A behavior-based approach for collision avoidance of mobile robots in unknown and dynamic environments

  • Authors:

  • D. Nakhaeinia;B. Karasfi

  • Affiliations:

  • Department of Computer Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran;Department of Computer Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran

  • Venue:
  • Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology - Computational intelligence models for image processing and information reasoning
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper introduces a new behavior-based collision avoidance approach for mobile robot navigation in unknown and dynamic environments, which called Nearest Virtual-Target NVT. The NVT approach was developed based on a modeling-planning-reaction configuration. In modeling module, sensory information is integrated to construct a local model of environment which represents obstacles distribution and free obstacle areas in a part of robot's work space. The planning module uses the “actual-virtual target switching strategy” to compute obstacle free paths towards the target. The robot motion generation is handled by the reaction module. The reaction module applies a fuzzy controller to control the robot's rotational and translational velocities. The contribution of this approach is solving navigation difficulties presented in previous approaches for successful motion of the robot towards the target in troublesome scenarios such as narrow passages, very dense, cluttered and dynamic environments. Feasibility and effectiveness of the proposed approach are verified through simulation and real robot experiments. Eventually, advantages and limitations of this approach are discussed.