SCENARIO-CASE APPROACH TO THE CONTROL OF HETEROGENEOUS ENSEMBLES OF DYNAMIC OBJECTS

V. G. Sherstjuk, I. V. Sokol, E. N. Tarasenko

Abstract


Purpose. The article is devoted to developing the method of intelligent coordination control of a complex heterogeneous ensemble of dynamic objects. Methodology. The method of solving this problem is based on the case-scenario approach presenting the activity of dynamic objects as templates that adapt to changing external conditions by using scenarios. The algorithm of satisfaction of critical time constraints was used to adapt scenarios. The proposed method can adequately reflect the experience and knowledge of control of a dynamic objects’ group using similar decision stereotypes to control in similar situations. The main elements of case decisions such as control actions, operations, scenarios, and plans were described. Findings. The hybrid control system was implemented. The lower level of the system was developed based on the hybrid system BRIZ, which combining the subsystem based on cases with the subsystem that implements the movement model and so is master, while case subsystem is slave. The middle and top levels of the system were developed as the event-based hybrid system MUSSON, which includes case-scenario subsystem, storage subsystem and subsystem that calculating spatial regions based on the model. Scripts and triggers for each class of events were described by scripting language SCDL. Originality. The three-tier coordination control system for ensembles of dynamic objects based on case-scenario approach was proposed for the first time. The lower level is dedicated to control of separate dynamic objects, the second level is aimed to coordination of objects that jointly move, and the upper level provide the mission of the whole ensemble of dynamic objects. Practical value. The proposed approach is insensitive to inaccuracies and incomplete observations. It can reduce the information overload in the situation analysis, as well as decision-making time, thus increasing the efficiency of coordination of ensembles of dynamic objects during their mission’s execution process. Important conditions for the implementation of scenario-case method are to ensure sufficient competence that allows to find appropriate case and choose an adequate set of scenarios in time, and to synchronize each dynamic object’s case base in time and content.


Keywords


dynamic object; situational disturbance; coordination; case; scenario; control action; prototype; constraint; adaptation

References


Sherstyuk, V. G. (2015). Case inference model in the «Monsoon» intelligent system. Artificial Intelligence, 1-2, 103-111.

Ros, R., López De Màntaras R., Sierra C., & Arcos J. L. (2005). A CBR system for autonomous robot navigation. Proceedings of the 2005 Conf. on Artificial Intelligence Research and Development, 131, 299-306. Netherlands: IOS Press Amsterdam.

Ben-Asher, Y., Feldman S., Gurl P., & Feldman M. (2008). Distributed Decision and Control for Cooperative UAVs using Ad-Hoc Communication. IEEE Transactions on Control Systems Technology, 16(3), 511-516. doi: 10.1109/tcst.2007.906314

Jadbabaie, A., Lin, J., & Morse, A. (2003). Coordination of groups of mobile autonomous agents using nearest neighbor rules. IEEE Transactions on Automatic Control, 48(6), 988-1001.

Jaidee, U., Muñoz-Avila H., & Aha, D. W. (ICCBR 2013). Case-Based Goal-Driven Coordination of Multiple Learning Agents. Lecture Notes in Computer Science: Case-Based Reasoning Research and Development, 7969, 164-178. doi: 10.1007/978-3-642-39056-2_12

Lawton, J. R. T., Beard, R. W., & Young, B. J. (2003). A decentralized approach to formation maneuvers. IEEE Transactions on Robotics and Automation, 19(6), 933-941. doi: 10.1109/tra.2003.819598

Mataric, M. J. (1995). Designing and Understanding Adaptive Group Behaviors. Adaptive Behavior, 4(1), 51-80. doi: 10.1177/105971239500400104

Michael, N., & Kumar, V. (2011). Control of Ensembles of Aerial Robots. Proceedings of the IEEE, 99(9), 1587-1602. doi: 10.1109/jproc.2011.2157275

Patlasov, O. M., & Tokariev, S. O. (2015). The measurement methodology improvement of the horizontal irregularities in plan. Science and Transport Progress, 4(58), 121-129. doi 10.15802/STP2015/49219

Sherstjuk, V. G. (2015). Scenario-case coordinated control of heterogeneous ensembles of unmanned aerial vehicles. Proc. of International Conference IEEE Actual Problems of Unmanned Aerial Vehicles Developments (APUAVD), October 13-15, 2015. 275-279. doi: 10.1109/apuavd.2015.7346620

Sherstjuk, V. (2013). The case-scenario approach to control the dynamic objects. Pressing issues and priorities in development of the scientific and technological complex, 17, 97-103. CA, USA: B&M Publishing.

