This paper presents a new method based on machine vision for mobile robots to detect and avoid obstacles in unknown environments. One of the challenges of mobile robots trajectory control in unknown environments is that their obstacle avoidance system to be designed robust to material and shape of the obstacle. In this research a mobile robot equipped with a camera is designed and fabricated. Also an algorithm is proposed and implemented on the robot in order to detect obstacles by image processing and to control the robot trajectory. Three color laser pointers are mounted on the robot with certain angles that emit beams to the ground at ahead of the robot. The received images from camera contain these colored points that their coordinates are determined by image processing. Then position of any possible obstacle is detected using the proposed algorithm and the robot is commanded to avoid obstacles by changing its path. These obstacles can be static or dynamic. Our experimental results show that the proposed method, with a high reliability, has the ability to detect and avoid obstacles with any shape and material whereas other similar methods had restrictions in this regard.