Journal "Software Engineering"
a journal on theoretical and applied science and technology
ISSN 2220-3397

Issue N3 2023 year

DOI: 10.17587/prin.14.110-122
Agent-Based Modelling of Interacting Unmanned Vehicles Dynamics with the FLAME GPU
A. S. Akopov, Dr. Sc., Professor, Chief Researcher, akopovas@umail.ru, CEMI RAS, Moscow, 117418, Russian Federation, MIREA — Russian Technological University, Moscow, 119454, Russian Federation, L. A. Beklaryan, Dr. Sc., Professor, Chief Researcher, beklar@cemi.rssi.ru, CEMI RAS, Moscow, 117418, Russian Federation
Corresponding author: Andranik S. Akopov, Dr. Sc., Professor, Chief Researcher, CEMI RAS, Moscow, 117418, Russian Federation Professor, MIREA — Russian Technological University, Moscow, 119454, Russian Federation E-mail: akopovas@umail.ru
Received on January 09, 2023
Accepted on January 25, 2023

The article presents an approach to modelling traffic flows based on the intelligent analysis of unmanned ground vehicles (UGVs) dynamics within of which a novel decision-making system on maneuvering for agent-UGVs is designed. The proposed system uses clustering methods for an estimation of a traffic congestion density on alternative routes of the digital road network (DRN) to detour problem areas and minimisе risks of traffic accidents appearing. For the first time, the spatial dynamics of interacting UGVs is modelled with complex schemes for constructing the DRNs, including multiple intersecting ring, straight and diagonal sections that form various alternative routes for road users. The de­veloped model is implemented with the supercomputer agent-based modelling framework FLAME GPU. An algorithm for the behaviour of UGVs during the formation of traffic congestions has been developed, in particular, it provides an effective splitting of traffic flows by increasing the probability of choosing less pressed alternative routes for UGVs. As a result of numerical experiments, the following important regularity was obtained: an increase in the share of UGVs in the DRN using intelligent maneuvering based on cluster analysis of traffic flows with a controlled radius of an agent personal space provides a decrease in the total density of traffic congestion and contributes to a decrease in accidents.

