Skip to main content
main-content
Top

Hint

Swipe to navigate through the chapters of this book

2020 | OriginalPaper | Chapter

A Reinforcement Learning Enhanced Fuzzy Control for Real-Time Off-Road Traction System

Authors: Vladimir Vantsevich, David Gorsich, Andriy Lozynskyy, Lyubomyr Demkiv, Sviatoslav Klos

Published in: Advances in Dynamics of Vehicles on Roads and Tracks

Publisher: Springer International Publishing

share
SHARE

Abstract

In deformable terrain conditions, the tire-surface gripping may be characterized by drastic, rapid, and frequent changes, and, thus, the response time of traction control systems (TCS) of off-road vehicles is crucial for real-time mobility improvements. To advance TCS performance, the time boundaries for the TCS response time is established in the paper based on a physical property of the transient tire traction force, which is the tire relaxation time constant. A Q-learning (QL) algorithm is synthesized to ensure the established time boundaries and to provide real-time TCS response. Then, the reinforcement learning algorithm is proposed to adjust parameters of a fuzzy logic controller (FLC). The proposed control method outperforms the straightforward reinforcement learning in terms of the smoothness of the output signal and control action while also ensuring the established time boundaries. The mathematical modeling and simulation study is applied to an open-link locomotion module described in the paper.
Literature
1.
go back to reference Day, A.J.: Braking of Road Vehicles. Butterworth-Heinemann, Oxford (2014) Day, A.J.: Braking of Road Vehicles. Butterworth-Heinemann, Oxford (2014)
2.
go back to reference Hori, Y.: Future vehicle driven by electricity and control-research on four-wheel-motored “UOT Electric March II”. IEEE Trans. Ind. Electron. 51(5), 954–962 (2004) CrossRef Hori, Y.: Future vehicle driven by electricity and control-research on four-wheel-motored “UOT Electric March II”. IEEE Trans. Ind. Electron. 51(5), 954–962 (2004) CrossRef
3.
go back to reference Vantsevich, V.V., Lozynskyy, A., Demkiv, L., Klos, S.: A foundation for real-time tire mobility estimation and control. In: 19th International and 14th European-African Regional Conference of the ISTVS, Budapest, Hungary, September 2017 (2017). Paper # 126 Vantsevich, V.V., Lozynskyy, A., Demkiv, L., Klos, S.: A foundation for real-time tire mobility estimation and control. In: 19th International and 14th European-African Regional Conference of the ISTVS, Budapest, Hungary, September 2017 (2017). Paper # 126
4.
go back to reference Mohajerin, N., Menhaj, M.B., Doustmohammadi, A.: A reinforcement learning fuzzy controller for the ball and plate system. In: International Conference on Fuzzy Systems, pp. 1–8. IEEE, July 2010 Mohajerin, N., Menhaj, M.B., Doustmohammadi, A.: A reinforcement learning fuzzy controller for the ball and plate system. In: International Conference on Fuzzy Systems, pp. 1–8. IEEE, July 2010
5.
go back to reference Boubertakh, H., Tadjine, M., Glorennec, P.Y., Labiod, S.: Tuning fuzzy PD and PI controllers using reinforcement learning. ISA Trans. 49(4), 543–551 (2010) CrossRef Boubertakh, H., Tadjine, M., Glorennec, P.Y., Labiod, S.: Tuning fuzzy PD and PI controllers using reinforcement learning. ISA Trans. 49(4), 543–551 (2010) CrossRef
6.
go back to reference Camci, E., Kayacan, E.: Game of drones: UAV pursuit-evasion game with type-2 fuzzy logic controllers tuned by reinforcement learning. In: 2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), pp. 618–625. IEEE, July 2016 Camci, E., Kayacan, E.: Game of drones: UAV pursuit-evasion game with type-2 fuzzy logic controllers tuned by reinforcement learning. In: 2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), pp. 618–625. IEEE, July 2016
7.
go back to reference Andreev, A.F., Kabanau, V., Vantsevich, V.: Driveline Systems of Ground Vehicles: Theory and Design. CRC Press, Boca Raton (2010) CrossRef Andreev, A.F., Kabanau, V., Vantsevich, V.: Driveline Systems of Ground Vehicles: Theory and Design. CRC Press, Boca Raton (2010) CrossRef
8.
