Deep Neural Networks Applied to Self-Driving Car Localization

We propose a new approach for real time inference of occupancy maps for self-driving cars using deep neural networks (DNN) named NeuralMapper. NeuralMapper receives LiDAR sensor data as input and generates as output the occupancy grid map around the car. NeuralMapper infers the probability of each grid map cell from one of the three following classes: Occupied, Free and Unknown. The system was tested with two datasets and achieved an average accuracy of 76.48% and 73.81%. We also evaluated our approach for localization purposes in a self-driving car and most of the localization pose errors were less than 0.20m with an RMSE of 0.28 which are close to the results in the literature for methods using other grid mapping approaches.

[1]  Patrice Y. Simard,et al.  Best practices for convolutional neural networks applied to visual document analysis , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[2]  Nicu Sebe,et al.  Effortless Deep Training for Traffic Sign Detection Using Templates and Arbitrary Natural Images , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[3]  Alberto Ferreira de Souza,et al.  A Model-Predictive Motion Planner for the IARA autonomous car , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[4]  Alberto Ferreira de Souza,et al.  Handling pedestrians in self-driving cars using image tracking and alternative path generation with Frenét frames , 2019, Comput. Graph..

[5]  Alberto Ferreira de Souza,et al.  Self-Driving Cars: A Survey , 2019, Expert Syst. Appl..

[6]  Eren Erdal Aksoy,et al.  SalsaNet: Fast Road and Vehicle Segmentation in LiDAR Point Clouds for Autonomous Driving , 2020, 2020 IEEE Intelligent Vehicles Symposium (IV).

[7]  Lennart Svensson,et al.  Fast LIDAR-based road detection using fully convolutional neural networks , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

[8]  Edilson de Aguiar,et al.  A light-weight yet accurate localization system for autonomous cars in large-scale and complex environments , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).

[9]  Andreas Geiger,et al.  Are we ready for autonomous driving? The KITTI vision benchmark suite , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Alberto Ferreira de Souza,et al.  Prior Map Frame Deep Detector NONE OFF RED GREEN Frame PredictionDetections Expected Locations Selection , 2019 .

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

[12]  Sebastian Thrun,et al.  Robust vehicle localization in urban environments using probabilistic maps , 2010, 2010 IEEE International Conference on Robotics and Automation.

[13]  Francisco Vaz,et al.  Perception maps for the local navigation of a mobile robot: a neural network approach , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[14]  Luis Perez,et al.  The Effectiveness of Data Augmentation in Image Classification using Deep Learning , 2017, ArXiv.

[15]  Edilson de Aguiar,et al.  Large-scale mapping in complex field scenarios using an autonomous car , 2016, Expert Syst. Appl..

[16]  Alberto Ferreira de Souza,et al.  Neural-based model predictive control for tackling steering delays of autonomous cars , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[17]  Ryan M. Eustice,et al.  Robust LIDAR localization using multiresolution Gaussian mixture maps for autonomous driving , 2017, Int. J. Robotics Res..

[18]  Paul Newman,et al.  Probably Unknown: Deep Inverse Sensor Modelling Radar , 2018, 2019 International Conference on Robotics and Automation (ICRA).

[19]  Roberto Cipolla,et al.  MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving , 2016, 2018 IEEE Intelligent Vehicles Symposium (IV).

[20]  Varun Gupta,et al.  Occupancy grid mapping using artificial neural networks , 2010, 2010 International Conference on Industrial Electronics, Control and Robotics.

[21]  Kurt Keutzer,et al.  SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[22]  Alberto Ferreira de Souza,et al.  A simple yet effective obstacle avoider for the IARA autonomous car , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).