ABSTRACTS OF ARTICLES OF THE JOURNAL "INFORMATION TECHNOLOGIES".
No. 3. Vol. 29. 2023

DOI: 10.17587/it.29.115-125

A. S. Akopov, Professor, L. A. Beklaryan, Professor,
Central Economics and Mathematics Institute RAS, Moscow, Russian Federation,
A. L. Beklaryan, Associate Professor, HSE University, Moscow, Russian Federation

Optimising Characteristics of an Intelligent Transport System Using a Real-Coded Genetic Algorithm Based on Adaptive Mutation

A novel real-coded genetic algorithm (FCGA-AM) that uses the proposed adaptive mutation (AM) operator is presented. The algorithm is designed to optimise the characteristics of the developed intelligent transportation system. The performance of the proposed genetic algorithm was evaluated in comparison with other methods of multicriteria heuristic optimization with the use of various test instances and well-known quality metrics for Pareto frontiers. At the next stage, the FCGA-AM was applied to find the best road safety trade-offs involving unmanned ground vehicles (UAVs) interacting with conventional ground vehicles (UTVs), pedestrians and other agents.
Keywords: intelligent transportation systems, traffic safety, real-coded genetic algorithm, multi-obective optimisation, multi-agent systems, unmanned ground vehicles, digital road networks

Acknowledgements: The reported study was funded by RFBR, project number 19-29-06003

P. 115–125

References

1. Fayazi S. A., Vahidi A. Mixed-Integer Linear Programming for Optimal Scheduling of Autonomous Vehicle Intersection Crossing, IEEE Transañtions on Intelligent Vehides, 2018, vol. 3, no. 3, pp. 287—299.
   
2. Hegyi A., Schutter B. D., Hellendoorn J. Optimal coordination of variable speed limits to suppress shock waves, IEEE Transañtions on Intelligent Transportation Systems, 2005, vol. 6, no. 1, pp. 102—112.
3. Akopov A. S., Beklaryan L. A., Thakur M. Improvement of Maneuverability Within a Multiagent Fuzzy Transportation System With the Use of Parallel Biobjective Real-Coded Genetic Algorithm, IEEE Transañtions on Intelligent Transportation Systems, 2022, vol. 23, no. 8, pp. 12648—12664.
4. Akopov A. S., Beklaryan L. A., Beklaryan A. L., Belousov F. A. Modelirovanie dvizheniya ansamblya nazemnih bespilotnih transportnih sredstv s ispolzovaniem FLAME GPU, Informañionnie tehnologii, 2021, vol. 27, no. 7. pp. 369—379 (in Russian).
5. Akopov A. S., Beklaryan L. A., Khachatryan N. K., Beklaryan A. L., Kuznetsova E. V. Mnogoagentnaja sistema upravlenija nazemnymi bespilotnymi transportnymi sredstvami, Informañionnye Tehnologii, 2020, vol. 26, no. 6, pp. 342—353 (in Russian).
6. Herrera F., Lozano M., Verdegay J. L. Tackling real-coded genetic algorithms: Operators and tools for behavioural analysis, Artifiñial Intelligenñe Review, 1998, vol. 12, no. 4, pp. 265—319.
7. Herrera F., Lozano M. Gradual distributed real-coded ge­netic algorithms, IEEE TransaCtions on Evolutionary Computation, 2000, vol. 4, no. 1, pp. 43—63.
8. Kureychik V. V., Rodzin S. I. Computational Models of Evolutionary and Swarm Bio Heuristics (Review), Informañionnie tehnologii, 2021, vol. 27, no. 10, pp. 507—520 (in Russian).
9. Nascimento S., Mirkin B., Moura F. Modeling proportional membership in fuzzy clustering, IEEE TransaCtions on Fuzzy Systems, 2003, vol. 11, no. 2, pp. 173—186.

10. Bezdek J. C. Cluster validity with fuzzy sets, Journal of Cybernetics, 1974, vol. 3, no. 3, pp. 58—73.

11. Friedrich T., Bringmann K., VoB T., Igel C. The logarith­mic hypervolume indicator, In Proñeedings of the 11th workshop proñeedings on Foundations of genetiñ algorithms (FOGA '11), 2011, Association for Computing Machinery, New York, NY, USA, pp. 81—92.

12. Zitzler E., Thiele L., Laumanns M., Fonseca C. M., da Fonseca V. G. Performance assessment of multiobjective opti­mizers: an analysis and review, IEEE TransaCtions on Evolutionary Computation, 2003, vol. 7, no. 2, pp. 117—132.

13. Deep K., Thakur M. A new crossover operator for real coded genetic algorithms, Applied Mathematics and Computation, 2007, vol. 188, no. 1, pp. 895—911.

14. Deep K., Thakur M. A new mutation operator for real coded genetic algorithms, Applied Mathematics and Computation, 2007, vol. 193, no. 1, pp. 211—230.

15. Zitzler E., Laumanns M., Thiele L. SPEA2: Improving the strength pareto evolutionary algorithm. Swiss Federal Inst. Teñhnol, Zurkh, Switzerland, 2001, TIK-Rep. N. 103.

16. Deb K., Jain H. An evolutionary many-objective optimi­zation algorithm using reference-point-based nondominated sorting approach, part I: solving problems with box constraints, IEEE Transañtions on Evolutionary Computation, 2014, vol. 18, no. 4, pp. 577—601.

17. Zhang Q., Li H. MOEA/D: A Multiobjective Evolutionary Algorithm Based on Decomposition, IEEE Transañtions on Evolutionary Computation, 2007, vol. 11, no. 6, pp. 712—731.

18. Moraes D. H., Sanches D. S., da Silva Rocha J., Garbelini J. M. C., Castoldi M. F. A novel multi-objective evolutionary algorithm based on subpopulations for the bi-objective traveling salesman problem, Soft Computing, 2019, vol. 23, pp. 6157—6168.

19. Zain M. Z., Kanesan J., Chuah J. H., Dhanapal S., Kendall G. A multi-objective particle swarm optimization algorithm based on dynamic boundary search for constrained optimization, Applied Soft Computing, 2018, vol. 70, pp. 680—700.

To the contents