Abstract
Explainable outcomes in autonomous navigation have become crucial for drivers, other vehicles, as well as for pedestrians. Creating trustworthy strategies is mandatory for the integration of self-driving cars into quotidian environments. This paper presents the successful implementation of an explainable Fuzzy Deep Reinforcement Learning approach for autonomous vehicles based on the AWS DeepRacer\(^{\mathrm{TM}}\) platform. A model of the environment is created by transforming crisp values into linguistic variables. A fuzzy inference system is used to define the reward of the vehicle depending on its current state. Guidelines to define the actions and to improve performance of the reinforcement learning agent are given based on the characteristics of the existing hardware. The performance of the models is tested on tracks with distinctive properties using agents with different policies and action spaces, and shows explainable and successful navigation of the agent on diverse scenarios.
Graphic Abstract
Similar content being viewed by others
Abbreviations
- AWS:
-
Amazon Web Services
- AI:
-
Artificial intelligence
- XAI:
-
Explainable artificial intelligence
- FIS:
-
Fuzzy inference system
- MF:
-
Membership function
- ML:
-
Machine learning
- DL:
-
Deep learning
- DNN:
-
Deep neural network
- DNN:
-
Convolutional neural network
- RL:
-
Reinforcement learning
References
Montemerlo, M., Thrun, S., Dahlkamp, H., Stavens, D., Strohband, S.: Winning the DARPA grand challenge with an AI robot. In: Proceedings of the AAAI National Conference on Artificial Intelligence, Boston, MA. AAAI (2006)
SAE International J3016. https://www.sae.org/standards/content/j3016_201401/. Accessed 12 Apr 2020
Urmson, C., et al.: Tartan Racing: A Multi-Modal Approach to the DARPA Urban Challenge. DARPA, Arlington County (2007)
Veres, S., Molnar, L., Lincoln, N., Morice, P.: Autonomous vehicle control systems: a review of decision making. Proc. Inst. Mech. Eng. I J. Syst. Control Eng. 225(2), 155–195 (2011)
Althoff, M., Lösch, R.: Can automated road vehicles harmonize with traffic flow while guaranteeing a safe distance?. In: Proceedings of IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), pp. 485–491 (2016)
Vagg, C., Brace, C.J., Hari, D., Akehurst, S., Poxon, J., Ash, L.: Development and field trial of a driver assistance system to encourage eco-driving in light commercial vehicle fleets. IEEE Trans. Intell. Transp. Syst. 14(2), 796–805 (2013)
Andersen, H., et al.: Trajectory optimization for autonomous overtaking with visibility maximization. In: Proceedings of IEEE International Conference on Intelligent Transportation Systems (ITSC), pp. 1–8 (2017)
Zhang, K., Yang, A., Su, H., de La Fortelle, A., Miao, K., Yao, Y.: Service-oriented cooperation models and mechanisms for heterogeneous driverless vehicles at continuous static critical sections. IEEE Trans. Intell. Transp. Syst. 18(7), 1867–1881 (2016)
Menéndez-Romero, C., Sezer, M., Winkler, F., Dornhege, C., Burgard, W.: Courtesy behavior for highly automated vehicles on highway interchanges. In: Proceedings of the IEEE Intelligent Vehicles Symposium (IV), pp. 943–948 (2018)
Li, L., Wen, D., Yao, Y.: A survey of traffic control with vehicular communications. IEEE Trans. Intell. Transp. Syst 15(1), 425–432 (2014)
Morignot, P., Rastelli, J.P., Nashashibi, F.: Arbitration for balancing control between the driver and ADAS systems in an automated vehicle: survey and approach. In: Proceedings of the IEEE Intelligent Vehicles Symposium (IV), pp. 575–580 (2014)
