Abstract
A type of topological approach to mobile robot navigation is discussed and experimentally evaluated. The environment as experienced by a moving robot is treated as a dynamical system. Simple types of reactive behavior are supplemented with eventual decisions to switch between them. When switching criteria are defined, the system may be described in the form similar to a finite state machine. Since it is embedded in the environment and dependent on the sensory flow of the robot, we introduce the term “Embedded flow state machine” (EFSM). We implemented it with a recurrent neural network, trained on a sequence of sensory contents and actions. One of the main virtues of this approach is that no explicit localization is required, since the recurrent neural network holds the state implicitly. The EFSM is applicable to multi-step prediction of sensory information and the travelled distances between decision points, given a sequence of decisions at decision points. Thus, the optimal path to a specified goal can be sought. One of the main issues is, for how many steps ahead the prediction is reliable enough. In other words, is it feasible to perform environment modelling and path planning in this manner? The approach is tested on a miniature mobile robot, equipped with proximity sensors and a color video camera. Decision ‘points,’ where deviations from the wall-following behavior are allowed, are based on color object recognition. In the case of an experimental environment of medium complexity, this approach was successful.
Similar content being viewed by others
References
Breitenberg, V.: Vehicles: Experiments in Synthetic Psychology. MIT, Cambridge, MA (1984)
Cleeremans, A., Servan-Schreiber, D., McClelland, J.: Finite state automata and simple recurrent networks. Neural Comput. 1(3), 372–381 (1989)
Gabrijel, I., Dobnikar, A.: On-line identification and reconstruction of finite automata with generalized recurrent neural networks. Neural Netw. 16(1), 101–120 (2003)
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2, 359–366 (1989)
Mondada, F., Franzi, E., Ienne, P.: Mobile robot miniaturisation: A tool for investigation in control algorithms. In: Yoshikawa, T., Miyazaki, F. (eds.) Proceedings of the Third International Symposium on Experimental Robotics, Kyoto, Japan, October 1993
Lotrič, U., Dobnikar, A.: Predicting time series using neural networks with wavelet-based denoising layers. Neural Comp. Appl. 14(1), 11–17 (2005)
Mataric, M.J.: Integration of representation into goal-driven behavior-based robots. IEEE Trans. Robot. Autom. 8(3), 304–312 (1992)
Omlin, C.W., Giles, C.L.: Constructing deterministic finite-state automata in recurrent neural networks. J.ACM 43(6), 937–972 (1996)
Šter, B.: An integrated learning approach to environment modelling in mobile robot navigation. Neurocomputing 57, 215–238 (2004)
Tani, J.: Model-based learning for mobile robot navigation from the dynamical systems perspective. IEEE Trans. Syst. Man Cybern., Part B, Cybern. 26(3), 421–436 (1996)
Williams, R.J., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural Comput. 1, 270–280 (1989)
Author information
Authors and Affiliations
Corresponding author
Additional information
Categories (3), (5).
Rights and permissions
About this article
Cite this article
Šter, B., Dobnikar, A. Modelling the Environment of a Mobile Robot with the Embedded Flow State Machine. J Intell Robot Syst 46, 181–199 (2006). https://doi.org/10.1007/s10846-006-9059-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10846-006-9059-z