A Modified Dynamic Window Approach to Obstacle Avoidance Combined with Fuzzy Logic

Abstract

As a classic reactive method for obstacles avoidance, the dynamic window approach (DWA) uses an objective function to choose the optimal velocity commands. The objective function consists of three weighted terms, respectively urging the robot to face to the target point, avoid crash and move fast. The environment where robot works is usually complex and changeable, and different situations need different weights. However, the original DWA and its extensions use constant weights, and there is no existing algorithm for changing them. In this paper, we propose a modified DWA combined with fuzzy logic. This can be done by analyzing the information about goal and obstacles, and then using fuzzy logic to decide suitable weights in real time. In contrast with the original DWA, the proposed method makes robot move more safely and smoothly.