Fuzzy logic based autonomous skid steering vehicle navigation

Abstract

A two-layer fuzzy logic controller has been designed for 2-D autonomous navigation of a skid steering vehicle in an obstacle filled environment. The first layer of the fuzzy controller provides a model for multiple sonar sensor input fusion and it is composed of four individual controllers, each calculating a collision possibility in front, back, left and right directions of movement. The second layer consists of the main controller that performs real-time collision avoidance while calculating the updated course to be followed by the vehicle. The two layer controller applicability and implementation is demonstrated through experimental results and case studies performed on a real mobile robot.

Autonomous Navigation of Unmanned Vehicles: A Fuzzy Logic Perspective

“…The proposed navigation scheme was initially implemented on the Nomad 200 mobile robot platform , for indoor navigation, and later on an ATRV skid steering mobile robot manufactured by iRobot (Doitsidis, et al, 2002). The mobile robot ATRV-mini (shown in Fig.…”

“…The data used for localization and calculation of the heading were produced from an odometer. For this robot system, a two-layer Mamdani-type controller has been designed and implemented (Doitsidis, et al, 2002). In the first layer, there are four fuzzy logic controllers responsible for obstacle detection and collision possibility calculation in the four main directions, front, back, left, right.…”

“…The fuzzy logic controller is implemented as a Mamdani-type controller similar to previous work Doitsidis, et al, 2002). The fuzzy logic controller rule base includes the fuzzy rules responsible for vehicle control.…”

“…Considering the environment uncertainty that is difficult if not impossible to model, fuzzy logic is one of the most widely used mathematical tools for autonomous vehicle navigation (Driankov & Saffiotti, 2001). Fuzzy logic techniques have already been used and are being used currently for autonomous navigation of ground (indoors (Aguire & Gonzalez, 2000;Doitsidis, et al, 2002;Goodridge & Luo, 1994;Ishikawa, 1991;Li, 1994;Oriolo, et al, 1998;Pin & Watanabe, 1994;Tsourveloudis, et al, 2001;Tunstel, 1996) and outdoors (Hagras, et al, 2001;Seraji & Howard, 2002;Valavanis, et al, 2005), aerial (fixed (Doitsidis, et al, 2004;Nikolos, et al, 2003a) and rotary wings (Amaral, 2001;Hoffmann, et al, 1999;Kadmiry & Driankov, 2001;Kadmiry & Driankov, 2004;Sugeno, 1999) and water (surface (Vanick, 1997) or submersible (Kanakakis, et al, 2004;Kanakakis, et al, 2001)) robotic vehicles. The wide applicability of fuzzy logic in autonomous navigation is mainly based on suitable knowledge representation of inherently vague notions achieved through fuzzy IF-THEN rules.…”

Incorporation of MATLAB into a distributed behavioral robotics architecture

“…This paper is motivated by the challenge to provide a platform to support advanced robot control research both at the AI level [1] and at the control-theoretic level [17]. The architecture, referred to in this paper as Distributed SFX, supports the implementation of large scale complex behavior-based robot control but still provides tools for low level experimental research within a single structured paradigm [5] [10].…”