Animate Orientation Based on Visual Landmarks and Scene Recognition

A biologically-inspired approach to robot route following is presented. The ant of the genus Formica rufa (a red forest ant) is used as a model species. These ants actively use collective foraging, unlike many other ant species. The scout ant remembers the route to food and can transmit information about the food location to foraging ants. Foragers can independently reach this place using this data and return home. The basis of the proposed method is the memorization the way by visual landmarks and fuzzy control. The animate path description model consists of a sequence of scenes and includes compass to account for the direction. The behavior of the animate-scout is implemented using an algorithm that simulates the foraging behavior of ants. The animate-forager performs actions to reproduce the route, applying the developed set of rules. The forager behavior is based on the same principles as that of a scout. But the scout remembers the scenes, and the forager recognizes and compares the visible scene and the scene from the route description. The actions of animates are presented in the form of elementary behavioral procedures. Each behavioral procedure is implemented using a finite state machine. The experiments for solving the foraging problem were carried out using a modeling system based on the ROS framework. The simulation results confirm the effectiveness of the proposed method. The method does not require large computing power and advanced sensory capabilities from the robot. It can also be used in reconnaissance and patrol tasks.

1. Cruse H., Wehner R. No need for a cognitive map: Decentralized memory for insect navigation, PLoS Comput. Biol., 2011, vol. 7, no. 3.

2. Sun X., Yue S., Mangan M. A decentralised neural model explaining optimal integration of navigational strategies in insects, Elife, 2020, vol.9, no.7, pp. 1—30.

3. Wilson E. O. Chemical communication among workers of the fire ant Solenopsis saevissima. 1. The organization of mass foraging, Anim. Behav. 1962, vol. 10, pp. 134—147.

4. Reznikova Z. Spatial cognition in the context of foraging styles and information transfer in ants, Anim. Cogn., 2020, vol. 23, no. 6, pp. 1143—1159.

5. Dlusskiy G. M. Family Formicidae ants, Moscow, Nauka, 1967, 236 p. (in Russian).

6. Ryabko B., Reznikova Z. The Use of Ideas of Information Theory for Studying "Language" and Intelligence in Ants, Entropy, 2009, no. 11, pp. 839—853.

7. Reznikova Z. Experimental paradigms for studying cognition and communication in ants (Hymenoptera: Formicidae), Myrmecological News, 2008, vol. 11, pp. 201—214.

8. Müller M., Wehner R. Path integration in desert ants, Cataglyphis fortis, Proceedings of the National Academy of Sciences of the United States of America, 1988, pp. 5287—5290.

9. Narendra A. Homing strategies of the Australian desert ant Melophorus bagoti II. Interaction of the path integrator with visual cue information, J. Exp. Biol., 2007, vol. 210, no. 10, pp. 1804—1812.

10. Wystrach A., Graham P. What can we learn from studies of insect navigation? // Anim. Behav, 2012, vol. 84, no. 1, pp. 13—20.

11. Wehner R. The architecture of the desert ant’s navigational toolkit (Hymenoptera: Formicidae), Myrmecol News, 2009, no. 12, pp. 85—96.

12. Wystrach A. et al. Views, landmarks, and routes: How do desert ants negotiate an obstacle course? J. Comp. Physiol. A Neuroethol. Sensory, Neural, Behav. Physiol., 2011, vol. 197, no. 2, pp. 167—179.

13. Zaxarov A. A. Ant, family, colony, Moscow, Fiton XXI, 2018, 192 p. (in Russian).

14. Collet M., Collett T. S. The learning and maintenance of local vectors in desert ant navigation, J. Exp. Biol., 2009, vol. 212, pp. 895—900.

15. Lambrinos D. et al. A mobile robot employing insect strategies for navigation, Rob. Auton. Syst., 2000, vol. 30, no. 1, pp. 39—64.

16. Vardy A. Long-range visual homing, 2006 IEEE Int. Conf. Robot. Biomimetics, ROBIO 2006, pp. 220—226.

17. Yu S. E., Kim D. Image-based homing navigation with landmark arrangement matching, Inf. Sci. (Ny), 2011, vol. 181, no. 16, pp. 3427—3442.

18. Stelzer A., Mair E., Suppa M. Trail-Map: A scalable landmark data structure for biologically inspired range-free navigation, 2014 IEEE Int. Conf. Robot. Biomimetics, IEEE ROBIO 2014, pp. 2138—2145.

19. Karpova I. P. On the question of representing the route of a mobile robot based on visual landmarks, Mekhatronika, Avtomatizatsiya, Upravlenie, 2017, vol. 18, no. 2, pp. 81—89 (in Russian)

20. Wilson S. W. Classifier Systems and the Animat Problem, Mach. Learn, 1987, vol. 2, no. 3, pp. 199—228.

21. Zaxarov A. A. et al. Monitoring of Formika ants, Moscow, KMK, 2013, 99 p. (in Russian).

22. Baddeley B. et al. A model of ant route navigation driven by scene familiarity, PLoS Comput. Biol., 2012, vol. 8, no. 1.

23. Roseboom W. et al. Activity in perceptual classification networks as a basis for human subjective time perception, Nat. Commun., 2019, vol. 10, no. 1, pp. 1—10.

24. Moskovskij A. D. Navigation system of an autonomous mobile robot based on the method of scene reconstruction, II All-Russian scientific and practical seminar "Unmanned vehicles with elements of artificial intelligence" (BTS-AI-2015), Saint Petersburg, Politexnika-servis, 2015, pp. 66—73 (in Russian).

25. Karpov V. E. About one mechanism of scheme reconstruction, Proceedings of the VI International Scientific and practical Conference "Integrated models and soft computing in artificial intelligence", Moscow, Fizmatlit, 2011, vol. 1, pp. 407—415 (in Russian).

26. Karpov V. E. Private mechanisms of leadership and consciousness in a swarm robotics, Proceedings of the XIII National Conference on artificial intelligence with the international participation (CAI-2012), Publishing house of BGTU, 2012, pp. 275—283 (in Russian).

27. Narendra A. Homing strategies of the Australian desert ant Melophorus bagoti I. Proportional path-integration takes the ant half-way home, J. Exp. Biol., 2007, vol. 210, no. 10, pp. 1798—1803.

28. Dupeyroux J., Viollet S., Serres J. R. An ant-inspired celestial compass applied to autonomous outdoor robot navigation, Rob. Auton. Syst., 2019, vol. 117, pp. 40—56.

29. Karpov V. E., Rovbo M. A., Ovsyannikova E. E. A system for modeling the behavior of groups of robotic agents with elements of a social organization Quorum, Programmnye produkty i sistemy, 2018, vol. 31, no. 3, pp. 581—590 (in Russian).