BEHAVIOR FUSION FOR ROBOT NAVIGATION IN UNCERTAIN ENVIRONMENTS USING FUZZY LOGIC Wei Li Xun Feng National Laboratory of Intelligent Technology and Systems, Department of Computer Science, Tsinghua University, Beijing (1 00084), China ABSTRACT zyxwvutsrqpo A key problem in behavior based control is to coordinate conflicts and competitions among multiple reactive behaviors. This paper presents a new method for behavior fusion for robot navigation in uncertain environments using fuzzy logic. The inputs to the proposed fuzzy control scheme consist of a heading angle between a robot and a specified target and the distances between the robot and the obstacles to the left, front, and right locations, acquired by an array of ultrasonic sensors. The outputs from the control scheme are commands for the speed control unit of two rear wheels of the mobile robot. The simulation results show that the proposed method, only using range information acquired by ultrasonic sensors, can be efficiently applied to robot navigation in complex and uncertain environments. 1 INTRODUCTION On the basis of the stimulus-response behavior in bio- system, behavior based control zyxwvutsr [ 11 [2][3] has been proposed for robot navigation in unknown environments since this method does not need building an entire world model and complex reasoning process. A key issue in behavior-based control, however, is how to coordinate conflicts and competitions among multiple reactive behaviors efficiently. In [l], the coordination of multiple behaviors is done by inhibiting those reactive behaviors with lower levels. However, this strategy is not very efficient for robot navigation when a mobile robot executes tasks in complex environments. The example in Fig.1 shows that the robot must efficiently weight multiple reactive behaviors, such as avoiding obstacle, following edge, and moving to the target and so on, according to range information, when it reaches a specified target. This paper presents a new method for behavior fusion for robot navigation using fuzzy logic [4][5][6]. The main idea of this method is to weight multiple reactive behaviors in dynamic environments by a fuzzy logic algorithm rather than simply to inhibit some reactive behaviors according their priority. This method also differs from the fuzzy control approaches for obstacle avoidance in [7][8][9] since perception and decision units in this method are integrated in one module and are directly oriented to dynamic environments to improve real-time response and reliability. To demonstrate the effectiveness and the robustness of the proposed method, we report simulation results on robot navigation in uncertain environments, such as moving obstacle avoidance in real-time, decelerating at curved and namw road, escaping from a U-shaped object and moving to target and so on. Fig. 1: Robot motion to a target by behavior fusion using fi1zzy logic 2 BEHAVIOR-BASED CONTROL USING ARTIFICIAL POTENTIAL FIELDS The usual approach for implementing behavior-based control is artificial potential fields [ 101 [ 1 11 1121. In combination with artificial potential fields, an inhibiting and suppressing strategy in [l] is used to fire a bchavior. In our experiment, some deficiencies of this strategy are noted as follows: 1. Much effort must be made to test and to adjust some parameters of potential fields and thresholds for firing reactive behaviors during preprogramming. 2. Robot motion with unstable oscillations between different behaviors may occur in some cases. This is 0-7803-2129-4194 $3.00 zyxwv 0 1994 zyxwv IEEE