Application of Models of Probabilistic Situations regarding Railways

The article describes application of models of information probabilistic situations for solving problems of traffic control on the railway. The content of situational control is revealed. The difference between a visual and a «blind» situation during vehicle’s movement is shown.

The information situation around a moving object can be deterministic and stochastic. The concept of a stochastic information control situation is introduced. The choice of alternatives in stochastic control situations is characterized by organizational, technological, and informational uncertainties.

This motivates development of control methods and algorithms that consider uncertainty and multicriteria in control of moving objects in such situations. Situational control can be used in automated, cyber-physical and intelligent control.

The article proposes a model for controlling mobile objects based on a probabilistic approach in a stochastic situation and on the consideration of a number of stochastic factors. The model is based on calculating the probability of existence of an obstacle in the path of a vehicle. Such a model can be used under the conditions of poor visibility and a probability of receiving erroneous information from sensors. The article gives a systematics of the probabilistic characteristics of a stochastic information situation accompanying a moving object. The application of dichotomous and oppositional analysis in studying obstacles on the route has been substantiated. The model for detecting a foreign object on a traffic route is based on the assumption of the presence of reliable and erroneous information. The analysis is based on Dempster–Schafer theory. The stochastic information situation model uses the probabilistic characteristics of the presence of an obstacle on the track. The probability of an object’s existence is estimated using Bayes’ theorem. The proposed model considers three factors of the stochastic situation: informational uncertainty in the signal; false signals, sensor measurement error. The field of application of this situational model comprises digital railway, intelligent transport systems, transport cyber-physical systems.

1. Lyovin, B. A., Tsvetkov, V. Ya. Object and situational models in transport management [Ob’ektnie i situatsionnie modeli pri upravlenii transportom]. Nauka i tekhnologii zheleznykh dorog, 2017, Iss. 2 (2), pp. 2–10. [Electronic resource]: http://www.vniias.ru/images/img/online_journal/pdf/02_2017/06_2017.pdf. Last accessed 11.05.2020.

2. Titov, E. K. Information situational management [Informatsionnoe situatsionnoe upravlenie]. Gosudarstvenniy sovetnik, 2019, Iss. 1 (25), pp. 51–56. [Electronic resource]: https://cyberleninka.ru/article/n/informatsionnoe-situatsionnoe-upravlenie/pdf. Last accessed 11.05.2020.

3. Lyovin, B. A., Tsetkov, V. Ya. Cybernetics and Physical Systems for Transport Management. World of Transport and Transportation, 2018, Vol. 16, Iss. 2 (75), pp. 138–145. [Electronic resource]: https://mirtr.elpub.ru/jour/article/viewFile/1441/1717. Last accessed 11.05.2020.

4. Kovalenko, N. I. Knowledge extraction for intelligent transport systems [Izvlechenie znanii dlya intellektualnykh transportnykh system]. Perspektivy nauki i obrazovaniya, 2014, Iss. 5, pp. 45–52. [Electronic resource]: https://cyberleninka.ru/article/n/izvlechenie-znaniy-dlya-intellektualnyh-transportnyh-sistem/pdf. Last accessed 11.05.2020.

5. Tsvetkov, V. Ya. Information Situation and Information Position as a Management Tool. European researcher. Series A, 2012, Vol. 36, Iss. 12–1, pp. 2166–2170. [Electronic resource]: http://docplayer.ru/25906936-Information-situation-and-information-position-as-a-management-tool-viktor-ya-tsvetkov.html. Last accessed 11.05.2020.

6. Pavlovsky, A. A., Okhotnikov, A. L. Information transport situation [Informatsionnaya transportnaya situatsiya]. Nauka i tekhnologii zheleznykh dorog, 2018, Iss. 2 (6), pp. 16–24. [Electronic resource]: http://www.vniias.ru/images/img/online_journal/pdf/02_2018/2_2018.pdf. Last accessed 11.05.2020.

7. Pavlovsky, A. A. Formal interpretation [Formalnaya intepretatsiya]. Perspektivy nauki i obrazovaniya, 2017, Iss. 4 (28), pp. 18–22. [Electronic resource]: https://www.elibrary_29904637_56184823.pdf. Last accessed 11.05.2020.