Toner, J., & Yuhai, T. (1998). Flocks, herds, and schools: A quantitative theory of flocking. Physical Review E, 58(4), 4828-4858. doi: 10.1103/physreve.58.4828

Tošić, P. T., & Vilalta, R. (2010). A Unified Framework for Reinforcement Learning, Co-Learning and Meta-Learning: How to Coordinate in Collaborative Multi-Agent Systems. Procedia Computer Science, 1(1), 2217-2226. doi: 10.1016/j.procs.2010.04.248

Zharikova, M., & Sherstjuk, V. (2016). Threat Assessment Method for Intelligent Disaster Decision Support System. Advances in Intelligent Systems and Computing, 512, 81-99. doi: 10.1007/978-3-319-45991-2_6


GOST Style Citations


  1. Шерстюк, В. Г. Модель вывода по прецедентам в интеллектуальной системе «Муссон» / В. Г. Шерстюк // Штучний інтелект. – 2015. – № 1/2. – С. 103–111.
  2. A CBR system for autonomous robot navigation / R. Ros, R. López De Màntaras, C. Sierra, J. L. Arcos // Proc. of the 2005 Conf. on Artificial Intelligence Research and Development. – Netherlands : IOS Press Amsterdam, 2005. – Vol. 131. – P. 299–306.
  3. Distributed Decision and Control for Cooperative UAVs using Ad-Hoc Communication / Y. Ben-Asher, S. Feldman, P. Gurl, M. Feldman // IEEE Transactions on Control Systems Technology. – 2008. – Vol. 16. – Iss. 3. – P. 511–516. doi: 10.1109/tcst.2007.906314.
  4. Jadbabaie, A. Coordination of groups of mobile autonomous agents using nearest neighbor rules / A. Jadbabaie, J. Lin, A. Morse // IEEE Transactions on Automatic Control. – 2003. – Vol. 48. – Iss. 6. – P. 988–1001. doi: 10.1109/TAC.2003.812781.
  5. Jaidee, U. Case-Based Goal-Driven Coordination of Multiple Learning Agents / U. Jaidee, H. Muñoz-Avila, D. W. Aha // Case-Based Reasoning Research and Development : Lecture Notes in Computer Science. – Berlin ; Heidelberg, 2013. – Vol. 7969. – P. 164–178. doi: 10.1007/978-3-642-39056-2_12.
  6. Lawton, J. R. T. A decentralized approach to formation maneuvers / J. R. T. Lawton, R. W. Beard, B. J. Young // IEEE Transactions on Robotics and Automation. – 2003. – Vol. 19. – Iss. 6. – P. 933–941. doi: 10.1109/tra.2003.819598.
  7. Mataric, M. J. Designing and Understanding Adaptive Group Behaviors / M. J. Mataric // Adaptive Behavior. – 1995. – Vol. 4. – Iss. 1. – P. 51–80. doi: 10.1177/105971239500400104.
  8. Michael, N. Control of Ensembles of Aerial Robots / N. Michael, V. Kumar // Proc. of the IEEE. – 2011. – Vol. 99. – Iss. 9. – P. 1587–1602. doi: 10.1109/jproc.2011.2157275.
  9. Patlasov, O. M. The measurement methodology improvement of the horizontal irregularities in plan / O. M. Patlasov, S. O. Tokariev // Наука та прогрес транспорту. – 2015. – № 4 (58). – С. 121–129. doi: 10.15802/STP2015/49219.
  10. Sherstjuk, V. G. Scenario-Case Coordinated Control of Heterogeneous Ensembles of Unmanned Aerial Vehicles / V. G. Sherstjuk // Actual Problems of Unmanned Aerial Vehicles Developments (APUAVD) : Proc. of 2015 IEEE 3rd Int. Conf. (13.10–15.10.2015). – Kyiv, Ukraine, 2015. – P. 275–279. doi: 10.1109/apuavd.2015.7346620.
  11. Sherstjuk, V. The case-scenario approach to control the dynamic objects / V. Sherstjuk // Pressing Issues and Priorities in Development of the Scientific and Technological Complex : Proc. of the Conf. – San Francisco, California (USA), 2013. – Vol. 17. – P. 97–103.
  12. Toner, J. Flocks, herds, and schools: A quantitative theory of flocking / J. Toner, T. Yuhai // Physical Review E. – 1998. – Vol. 58. – Iss. 4. – P. 4828–4858. doi: 10.1103/physreve.58.4828.
  13. Tošić, P. T. A Unified Framework for Reinforcement Learning, Co-Learning and Meta-Learning: How to Coordinate in Collaborative Multi-Agent Systems / P. T. Tošić, R. Vilalta // Procedia Computer Science. – 2010. – Vol. 1. – Iss. 1. – P. 2217–2226. doi: 10.1016/j.procs.2010.04.248.
  14. Zharikova, M. Threat Assessment Method for Intelligent Disaster Decision Support System / M. Zharikova, V. Sherstjuk // Advances in Intelligent Systems and Computing. – Berlin, 2016. – Vol. 512. – P. 81–99. doi: 10.1007/978-3-319-45991-2_6.


DOI: http://dx.doi.org/10.15802/stp2017/100087

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

 

ISSN 2307–3489 (Print)
ІSSN 2307–6666 (Online)