An Approach to Scene Recognition Based on the Local Interaction of a Group of Robots

The paper considers a group of animates (bio-inspired abstract models or technical devices) that use the visual analyzer described by the authors earlier. The visual analyzer recognizes the scene observed by the animat, determines the class of the situation and selects the corresponding behavior. The analyzer is based on the" language of poses" , borrowed from some species of ants, which allows them to visually inform other individuals of their condition. The first proposed algorithm describes a visual memory mechanism that allows an animat to remember seen objects for some time and select its behavior in a more stable way compared to a basic visual analyzer. The second algorithm describes a group recognition approach. Robots are able to exchange information about the scene they are observing presented in the form of a graph using local communication. The robot, receiving such information from its neighbors, is able to expand its picture of the world and more correctly choose its behavior based on the recognized situation than if it only had its own data. A demonstration task was set to test the efficiency, approximately simulating a colony of ants that gather food in a certain area. Colony, nest, food, and enemy individuals are modeled in the developed simulation environment. Group efficiency was defined as the amount of food collected over the allotted time period. Animates using the visual memory algorithm showed an increase in efficiency for all the studied memory parameters. Moreover, the dependence is not monotonic, and there is a certain value at which maximum efficiency is achieved. The use of the group recognition algorithm also showed an increase in efficiency compared to the basic visual analyzer. The experiments were carried out for different distances of local interaction. As with memory, there is a value of interaction distance at which the maximum efficiency is achieved. The combination of both algorithms also has interesting results. The experiments showed that the smaller the memory of the robot, the greater the increase in efficiency from using the collective recognition algorithm.

collective recognition, a group of robots, animat, visual analyzer, scene analysis, local communication

1. Sankaranarayanan A. C., Veeraraghavan A., Chellappa R. Object detection, tracking and recognition for multiple smart cameras, Proc. IEEE, 2008, vol. 96, no. 10, pp. 1606—1624.

2. Zervos M. Multi-Camera Face Detection and Recognition Applied to People Tracking, Sch. Comput. Commun. Sci. Ec. Polytech. Fédérale Lausanne, 2013, January.

3. Yamashita A. et al. Human tracking with multiple cameras based on face detection and mean shift, 2011 IEEE Int. Conf. Robot. Biomimetics, ROBIO 2011, 2011, pp. 1664—1671.

4. Harguess J., Hu C., Aggarwal J. K. Fusing face recognition from multiple cameras, 2009 Work. Appl. Comput. Vision, WACV 2009, 2009.

5. An L., Kafai M., Bhanu B. Face recognition in multicamera surveillance videos using dynamic Bayesian network, 2012 6th Int. Conf. Distrib. Smart Cameras, ICDSC 2012, 2012.

6. Karpov V. E., Karpova I. P., Kulinich A. A. Social community robots, Moscow, URSS, 2019, 352 p.

7. SwarmRobot. The official website of the project SwarmRobot, 2016, available at: http://www.swarm-bots.org (accessed: 03.03.2020).

8. Kernbach S. Handbook Of Collective Robotics, Handbook of Collective Robotics — Fundamentals and Challenges, 2013, vol. 2, no. 2000, pp. 978—981.

9. Giusti A. et al. Cooperative sensing and recognition by a swarm of mobile robots, IEEE Int. Conf. Intell. Robot. Syst., 2012, pp. 551—558.

10. Stegagno P., Massidda C., Bülthoff H. H. Object Recognition in Swarm Systems: Preliminary Results, Workshop on the Centrality of Decentralization in Multi-Robot Systems: Holy Grail or False Idol? (IEEE ICRA 2014), 2014, pp. 1—3.

11. Maghami M., Koval M. C., Georgiopoulos M., Rubinoff A. E. A Social Network Analysis for Automatic Target Recognition in Swarm Robotics, International Conference on Robotics and Automation 2010 (ICRA 2010), 2010.

12. Moskovsky A. D., Burgov E. V., Ovsyannikova E. E. Visual analyzer of the animat as a semantic basis of robot sensoric system, Mekhatronika, Avtomatizatsiya, Upravlenie, 2018, vol. 19, no. 5, pp. 336—345 (in Russian).

13. Meyer J. A., Wilson S. Simulation of Adaptive Behavior: from Animals to Animats, Cambridge, MA, MIT Press, 1991.

14. Zaharov A. A. Ants of forest communities, their life and role in the forest, Мoscow, Tovarishhestvo nauchnyh izdanij KMK, 2015, 404 p. (in Russian).

15. Forel A. The social world of ants, Bradford, 1928.

16. Topoff H. An ant nest hat facilitates removing at all stages at development, Ann. Entomol. Soc. Amer., 1975, vol. 68, no. 1, pp. 182—183.

17. Reznikiva J. I. Interspecific relationships in ants, Novosibirsk, Nauka, 1983, 208 p. (in Russian).

18. Burgov E. V. Multi-species association of anthills: transition from incomplete to full association, Zoologicheskij zhurnal, 2015, vol. 94, no. 10, pp. 1200—1210 (in Russian)..

19. Cammaerts M.-C. Colour vision in the ant Myrmica sabuleti MEINERT, 1861 (Hymenoptera: Formicidae), Myrmecological News. Österreichische Gesellschaft f ür Entomofaunistik, 2007, vol. 10, pp. 41—50.

20. Cammaerts M.-C. et al. Use of olfactory and visual cues for orientation by the ant Myrmica ruginodis (Hymenoptera: Formicidae), Myrmecological News. Österreichische Gesellschaft f ür Entomofaunistik, 2012, vol. 16, pp. 45—55.

21. Hölldobler B. Multimodal signals in ant communication, J. Comp. Physiol. A., 1999, vol. 184, pp. 129—141.

22. Fedoseeva E. B. A technological approach to the description of group foraging of ants Myrmica rubra, Zool. Journal, 2015, vol. 94, no. 10, pp. 1163—1178 (in Russian).

23. Dlusskij G. M. Formica ants, Moscow, Nauka, 1967, 233 p. (in Russian).

24. Moskovsky A. D. Graphs as a tool for solving the problem of scene recognition, Fourth All-Russian Scientific and Practical Seminar " Unmanned vehicles with elements of artificial intelligence" (UBS-AI-2017), workshop proceedings, 2017, pp. 56—64 (in Russian).

25. Karpov V. E. About one scene reconstruction mechanism, VI-th International Scientific and Practical Conference "Integrated Models and Soft Computing in Artificial Intelligence" , collection of scientific papers, vol. 1, Мoscow, Fizmatlit, 2011, pp. 407—415 (in Russian).