A New Obstacle Avoidance Method for Service Robots in Indoor Environments

摘要

\nThe objective of this paper is to propose an obstacle avoidance method for service robots in indoor environments using vision and ultrasonic sensors. For this research, the service robot was programmed to deliver a drinking cup from a specified starting point to the recognized customer. We have developed three main modules: one for face recognition, one for obstacle detection, and one for avoidance maneuvering. The obstacle avoidance system is based on an edg edetection method using information from the landmark and planned-path generation. Speed, direction and distance of the moving obstacle are measured using vision and distance sensors in order for the robot to make an avoidance maneuver. Algorithms for obstacle avoidance are proposed and a new geometric model is introduced for making good avoidance maneuvers. The main aim of this research is to provide a complete mechanism for obstacle avoidance by vision based service robots, where common obstacle avoidance methods, such as PVM, do not provide such a feature. We present the results of an experiment with a service robot in which the proposed method was implemented, after which its performance is evaluated.\n