8. Tsvetkov, V. Ya. Integrated Control of High Speed Railway. World of Transport and Transportation, 2013, Vol. 11, Iss. 5 (49), pp. 6–9. [Electronic resource]: https://mirtr.elpub.ru/jour/article/view/441. Last accessed 11.05.2020.

9. Okhotnikov, A. L. Application of Dempster–Schafer theory for optimization of transportation [Primenenie teorii Dempstera–Shafera dlya optimizatsii perevozok]. Nauka i tekhnologii zheleznykh dorog, 2018, Iss. 4 (8), pp. 61–74. [Electronic resource]: http://www.vniias.ru/images/img/online_journal/pdf/01_2019/01_2019.pdf. Last accessed 11.05.2020.

10. Musicki, D., Evans, R. Joint Integrated Probabilistic Data Association: JIPDA. IEEE Transactions on Aerospace and Electronic Systems, Vol. 40, No. 3, pp. 1094–1099, July 2004. DOI: 10.1109/TAES.2004.133748.

11. Mahlisch, M., Ritter, W., Dietmayer, K. De-cluttering with Integrated Probabilistic Data Association for Multisensor Multitarget ACC Vehicle Tracking. IEEE Intelligent Vehicles Symposium, Istanbul, Turkey, June 2007, pp. 178–183. DOI: 10.1109/IVS.2007.4290111.

12. Munz, M., Maehlisch, M., Dickmann, J., Dietmayer, K. Probabilistic Modeling of Sensor Properties in Generic Fusion Systems for Modern Driver Assistance Systems. IEEE Intelligent Vehicles Symposium, San Diego (CA), USA, June 2010, pp. 760–765. DOI: 10.1109/IVS.2010.554804.

13. Kudzh, S. A., Tsvetkov, V. Ya. Logic and algorithms: Monograph [Logika i algoritmy: Monografiya]. Moscow, MAKS Press, 2019, 112 p.

14. Wenbo, He; Hoang, Nguyen; Xue, Liu; Nahrstedt, K.; Abdelzaher, T. iPDA: An integrity-protecting private data aggregation scheme for wireless sensor networks. MILCOM 2008–2008 IEEE Military Communications Conference. IEEE, 2008, pp. 1–7. [Electronic resource]: https://www.ideals.illinois.edu/bitstream/handle/2142/11413/iPDA%20An%20Integrity-Protecting%20Private%20Data%20Aggregation%20Scheme%20for%20Wireless%20Sensor%20Networks.pdf?sequence=2&isAllowed=y. Last accessed 11.05.2020.

15. Musicki, D., Evans, R. Joint integrated probabilistic data association: JIPDA. IEEE transactions on Aerospace and Electronic Systems, 2004, Vol. 40, Iss. 3, pp. 1093–1099. DOI: 10.1109/TAES. 2004.133748.

16. Ba-Ngu, Vo; Wing-Kin, Ma. The Gaussian mixture probability hypothesis density filter. IEEE Transactions on signal processing, 2006. Vol. 54, Iss. 11, pp. 4091–4104. DOI: 10.1109/TSP.2006.881190/

17. Okhotnikov, A. L., Dzyuba, Yu. V. Soft situational control [Myagkoe situatsionnoe upravlenie]. In: Intelligent control systems for railway transport. Computer and mathematical modeling (ISUZHT‑2018). Proceedings of the seventh scientific and technical conference, 2018, pp. 62–64. [Electronic resource]: https://www.elibrary_36916645_17254769.pdf. Last accessed 11.05.2020.

18. Aeberhard, M., Paul, S., Kaempchen, N., Bertram, T. Object Existence Probability Fusion using Dempster–Shafer Theory in a High-Level Sensor Data Fusion Architecture. IEEE Intelligent Vehicles Symposium, Baden-Baden, Germany, June 2011, pp. 770–775. DOI: 10.1109/IVS.2011.594043.

19. Gospodinov, S. G. Probabilistic logical analysis [Veroyatnostno logicheskiy analiz]. ITNOU: Information technologies in science, education and management, 2019, Iss. 1, pp. 3–8. [Electronic resource]: http://www.vniias.ru/images/img/online_journal/pdf/03_2019/03_2019.pdf. Last accessed 11.05.2020.