Intelligent robotic navigation

Abstract

One interesting Speaker, Mr. Gonzalo Ferrer – SKOLTECH [5] mentioned that robot barely perceive the world, which is formidably complex and process this limited data to plan their motions. And one can also argue that on simple scenarios, the task of navigating is completely solved. Nonetheless, full autonomy in robotics has not arrived yet.

In his talk, he presented an overview on robot navigation on dynamic environments. Under the interaction with pedestrians, complex situations arise where known path planning techniques provide poor solutions. He presented a new prediction approach on human motion and how to integrate it under the same planning scheme, obtaining a more intelligent robot motion behaviour. Some degree of uncertainty is unavoidable, due to the unpredictable nature of pedestrians, making impossible a perfect accuracy on prediction.

And in this project, the objective is to create the functionality test robotic navigation using TURTLEBOT3. The inbuilt-ROS TurtleBot3 robot can accommodate to the complex manoeuvre applications and test it on a navigational system. A real-time imaging camera will be installed on the robot to further enhance the capabilities of the robot. In addition, ultra sonic sensor and Raspberry-pi camera are used for obstacle avoidance and real-time imaging detection respectively. This helps to prevent collision because the sensor and camera can detect the distance and provide the robot ample time to react and re-manoeuvre its course.