The efficiency of cooperative navigation algorithms for groups of mobile robots critically depends on their hyperparameters, the optimal values of which vary with the structure of the environment (e.g., office or polygon). Manually tuning these parameters for each new environment type is impractical. This paper proposes a method for automatically adapting the behavior of a robot group using evolutionary tuning. Based on the GARCA hybrid architecture, which considers neighbors' goals, a compact vector of six interpretable hyperparameters is formed. A genetic algorithm with real-valued encoding is used for their optimization. The results of a numerical experiment confirm that evolutionary tuning can automatically discover different behavioral strategies: an "aggressive" one for structured office environments and a "cooperative" one for environments with chaotic obstacles. The adapted GARCA+GA algorithm significantly outperforms methods with fixed parameters in terms of mission success rate and completion time.
cooperative navigation, group of mobile robots, evolutionary tuning, genetic algorithm, environment adaptation, hyperparameters, GARCA
1. Floreano D., Husbands P., Nolfi S. Evolutionary robotics // Springer Handbook of Robotics. – Berlin, Heidelberg: Springer, 2008. – Pp. 1423-1451. DOI: https://doi.org/10.1007/978-3-540-30301-5_62
2. Van den Berg J., Lin M., Manocha D. Reciprocal velocity obstacles for real-time multi-agent navigation // 2008 IEEE International Conference on Robotics and Automation. – 2008. – Pp. 1928-1935. DOI: https://doi.org/10.1109/ROBOT.2008.4543489
3. Zarevich A. I., Makarenko F. V., Yagodkin A. S., Zol'nikov K. V. Modelirovanie povedeniya mobil'nyh robotov s ispol'zovaniem geneticheskih algoritmov // Modelirovanie sistem i processov. – 2022. – T. 15, № 3. – S. 7-16. DOI: https://doi.org/10.12737/2219-0767-2022-15-3-7-16
4. Karaman S., Frazzoli E. Sampling-based algorithms for optimal motion planning // The International Journal of Robotics Research. – 2011. – Vol. 30, № 7. – Pp. 846-894. DOI: https://doi.org/10.1177/0278364911406761
5. Santos F. M., Silva M. G., Moreira A. P. Hybrid RRT*-RVO for multi-robot navigation in dynamic environments // ROBOTICA. – 2019. – Vol. 37, № 9. – Pp. 1571-1587.
6. Modelirovanie oslableniya ioniziruyuschego izlucheniya za schet zaschitnogo korpusa mikroshem / A. V. Poluektov, R. Yu. Medvedev, A. I. Zarevich // Modelirovanie sistem i processov. – 2024. – T. 17, № 2. – S. 93–100. – DOIhttps://doi.org/10.12737/2219-0767-2024-17-2-93-100. – EDN QQRQXE.
7. Regressionnyy analiz ocenki zagruzki platnogo otdeleniya stomatologicheskoy polikliniki / T. P. Novikova, A. A. Bodin, A. I. Zarevich // Nauchno-tehnicheskiy vestnik Povolzh'ya. – 2023. – № 3. – S. 77–80.
8. Primenenie elementov otricatel'noy logiki pri postroenii energoeffektivnogo kombinacionnogo ustroystva / F. V. Makarenko, A. S. Yagodkin, O. A. Denisova [i dr.] // Modelirovanie sistem i processov. – 2023. – T. 16, № 1. – S. 56–66. – DOIhttps://doi.org/10.12737/2219-0767-2023-16-1-56-66.
9. Tehnologiya razrabotki RTL-modeli opisaniya izdeliya pri razrabotke programmno-analiticheskogo kompleksa SAPR / D. V. Shehovcov, A. M. Plotnikov, K. V. Zol'nikov, A. I. Zarevich // Modelirovanie sistem i processov. – 2023. – T. 16, № 3. – S. 79–86. DOI: https://doi.org/10.12737/2219-0767-2023-16-3-79-86
10. Geneticheskie algoritmy v modelirovanii povedeniya robota / A. S. Logvinenko, L. Yu. Smilyanskiy, A. I. Zarevich, F. V. Makarenko // Novye aspekty modelirovaniya sistem i processov : materialy Mezhdunar. nauch.-prakt. konf. / otv. red. V. K. Zol'nikov, A. I. Zarevich. – Voronezh, 2023. – S. 94–103.
11. Komp'yuternoe modelirovanie raboty tranzistorov i poluprovodnikovyh priborov na ego osnove / A. V. Poluektov, F. V. Makarenko, R. Yu. Medvedev // Modelirovanie sistem i processov. – 2023. – T. 16, № 1. – S. 77–84. – DOIhttps://doi.org/10.12737/2219-0767-2023-16-1-77-84. – EDN LOLZMT.
12. Modelirovanie raboty dioda i ocenka parametrov ego raboty / A. V. Poluektov, R. Yu. Medvedev, V. K. Zol'nikov // Modelirovanie sistem i processov. – 2023. – T. 16, № 1. – S. 85–93. – DOIhttps://doi.org/10.12737/2219-0767-2023-16-1-85-93. – EDN RALIJG.
13. Integraciya programmnogo produkta Calibre v sredu Cadence Virtuoso i povyshenie intellektual'nyh svoystv SAPR proektirovanii mikroshem / A. V. Poluektov, D. V. Shehovcov, I. V. Skorkin, P. A. Chubunov // Modelirovanie sistem i processov. – 2023. – T. 16, № 4. – S. 71–80. – DOIhttps://doi.org/10.12737/2219-0767-2023-16-4-71-80. – EDN PBUJZO.
14. Ispol'zovanie storonnih bibliotek pri napisanii programm dlya obrabotki statisticheskih dannyh / A. V. Poluektov, F. V. Makarenko, A. S. Yagodkin // Modelirovanie sistem i processov. – 2022. – T. 15, № 2. – S. 33–41. – DOIhttps://doi.org/10.12737/2219-0767-2022-15-2-33-41. – EDN HHYURU.
15. Eksperimental'nye issledovaniya radiacionnogo vozdeystviya na mikroshemy FRAM / V. K. Zol'nikov, N. G. Gamzatov, V. I. Anciferova [i dr.] // Modelirovanie sistem i processov. – 2022. – T. 15, № 3. – S. 16–24. – DOIhttps://doi.org/10.12737/2219-0767-2022-15-3-16-24. – EDN UOCKEW.
16. Modelirovanie kolebatel'nyh processov v pakete MVSTUDIUM / A. V. Poluektov, K. V. Zol'nikov, V. I. Anciferova // Modelirovanie sistem i processov. – 2021. – T. 14, № 4. – S. 139–148. – DOIhttps://doi.org/10.12737/2219-0767-2021-14-4-139-148. – EDN PPOUDI.
17. Apparatno-programmnyy kompleks dlya avtomatizirovannyh ispytaniy sil'notochnyh preobrazovateley / A. I. Zarevich, S. V. Murav'ev, E. V. Bedareva [i dr.] // Izvestiya Tomskogo politehnicheskogo universiteta. – 2013. – T. 322, № 4. – S. 180–184.
18. Lokal'naya ustoychivost' kolebaniy magnetrona so svyazannymi rezonatorami / A. I. Zarevich, S. S. Novikov // Vestnik nauki Sibiri. – 2013. – № 4 (10). – S. 109–114.