go back to reference Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018) MATH Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018) MATH
9.
10.
go back to reference Aceves-López, A., Aguilar-Martin, J.: A simplified version of Mamdani’s fuzzy controller: the natural logic controller. IEEE Trans. Fuzzy Syst. 14(1), 16–30 (2006) CrossRef Aceves-López, A., Aguilar-Martin, J.: A simplified version of Mamdani’s fuzzy controller: the natural logic controller. IEEE Trans. Fuzzy Syst. 14(1), 16–30 (2006) CrossRef
11.
go back to reference Vantsevich, V.V., Lozynskyy, A., Demkiv, L., Holovach, I.: Fuzzy logic control of agile dynamics of a wheel locomotion module. In: Dynamics of Vehicles on Roads and Tracks Vol 1: Proceedings of the 25th International Symposium on Dynamics of Vehicles on Roads and Tracks (IAVSD 2017), Rockhampton, Queensland, Australia, p. 401. CRC Press (2017) Vantsevich, V.V., Lozynskyy, A., Demkiv, L., Holovach, I.: Fuzzy logic control of agile dynamics of a wheel locomotion module. In: Dynamics of Vehicles on Roads and Tracks Vol 1: Proceedings of the 25th International Symposium on Dynamics of Vehicles on Roads and Tracks (IAVSD 2017), Rockhampton, Queensland, Australia, p. 401. CRC Press (2017)
12.
go back to reference Higuchi, A., Pacejka, H.B.: The relaxation length concept at large wheel slip and camber. Veh. Syst. Dyn. 27(S1), 50–64 (1997) CrossRef Higuchi, A., Pacejka, H.B.: The relaxation length concept at large wheel slip and camber. Veh. Syst. Dyn. 27(S1), 50–64 (1997) CrossRef
13.
go back to reference Vantsevich, V.V., Demkiv, L.I., Klos, S.R.: Analysis of tire relaxation constants for modeling vehicle traction performance and handling. In: ASME 2018 Dynamic Systems and Control Conference. American Society of Mechanical Engineers, September 2018 Vantsevich, V.V., Demkiv, L.I., Klos, S.R.: Analysis of tire relaxation constants for modeling vehicle traction performance and handling. In: ASME 2018 Dynamic Systems and Control Conference. American Society of Mechanical Engineers, September 2018
14.
go back to reference TNO Automotive: MF-Tyre/MF-Swift 6.2 Help Manual, The Netherlands (2013) TNO Automotive: MF-Tyre/MF-Swift 6.2 Help Manual, The Netherlands (2013)
15.
go back to reference Adams Tire Help (for Adams 2017.2). MSC software documentation (2017) Adams Tire Help (for Adams 2017.2). MSC software documentation (2017)
16.
go back to reference Rill, G.: First order tire dynamics. In: Proceedings of the III European Conference on Computational Mechanics Solids, Structures and Coupled Problems in Engineering, Lisbon, Portugal, vol. 58, June 2006 Rill, G.: First order tire dynamics. In: Proceedings of the III European Conference on Computational Mechanics Solids, Structures and Coupled Problems in Engineering, Lisbon, Portugal, vol. 58, June 2006
17.
go back to reference Ng, A.Y., Coates, A., Diel, M., Ganapathi, V., Schulte, J., Tse, B., Berger, E., Liang, E.: Autonomous inverted helicopter flight via reinforcement learning. In: Experimental Robotics IX, pp. 363–372. Springer, Heidelberg (2006) Ng, A.Y., Coates, A., Diel, M., Ganapathi, V., Schulte, J., Tse, B., Berger, E., Liang, E.: Autonomous inverted helicopter flight via reinforcement learning. In: Experimental Robotics IX, pp. 363–372. Springer, Heidelberg (2006)
18.
go back to reference Molnos, A., Lesecq, S., Mottin, J., Puschini, D.: Investigation of Q-learning applied to DVFS management of a System-on-Chip. IFAC-PapersOnLine 49(5), 278–284 (2016) MathSciNetCrossRef Molnos, A., Lesecq, S., Mottin, J., Puschini, D.: Investigation of Q-learning applied to DVFS management of a System-on-Chip. IFAC-PapersOnLine 49(5), 278–284 (2016) MathSciNetCrossRef
19.
go back to reference Dorf, R.C., Bishop, R.H.: Modern Control Systems. Pearson, Boston (2011) MATH Dorf, R.C., Bishop, R.H.: Modern Control Systems. Pearson, Boston (2011) MATH
Metadata
Title
A Reinforcement Learning Enhanced Fuzzy Control for Real-Time Off-Road Traction System
Authors
Vladimir Vantsevich
David Gorsich
Andriy Lozynskyy
Lyubomyr Demkiv
Sviatoslav Klos
Copyright Year
2020
DOI
https://doi.org/10.1007/978-3-030-38077-9_137

Premium Partner