Broggi, A., Debattisti, S., Panciroli, M., Porta, P.: Moving from analog to digital driving. In: Proceedings of the IEEE Intelligent Vehicles Symposium (IV), pp. 1113–1118 (2013)
Althoff, M., Koschi, M., Manzinger, S. CommonRoad: composable benchmarks for motion planning on roads. In: Proceedings of the IEEE Intelligent Vehicles Symposium (IV), pp. 719–726 (2017)
Morignot, P., Nashashibi, F.: An ontology-based approach to relax traffic regulation for autonomous vehicle assistance. In: Proceedings of IASTED International Conference on Artificial Intelligence and Applications, pp. 10–17 (2013)
Du, N., Zhou, F., Pulver, E., Tilbury, D., Robert, L., Pradhan, A., Yang, X.: Examining the effects of emotional valence and arousal on takeover performance in conditionally automated driving. Transp. Res. C Emerg. Technol. 112, 78–87 (2020)
Jayaraman, S., Chandler, C., Tilbury, D., Yang, X., Pradhan, A., Tsui, K., Robert, L.: Pedestrian trust in automated vehicles: role of traffic signal and AV driving behavior. Front. Robot. AI 6(117) (2019)
Vasiljević, G., Miklić, D., Draganjac, I., Kovačić, Z., Lista, P.: High-accuracy vehicle localization for autonomous warehousing. Robot. Comput. Integr. Manuf. 42, 1–16 (2016)
Schneemann, F., Gohl, I.: Analyzing driver-pedestrian interaction at crosswalks: a contribution to autonomous driving in urban environments. In: IEEE Intelligent Vehicles Symposium (IV), Gothenburg, pp. 38–43 (2016)
Claussmann, L., Revilloud, M., Glaser, S., Gruyer, D.: A study on al-based approaches for high-level decision making in highway autonomous driving. In: Proceedings of IEEE International Conference on Systems, Man and Cybernetics (SMC), pp. 3671–3676 (2017)
Claussmann, L., Revilloud, M., Gruyer, D., Glaser, S.: A review of motion planning for highway autonomous driving. IEEE Trans. Intell. Transp. Syst. 21(5), 1826–1848 (2019)
Balal, E., Cheu, R.L., Sarkodie-Gyan, T.: A binary decision model for discretionary lane changing move based on fuzzy inference system. Transp. Res. C Emerg. Technol. 67, 47–61 (2016)
Lefévre, S., Carvalho, A., Borrelli, F.: A learning-based framework for velocity control in autonomous driving. IEEE Trans. Autom. Sci. Eng. 13(1), 32–42 (2016)
Li, N., Oyler, D.W., Zhang, M., Yildiz, Y., Kolmanovsky, I., Girard, R.: Game theoretic modeling of driver and vehicle interactions for verification and validation of autonomous vehicle control systems. IEEE Trans. Control Syst. Technol. 26(5), 1782–1797 (2018)
Huy, Q., Mita, S., Nejad, H.T.N., Han, L.: Dynamic and safe path planning based on support vector machine among multi moving obstacles for autonomous vehicles. IEICE Trans. Inf. Syst. E96–D(2), 314–328 (2013)
Lefévre, S., Vasquez, D., Laugier, C.: A survey on motion prediction and risk assessment for intelligent vehicles. ROBOMECH J. 1(1), 1–14 (2014)
Constantin, A. Park, J., Iagnemma, K.: A margin-based approach to threat assessment for autonomous highway navigation. In: Proceedings of the IEEE Intelligent Vehicles Symposium (IV), pp. 234–239 (2014)
Ardelt, M., Waldmann, P., Homm, F., Kaempchen, N.: Strategic decision-making process in advanced driver assistance systems. IFAC Proc. Vol. 43(7), 566–571 (2010)
Chen, C., Seff, A., Kornhauser, A., Xiao, J.: DeepDriving: learning affordance for direct perception in autonomous driving. In: Proceedings of IEEE International Conference on Computer Vision, pp. 2722–2730 (2015)
Yang, L., Liang, X., Wang, T., Xing, E.: Real-to-virtual domain unification for end-to-end autonomous driving. In: Proceedings of European Conference on Computer Vision (ECCV), pp. 530–545 (2018)
