High performance embedding environment for reacting suddenly appeared road obstacles

Abstract

We present a high performance embedding environment for developing vision based vehicle/ robot controlling. This particular environment is consisted of two main parts as recognition part and control part. Former can conducts vision based recognition targets such as obstacle detection while latter can controls the vehicle/robot in real time following the recognition information. The tests were conducted to confirm the performance of the proposed embedding environment, installing it on a wheel robot. Here, the test was conduct to stop the moving robot when an obstacle appeared suddenly. In the experiments, system could conduct obstacle detection as well as motor controlling effectively in order to stop the robot.