AIBA: An AI Model for Behavior Arbitration in Autonomous Driving
Driving in dynamically changing traffic is a highly challenging task for autonomous vehicles, especially in crowded urban roadways. The Artificial Intelligence (AI) system of a driverless car must be able to arbitrate between different driving strategies in order to properly plan the car’s path, based on an understandable traffic scene model. In this paper, an AI behavior arbitration algorithm for Autonomous Driving (AD) is proposed. The method, coined AIBA (AI Behavior Arbitration), has been developed in two stages: (i) human driving scene description and understanding and (ii) formal modelling. The description of the scene is achieved by mimicking a human cognition model, while the modelling part is based on a formal representation which approximates the human driver understanding process. The advantage of the formal representation is that the functional safety of the system can be analytically inferred. The performance of the algorithm has been evaluated in Virtual Test Drive (VTD), a comprehensive traffic simulator, and in GridSim, a vehicle kinematics engine for prototypes.
KeywordsBehavior arbitration Context understanding Autonomous driving Self-driving vehicles Artificial intelligence
We hereby acknowledge Elektrobit Automotive, Széchenyi István University, and the TAMOP - 4.2.2.C-11/1/KONV-2012-0012 Project “Smarter Transport - IT for co-operative transport system” for providing the infrastructure and for support during research.
- 2.Shalev-Shwartz, S., Shammah, S., Shashua, A.: On a formal model of safe and scalable self-driving cars (2017). arXiv preprint arXiv:1708.06374
- 3.Litman, T.: Autonomous vehicle implementation predictions. Victoria Transport Policy Institute, Victoria, Canada, p. 28 (2017)Google Scholar
- 4.Janai, J., Güney, F., Behl, A., Geiger, A.: Computer vision for autonomous vehicles: problems, datasets and state-of-the-art (2017). arXiv preprint arXiv:1704.05519
- 6.Janai, J., Guney, F., Behl, A., Geiger, A.: Computer vision for autonomous vehicles: Problems, datasets and state-of-the-art (2017). arXiv preprint arXiv:1704.05519
- 9.Lefevre, S., Gao, Y., Vasquez, D., Tseng, H.E., Bajcsy, R., Borrelli, F.: Lane keeping assistance with learning-based driver model and model predictive control. In: Proceedings of the 12th ISAVC, Tokyo, Japan (2014)Google Scholar
- 11.Pozna, C., Troester, F.: Human behavior model based control program for ACC mobile robot. Acta Polytechnica Hungarica 3(3), 59–70 (2006)Google Scholar
- 12.Pozna, C., Precup, R.E., Minculete, N., Antonya, C., Dragos, C.A.: Properties of classes, subclasses and objects in an abstraction model. In: 19th International Workshop on Robotics in Alpe-Adria-Danube Region, pp. 291–296 (2010)Google Scholar
- 15.Bojarski, M., et al.: End to end learning for self-driving cars. CoRR, vol. abs/1604.07316 (2016)Google Scholar
- 16.Grigorescu, S.: Generative one-shot learning (GOL): a semi-parametric approach for one-shot learning in autonomous vision. In: International Conference on Robotics and Automation ICRA 2018, 21–25 May 2018, Brisbane, Australia (2018)Google Scholar
- 17.Trasnea, B., Marina, L.A., Vasilcoi, A., Pozna, C., Grigorescu, S.: GridSim: a vehicle kinematics engine for deep neuroevolutionary control in autonomous driving. In: 3rd IEEE International Conference on Robotic Computing (IRC), pp. 443–444 (2019)Google Scholar
- 18.Marina, L.A., Trasnea, B., Cocias, T., Vasilcoi, A., Moldoveanu, F., Grigorescu, S.: Deep grid net (DGN): a deep learning system for real-time driving context understanding. In: 3rd IEEE International Conference on Robotic Computing (IRC), pp. 399–402 (2019)Google Scholar