Bojarski, M., Del Testa, D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., Jackel, L., Monfort, M., Muller, U., Zhang, J., Zhang, X., Zhao, J., Zieba, K.: End to End Learning for Self-Driving Cars (2016)
Chen, W., Qu, T., Zhou, Y., Weng, K., Wang, G., Fu, G.: Door recognition and deep learning algorithm for visual based robot navigation. In: IEEE International Conference on Robotics and Biomimetics (ROBIO 2014), Bali, pp. 1793–1798 (2014)
Zhu, Y., et al.: Target-driven visual navigation in indoor scenes using deep reinforcement learning. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), Singapore, pp. 3357–3364 (2017)
Richter, C., Nicholas, R.: Safe Visual Navigation Via Deep Learning and Novelty Detection. Robotics: Science and Systems XIII (2017). https://doi.org/10.15607/RSS.2017.XIII.064
Kaufmann, E., Loquercio, A., Ranftl, R., Dosovitskiy, A., Koltun, V., Scaramuzza, D.: Deep Drone Racing: Learning Agile Flight in Dynamic Environments, Conference on Robot Learning. (CORL), Zurich (2018)
Jung, S., Hwang, S., Shin, H., Shim, D.H.: Perception, guidance, and navigation for indoor autonomous drone racing using deep learning. IEEE Robot. Autom. Lett. 3(3), 2539–2544 (2018)
Shou, Z., Di, X.: Reward Design for Driver Repositioning Using Multi-Agent Reinforcement Learning Sci Dir. 119, (2020). https://doi.org/10.1016/j.trc.2020.102738
Samek, W., Müller, K.: Towards Explainable Artificial Intelligence, Explainable AI: Interpreting. Explaining and Visualizing Deep Learning. Springer, Berlin (2019)
Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. In: Advances in Neural Information Processing Systems (NIPS). pp. 1135–1143 (2015)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks (2018)
Samek, W., Wiegand, T., Müller, K.R.: Explainable artificial intelligence: understanding, visualizing and interpreting deep learning models. ITU J. ICT Discov. 1(1), 39–48 (2018)
Kim, B., Wattenberg, M., Gilmer, J., Cai, C., Wexler, J., Viegas, F., Sayres, R.: Interpretability beyond feature attribution: quantitative testing with concept activation vectors (TCAV). In: International Conference on Machine Learning (ICML), pp. 2673–2682 (2018)
Montavon, G., Samek, W., Müller, K.: Methods for interpreting and understanding deep neural networks. Digit. Signal Process. 73, 1–15 (2018)
Lapuschkin, S., Wäldchen, S., Binder, A., Montavon, G., Samek, W., Müller, K.: Unmasking clever hans predictors and assessing what machines really learn. Nat. Commun. 10, 1096 (2019)
Koh, P., Liang, P.: Understanding black-box predictions via influence functions. In: International Conference on Machine Learning (ICML), pp. 1885–1894 (2017)
Adadi, A., Berrada, M.: Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6, 52138–52160 (2018)
Haspiel, J., Du, N., Meyerson, J., Robert, L., Tilbury, D., Yang, X., Pradhan, A.: Explanations and Expectations: Trust Building in Automated Vehicles, pp. 119–120 (2018)
Holzinger, A., Biemann, C., Pattichis, C., Kell, D.: What do we need to build explainable AI systems for the medical domain? Explainable AI for the Medical Domain (2017)
Amarasinghe, K., Kenney, K., Manic, M.: Toward explainable deep neural network based anomaly detection. In: 11th International Conference on Human System Interaction (HSI), Gdansk, pp. 311–317 (2018)
Fernandez, A., Herrera, F., Cordon, O., Jose del Jesus, M., Marcelloni, F.: Evolutionary fuzzy systems for explainable artificial intelligence: why, when, what for, and where to? IEEE Comput. Intell. Mag. 14(1), 69–81 (2019)
Fürnkranz, J., Gamberger, D., Lavrac, N.: Foundations of Rule Learning. Springer, New York (2012)
