Abstract
The Mexican Robotics Tournament “Torneo Mexicano de Robotica (MRT)” holds an international tournament of autonomous driving with open source/hardware vehicles with a scale of 1:10, said vehicles must complete several by their self, using several machine learning algorithms. With the purpose of improving the results in the autonomous car contest a novel driving simulation platform was developed. For this, the Udacity driving simulator which is built in Unity software was used. First, a virtual track was elaborated according to the measures established by the MRT specifications, then, a 1:1 replica of the MRT-vehicle was used to simulate the collection of 420 images, then, in order to validate the proposal, a neural network was developed to classify the images captured by the virtual camera placed in the vehicle of the simulation platform. These images were classified into three categories according to the actions of the vehicle must perform (turn left, right and move forward). The results were satisfactory, obtaining 79% of accuracy and a recall value of 0.93, offering a standalone platform for the training of the vehicle.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Negrete, M., Morales, A., Sossa, H., Castelán, M., Morales, M.: Reglamento del Torneo Mexicano de Robótica 2019. Rulebook presented at the Mexican Robotics Tournament 2019 - Categoría: AutoModelCar, CDMX, México (2019). https://www.femexrobotica.org/tmr2019/wp-content/uploads/2019/03/AutoModelCarRulebook.pdf
Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A. Koltun, V.: CARLA: an open urban driving simulator. In: Proceedings of the 1st Annual Conference on Robot Learning, in PMLR, vol. 78, pp. 1–16 (2017). http://proceedings.mlr.press/v78/dosovitskiy17a/dosovitskiy17a.pdf
Wymann, B., Espi´e, E., Guionneau, C., Dimitrakakis, C., Coulom, R., Sumner, A.: TORCS, the open racing car simulator, v1.3.5 (2013). http://www.torcs.org
Pomerleau, D.: Alvinn, an autonomous land vehicle in a neural network. Technical report, Carnegie Mellon University, Computer Science Department (1989). https://papers.nips.cc/paper/95-alvinn-an-autonomous-land-vehicle-in-a-neural-network.pdf
Bojarski, M., et al.: End to end learning for self-driving cars. Cornell University (2016). https://arxiv.org/pdf/1604.07316.pdf
Chen, C., Seff, A., Kornhauser, A., Xiao, J.: DeepDriving: learning affordance for direct perception in autonomous driving. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 2722–2730 (2015). https://doi.org/10.1109/iccv.2015.312
Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the kitti dataset. Int. J. Robot. Res. (2013). http://www.cvlibs.net/datasets/kitti/
Sallab, A., Abdou, M., Perot, E., Yogamani, S.: Deep reinforcement learning framework for autonomous driving. Electron. Imaging 2017(19), 70–76 (2017). https://doi.org/10.2352/issn.2470-1173.2017.19.avm-023
Qué son las redes neuronales y sus funciones. (2019). https://www.atriainnovation.com/que-son-las-redes-neuronales-y-sus-funciones/. Accessed 10 June 2020
7 Types of Activation Functions in Neural Networks: How to Choose? (2020). MissingLink.Ai. https://missinglink.ai/guides/neural-network-concepts/7-types-neural-network-activation-functions-right/
Narkhede, S.: Understanding confusion matrix. Towards Data Science (2019). https://towardsdatascience.com/understanding-confusion-matrix-a9ad42dcfd62
Ghoneim, S.: Accuracy, recall, precision, f-score & specificity, which to optimize on? Towards data science (2019). https://towardsdatascience.com/accuracy-recall-precision-f-score-specificity-which-to-optimize-on-867d3f11124
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
de la Torre, M.I.O., Luna-García, H., Celaya-Padilla, J.M., Gamboa-Rosales, H., Sarmiento, W.J., Collazos, C.A. (2020). Autonomous Driving: Obtaining Direction Commands by Classifying Images Within a Simulation Platform. In: Agredo-Delgado, V., Ruiz, P.H., Villalba-Condori, K.O. (eds) Human-Computer Interaction. HCI-COLLAB 2020. Communications in Computer and Information Science, vol 1334. Springer, Cham. https://doi.org/10.1007/978-3-030-66919-5_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-66919-5_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-66918-8
Online ISBN: 978-3-030-66919-5
eBook Packages: Computer ScienceComputer Science (R0)