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: 1.71). 09/2003; DOI: 10.1109/TIM.2003.816846
Source: IEEE Xplore

ABSTRACT 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.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents new hybrid control architecture-based interval type-2 nuro-fuzzy (IT2NF) for embedded mobile robot navigation where event-driven control is used to handle the dynamically changing of the environment. The proposed hybrid control architecture combining behavior-based reactive navigation and model-based environmental classification has been developed. Weightless neural network (WNNs) in charge of environmental classification, this strategy does not only enable the mobile robot to avoid local minimum points but also eliminates the requirement for prior detailed modeling of the environment. Then, IT2FLC based reactive behavior is utilized to perform mobile robot navigation task use environmental pattern classification. The previous study show that embedded controller on low cost microcontroller is difficult to design due to hardware and software constraints. In this paper, the hybrid control architecture uses hierarchical structure of IT2 fuzzy sets (IT2FS) to avoid the huge rule base due to the embedded platform and modular structure of WNNs to reduce the computational cost and increases processing speed of the controller. Technologies to address these limitations are integrated into hybrid controller architecture to be carried out, thus the autonomous mobile robot navigation system can be executed successfully. Flexibility and performance of the proposed control architecture is validated through experiments on the real embedded mobile robot in a variety of environmental condition. The experimental results show that, the proposed architecture-based IT2NF has dealt in real environment with uncertainties present in the changing and unstructured environments can avoid obstacles at the desired safe distance, follow the desired trajectory in smooth movement and produces minimal computational resources.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents an environment for design of interactive behaviors for social robots. Its structure consists of three levels which are: perception, decision and action. Their principles are briefly described and we detail more specifically implementation of people searching and monitoring in cluttered environments. We describe in particular the methods for people detection, state estimation and trajectory generation for interactive monitoring. We demonstrate experimentally that the designed reasoning system is able to regulate the robot behavior in complex situations. The robustness of the framework is evaluated experimentally for person following in his home space that may lead the system to lose the person detection because of occlusions and to use shortcuts.
    Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on; 01/2012
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper discusses biology-inspired artificial neural network (NN) solutions able to provide an intelligent connection of the perception to action for the real-time control of androids to be deployed in eldercare home environments.
    Medical Measurements and Applications Proceedings (MeMeA), 2013 IEEE International Symposium on; 01/2013

Full-text (2 Sources)

Available from