Kuncheva, L.: How good are fuzzy if-then classifiers? IEEE Trans. Syst. Man Cybern. B 30(4), 501–509 (2000)
Mencar, C., Alonso, J.: Paving the way to explainable artificial intelligence with fuzzy modelling. In: Fuzzy Logic and Applications: 12th International Workshop, pp. 215–226 (2018)
Morales-Vargas, E., Reyes-García, C., Peregrina-Barreto, H., Orihuela-Espina, F.: Facial expression recognition with fuzzy explainable models. In: Models and Analysis of Vocal Emissions for Biomedical Applications: 10th International Workshop (2017)
Keneni, B., et al.: Evolving rule-based explainable artificial intelligence for unmanned aerial vehicles. IEEE Access 7, 17001–17016 (2019)
Deng, Y., Ren, Z., Kong, Y., Bao, F., Dai, Q.: A hierarchical fused fuzzy deep neural network for data classification. IEEE Trans. Fuzzy Syst. 25(4), 1006–1012 (2017)
Lee, C., Teng, C.: Identification and control of dynamic systems using recurrent fuzzy neural networks. IEEE Trans. Fuzzy Syst. 8(4), 349–366 (2000)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Deng, L., Yu, D.: Deep learning: methods and applications. Found. Trends Signal Process. 7, 3–4 (2013)
Russel, S., Norvig, P.: Artificial Intelligence: A Modern Approach, 3rd Edition (2010)
Zadeh, L.A.: Fuzzy sets. Inform. Control 8(3), 338–353 (1965)
Zadeh, L.A.: Outline of a new approach to the analysis of complex systems and decision processes. IEEE Trans. Syst. Man Cybern. 1, 28–44 (1973)
Ponce-Cruz, P., Ramírez-Figueroa, F.: Intelligent Control Systems with LabVIEW. Springer, Berlin (2010)
Ponce-Cruz, P.: Inteligencia Artificial con Aplicaciones a la Ingeniería, Editorial Alfaomega (2011)
Knapp, R., Agarwal, U., Djamschidi, R., Layeghi, S., Dastamalchi, M.: The use of fuzzy set classification for pattern recognition of the polygraph. In: IEEE 3rd International Fuzzy Systems Conference (1995)
Driankov, D., Saffiotti, A.: Fuzzy Logic in Autonomous Navigation. Springer, Berlin (2001)
Wu, D.: Twelve considerations in choosing between Gaussian and trapezoidal membership functions in interval type-2 fuzzy logic controllers. In: IEEE International Conference on Fuzzy Systems (2012)
AWS DeepRacer Developer Guide: Amazon Web Services Inc. (2020). https://docs.aws.amazon.com/deepracer/latest/ developerguide/awsracerdg.pdf. Accessed 12 Apr 2020
Acknowledgements
The authors would like to thank Nora Clancy Kelsall for her English Language editing, and Dr. David Balderas-Silva and Dr. Renato Galluzzi review services. This research is being supported by the Laboratory of Computer Intelligente, Mechatronics and Biodesign (CIMB) at Tecnologico de Monterrey.
Funding
Funding was provided by Tecnologico de Monterrey - Grant No. A00996397, and Consejo Nacional de Ciencia y Tecnologia (CONACYT) by the scholarship 679120.
The authors would like to acknowledge the financial support of the Novus Grant with PEP no. PHHT032-19ZZ00013, TecLabs, Tecnologico de Monterrey, in the production of this work.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Code availability
All the versions of the Deep Reinforcement Learning Fuzzy Inference System are located in this Github repository https://github.com/Rolix57/RL-FISRolix57/RL-FIS.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Bautista-Montesano, R., Bustamante-Bello, R. & Ramirez-Mendoza, R.A. Explainable navigation system using fuzzy reinforcement learning. Int J Interact Des Manuf 14, 1411–1428 (2020). https://doi.org/10.1007/s12008-020-00717-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12008-020-00717-1