Simulation of collision avoidance by navigation assistance using stereo vision

In the research study the fully automated vehicles is one of the most important factor to navigate the vehicle by avoiding obstacles and to maintain specific path. The methodologies to achieve this could be researched on robots which rely on their ability to sense and interact. Laser sensors and Ultra-sonic sound sensors have been a traditional way to detect objects in the recent past but they were not efficient at close range. By using stereo vision it is possible to detect objects and their distances just like how we humans detect object and their relative distances with the eyes. The objective of the project is to develop a system where it imports data a stereo vision camera, understand the nature of the environment and to choose the right direction to get an appropriate speed for a robot to navigate.