Behavior-based neuro-fuzzy controller for mobile robot navigation

Sch. of Inf. Technol. & Eng., Univ. of Ottawa, Ont., Canada
IEEE Transactions on Instrumentation and Measurement (Impact Factor: 1.79). 09/2003; 52(4):1335 - 1340. DOI: 10.1109/TIM.2003.816846
Source: IEEE Xplore


This paper discusses a neuro-fuzzy controller for sensor-based mobile robot navigation in indoor environments. The control system consists of a hierarchy of robot behaviors.

    • "The mechanism for orchestrating the behaviours is called arbitration. Approaches for arbitration proposed in literature include, fuzzy (Mo et al., (2013), Seraji et al., (2002), Yang et al., (2004)), Neuro-fuzzy (Rusu et al., (2003), Li et al., (1997)) and regularization (Egerstedt et al., (1999)). Though, these methods can circumvent static obstacles successfully; the result cannot be extended to dynamic obstacles in unknown environment. "

    No preview · Article · Oct 2015 · International Journal of Heavy Vehicle Systems
  • Source
    • "Fuzzy systems provide a framework to represent imprecise information and to reason with this kind of information, while neural networks enhance fuzzy systems with the capability of learning from input-output data; learning is used to adapt parameters of the fuzzy system as membership functions or rules. Some example representative application areas of NFS are: pattern recognition [1] [2], robotics [3] [4], nonlinear system identification [5] [6], adaptive signal processing [7] [8], etc.. In addition, new potential applications can be found in the field of ubiquitous computing and ambient intelligence [9]. "

    Preview · Article · Jan 2014
  • Source
    • "In [1], a neuro-fuzzy reasoning algorithm, having the advantage of greatly reducing the number of fuzzy rules, was proposed to fulfill the navigation task of mobile robots. In [2], a behavior-based neuro-fuzzy controller for mobile robot system was addressed for the navigation problem. In this work, a neuro-fuzzy method was applied to implement the behavioral function. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper aims to investigate the formation control of multi-robot systems, where the kinematic model of a differentially driven wheeled mobile robot is considered. Based on the graph-theoretic concepts and locally distributed information, an adaptive neural fuzzy formation controller is designed with the capability of on-line learning. The learning rules of controller parameters can be derived from the analyzing of Lyapunov stability. In addition to simulations, the proposed techniques are applied to an experimental multi-robot platform for performance validations. From simulation and experimental results, the proposed adaptive neural fuzzy protocol can provide better formation responses compared to conventional consensus algorithms.
    Full-text · Article · Sep 2013 · International Journal of Fuzzy Systems
Show more