Keywords: agent-based modelling of transportation systems, unmanned vehicles, road networks, simulation of traffic congestion and accidents, simulation modelling for intelligent transport systems, FLAME GPU
pp. 110–122
For citation:
Akopov A. S., Beklaryan L. A. Agent-Based Modelling of Interacting Unmanned Vehicles Dynamics with the FLAME GPU, Programmnaya Ingeneria, 2023, vol. 14, no. 3, pp. 110—122. DOI: 10.17587/prin.14.110-122. (in Russian).
References:
  1. 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 Transactions on Intelligent Transportation Systems, 2022, vol. 23, no. 8, pp. 12648—12664. DOI: 10.1109/TITS.2021.3115827.
  2. Akopov A. S., Beklaryan L. A. Simulation of rates of traffic accidents involving unmanned ground vehicles within a transporta­tion system for the 'smart city' Business Informatics, 2022, vol. 16, no. 4, pp. 19—35. DOI: 10.17323/2587-814X.2022.4.i9.35.
  3. Akopov A. S., Beklaryan L. A., Beklaryan A. L. Simulation-Based Optimisation for Autonomous Transportation Systems Using a Parallel Real-Coded Genetic Algorithm with Scalable Nonuniform Mutation, Cybernetics and information technologies, 2021, vol. 21, no. 3, pp. 127-144. DOI: 10.2478/cait-2021-0034.
  4. Akopov A. S., Beklaryan L. A., Beklaryan A. L. Belousov F. L. Simulation of Motion of an Ensemble of Unmanned Ground Vehicles Using FLAME GPU, Informacionnye tekhnologii, 2021, vol. 27, no 7, pp. 369—379. DOI: 10.17587/it.27.369-379 (in Russian).
  5. Akopov A. S., Beklaryan L. A., Khachatryan N. K. еt al. Multi-agent control system for unmanned ground vehicles, Informa-cionnye tekhnologii, 2020, vol. 26, no. 6, pp. 342—353. DOI: 10.17587/ it.26.342-353 (in Russian).
  6. Gong D., Tang M., Buchmeister B., Zhang H. Solving Lo­cation Problem for Electric Vehicle Charging Stations — A Shar­ing Charging Model, IEEE Access, 2019, vol. 7, pp. 138391-138402. DOI: 10.1109/ACCESS.2019.2957803.
  7. Shen T., Hua K., Liu J. Optimized Public Parking Loca­tion Modelling for Green Intelligent Transportation System Using Genetic Algorithms, IEEE Access, 2019, vol. 7, pp. 176870—176883. DOI: 10.1109/ACCESS.20i9.2943079.
  8. Nikam V. B., Arora A., Lambture D. et al. Optimal Posi­tioning of Small Cells for Coverage and Cost Efficient 5G Network Deployment: A Smart Simulated Annealing Approach, In proceed­ings of2020 IEEE 3rd 5G World Forum (5GWF), 2020, pp. 454—459. DOI: 10.1109/5GWF49715.2020.9221257.
  9. Richmond P., Chisholm R., Heywood P. et al. FLAME GPU, Zenodo, 2021. DOI: 10.5281/ZENODO.5428984.
  10. Duan M. Short-Time Prediction of Traffic Flow Based on PSO Optimized SVM, In proceedings of 2018 International Confer­ence on Intelligent Transportation, Big Data & Smart City (ICITBS), 2018, pp. 41—45. DOI: 10.1109/ICITBS.2018.00018.
  11. Gnana Jeevan A. N., Keerthika K., Rao Terli S. et al. A Novel Approach for Predicting wide range of traffic congestion using deep learning Technique, In proceedings of2022 International Conference on Innovative Computing,, Intelligent Communication and Smart Electrical Sys­tems (ICSES), 2022, pp. 1—6. DOI: 10.1109/ICSES55317.2022.9914313.
  12. Yin Z., Wang J., Lu H. A Study on Urban Traffic Conges­tion Dynamic Predict Method Based on Advanced Fuzzy Clustering Model, In proceedings of 2008 International Conference on Compu­tational Intelligence and Security, 2008, pp. 96-100. DOI: 10.1109/CIS.2008.i94.
  13. Gasnikov A. V. et al. Introduction to mathematical modeling of traffic flows: Textbook, Moscow, Moscow Institute of Physics and Technology, 2010, pp. 362 (in Russian).
  14. Ie О. N. Simulation of transport systems: software tools and directions for their improvement, Aktual'nye voprosy sovremennoj ekonomiki, 2020, no. 5, pp. 428—439 (in Russian).
  15. Lee K. S., Yom J. K., Moon D. Applications of TRANSIMS in Transportation: A Literature Review, Procedia Computer Science, 2014, vol. 32, pp. 769—773. DOI: 10.1016/j.procs.2014.05.489.
  16. Dantsuji T., Hoang N. H., Zheng N., Vu H. L. A novel metamodel-based framework for large-scale dynamic origin—desti­nation demand calibration, Transportation Research Part C: Emerging Technologies, 2022, vol. 136, 103545. DOI: 10.1016/j.trc.202i.i03545.
  17. Craighead J., Murphy R., Burke J., Goldiez B. A Survey of Commercial & Open Source Unmanned Vehicle Simulators, In proceedings of 2007 IEEE International Conference on Robotics and Automation, 2007, pp. 852—857. DOI: 10.1109/ROBOT.2007.363092.
  18. Mullner D. fastcluster: Fast Hierarchical, Agglomerative Clustering Routines for R and Python, Journal of Statistical Software, 2013, vol. 53, no. 9, pp. 1—18.
  19. Richmond P., Walker D., Coakley S., Romano D. High per­formance cellular level agent-based simulation with FLAME for the GPU, Briefings in Bioinformatics, 2010, vol. 11, no. 3, pp. 334—347. DOI: 10.1093/bib/bbp073.
  20. Tracking: An Integrated System and Evaluation for Monitoring Driver Awareness, IEEE Transactions on Intelligent Transportation Systems, 2010, vol. 11, no. 2, pp. 300—311. DOI: 10.1109/TITS.2010.2044241.
  21. Maltsev A. V. Methods for Real&Time Distributed Imitation of Indirect Shading in Virtual Environment on GPU, Programmnaya ingeneria, 2020, vol. 11, no. 4, pp. 213—218. DOI: 10.17587/ prin.11.213-218 (in Russian).