Dynamic Obstacle Avoidance Algorithm for Mobile Robots Based on Depth Image

Abstract

This paper presents an obstacle avoidance approach based on Indoor environment depth information under dynamic environment for mobile robots.The depth information of surrounding environment is collected by a Kinectcamera and used to set a robot obstacle avoidance warning zone.When the moving obstacle enters the warning zone,the robot's obstacle avoidance direction is determined preliminary by the obstacles position,and then an improved Kalman filter algorithm is used to optimizing the avoidance path.Experiments show that this approach can overcome the potential problem of path selection,and realize the mobile robot's obstacle avoidance behavior in the dynamic environment.