Article 10320

Title of the article

AN OPTIMIZATION METHOD OF THE UNMANNED VEHICLE CONTROLLER’S
PARAMETERS BASED ON THE OPTIMIZATION OF PARTICLES’S ROY 

Authors

Darina Anna Nikolaevna, candidate of physical and mathematical sciences, associate professor, leading researcher, Federal research center «Computer science and control» of RAS (Dorodnitsyn computer center of the Russian Academy of Sciences) (bld. 2, 44 Vavilova street, Moscоw, Russia), daryina@ccas.ru
Prokopyev Igor Vitalevich, doctor of technical sciences, leading researcher, Federal research center «Computer science and control» of RAS (Dorodnitsyn computer center of the Russian Academy of Sciences) (bld. 2, 44 Vavilova street, Moscоw, Russia), fvi2014@list.ru

Index UDK

658.62.018.012 

DOI

10.21685/2307-4205-2020-3-10 

Abstract

For an unmanned vehicle, in difficult conditions, when spatial constraints seriously narrow the space of admissible states, the strategy of choosing a state space is more effective than sampling in the control space. Although this was obvious, the practical question is how to achieve it while meeting the stringent constraints of the vehicle's dynamic feasibility. This article presents an unmanned vehicle control system based on the predictive integrated path model (MPPI) controller, deep convolutional neural network (CNN) for real-time scene understanding and particle swarm optimization (PSO) to find the vector of optimal cost function parameters. The method is based on the optimization of the cost function, which determines where the vehicle should move on the surface of the path. 

Key words

unmanned vehicle, predictive control model, neural network, particle swarm optimization method. 

 Download PDF
References

1. Mayne D. Q. Automatica. 2014, vol. 50, no. 12, pp. 2967–2986.
2. Howard T., Kelly A. International Journal of Robotics Research. 2007, vol. 26, no. 2, pp. 141–166.
3. Engel J., Schops T., Cremers D. European Conference on Computer Vision. Springer, 2014, pp. 834–849.
4. Mur-Artal R., Montiel J. M. M., Tardos J. D. IEEE Transactions on Robotics. 2015, vol. 31 (5), pp. 1147–1163.
5. Zhang J., S. Singh Loam Robotics: Science and Systems. 2014, vol. 2, pp. 634–637.
6. Newcombe R. A., Izadi S., Hilliges O., Molyneaux D., Kim D., Davison A. J., Kohi P., Shotton J., Hodges S., Fitzgibbon A. Mixed and augmented reality (ISMAR), 2011 10th IEEE international symposium. 2011, pp. 127– 136.
7. Kendall A., Cipolla R. Proceedings of the International Conference on Robotics and Automation (ICRA). 2016, pp. 1–8.
8. Williams G., Drews P., Goldfain B., Rehg J. M., Theodorou E. A. 2016 IEEE International Conference on Robotics and Automation (ICRA). 2016, pp. 1433–1440.
9. Williams G., Aldrich A., Theodorou E. A. Journal of Guidance, Control, and Dynamics. 2017, pp. 1–14.
10. Dar'ina A. N., Diveev A. I., Prokop'ev I. V. Voprosy teorii bezopasnosti i ustoychivosti system [Questions of the theory of security and stability of systems]. Moscow: FITs IU RAN, 2019, iss. 21, pp. 66–77. [In Russian]
11. Weise T. Global Optimization Algorithms – Theory and Application: Ph.D Thesis. University of Kassel, 2008, pp. 184–186.
12. Kennedy J., Eberhart R. Proceedings of IEEE International conference on Neural Networks. 1995, pp. 1942– 1948.
13. Diveev A., Sofronova E. Bio-Inspired Computational Algorithms and Their Applications. Ed. by Dr. Shangce Gao. InTech, 2012, pp. 19–42.
14. Williams G., Wagener N., Goldfain B., Drews P., Rehg J. M., Boots B., Theodorou A. E. 2017 IEEE International Conference on Robotics and Automation (ICRA) (29 May – 3 June 2017). 2017, pp. 361–363.

 

Дата создания: 24.11.2020 14:46
Дата обновления: 24.11.2020 16:08