Elsevier

Fuzzy Sets and Systems

Volume 107, Issue 1, 1 October 1999, Pages 1-24
Fuzzy Sets and Systems

Uncertainty representation for mobile robots: Perception, modeling and navigation in unknown environments

https://doi.org/10.1016/S0165-0114(97)00321-7Get rights and content

Abstract

We present a fuzzy-sets based approach to the problem of mobile robot navigation in unknown environments. Fuzzy sets are used to represent the uncertainty that is inherent to the perception of the environment through the robot sensors. This uncertainty is then propagated in the process of map building so that not only a plausible spatial layout of the environment, but also the confidence on this layout, is obtained. The initial map built by the robot is then used for self-localization as it continues navigating in the same environment. The new information collected by the sensors is matched to the initial map and the transformation that brings them together is used to correct and bound the dead-reckoning errors. Uncertainty representation is a key aspect of this process since it allows to immediately detect pairs of coincident boundaries, thus, permitting real-time self-localization. The approach is illustrated by experiments in office environments.

References (26)

  • J. Gasós et al.

    Using imprecise environment information for guiding scene interpretation

    Fuzzy Sets and Systems

    (1997)
  • M. Poloni et al.

    Fuzzy logic and autonomous vehicles: experiments in ultrasonic vision

    Fuzzy Sets and Systems

    (1995)
  • J. Borenstein et al.

    Real-time obstacle avoidance for fast mobile robots

    IEEE Trans. Systems Man Cybernet.

    (1989)
  • J. Borenstein et al.

    UMBmark - A method for measuring, comparing, and correcting dead-reckoning errors in mobile robots

  • J. Borenstein et al.

    Measurement and correction of systematic odometry errors in mobile robots

    IEEE Trans. Robotics Automat.

    (1996)
  • A. Cai et al.

    Integration of distributed sensing information in DARS based on evidential reasoning

  • A. Curran et al.

    Sensor-based self-localization for wheeled mobile robots

    J. Robotic Systems

    (1995)
  • M. Drumheller

    Mobile robot localization using sonar

    IEEE Trans. Pattern Anal. Mach. Intelligence

    (1987)
  • R. Duda et al.

    Pattern Classification and Scene Analysis

    (1973)
  • A. Elfes

    Sonar-based real-world mapping and navigation

    IEEE J. Robotics Automat.

    (1987)
  • L. Feng et al.

    Estimation of the absolute position of mobile systems by an optoelectronic processor

    IEEE Trans. Systems Man Cybernet.

    (1992)
  • J. Gasós et al.
  • P. Hebert et al.

    Decoupling odometry and exteroceptive perception in building a global world map of a mobile robot: the use of local maps

  • Cited by (51)

    • Application of probability to enhance the performance of fuzzy based mobile robot navigation

      2019, Applied Soft Computing Journal
      Citation Excerpt :

      In recent years, the FL have been used with different intelligent approaches to improve the performance of mobile robot when working in presence of dynamic uncertainty such as Neural Network [7,8], Ant Colony Algorithm [9], Genetic Algorithm [10–12], Particle Swarm Optimization [13], Potential Field Approach [14], Wind Driven Optimization [15], Tabu Search [16], Grey Wolf Optimization [17], Firefly Algorithm [18], Bee Colony Algorithm [19] and many more. Furthermore, the FL has been presented with some modification and up gradation to improve the navigational performance like Gasos et al. [20] have provided the improved approach to map building and self-localization in unknown environment; Yili et al. [21] have combined “virtual target” and “fuzzy logic” for local path planning and developed non-collision path planning using double layer fuzzy mechanism for controlling both speed and heading angle; Moustris et al. [22] have presented the switching FL controller with bounded curvature constraints for MRN; Ching [23] and Rubio et al. [24] has developed the vision guidance system based on the image processing with fuzzy to avoid obstacles while working in real environment; Mendonca et al. [25] have offered the cooperative architecture for swarm robotics based on reinforcement learning and dynamic fuzzy cognitive maps; and Petri net-fuzzy based model for self-navigation of robot have been developed and proposed by Kim et al. [26]. Numerous efforts have been provided by various researcher for solving the path planning problem over dynamic conditions and using FL alone is difficult task.

    • Fuzzy uncertainty modeling for grid based localization of mobile robots

      2010, International Journal of Approximate Reasoning
    View all citing articles on Scopus
    View full text