Human Rescue Based on Autonomous Robot KUKA YouBot with Deep Learning Approach

We report the successful integration of deep learning approach for autonomous robot KUKA YouBot navigation. The incorporation of deep learning approach was achieved thanks the environments like Open Source Computer Vision Library (OpenCV), Python and Robot Operating System (ROS)working together. The ROS with Hydro medusa distribution provides the managing of odometry, kinematics and path planning nodes in robot KUKA YouBot. The combination of all nodes by using Gazebo software offers the enough support in order to perform the simulation of the autonomous robot navigation in a human rescue task and provides the application of Deep Learning with the intention of providing autonomy in the KUKA Youbot during simulation and practical tasks. Python software lets the communication tasks taking advantage of data processing tools with the deep learning algorithms. Then, OpenCV supports the integration of the deep learning approach by using the Single Shot Detector algorithm which provides robustness in velocity and precision which mainly allows the human detection by using a trained neuronal network. The combination of OpenCV, Python and ROS software is a capable architecture for providing smart autonomous navigation capability for different applications like: social robots, human rescue, precision farming, and especially it is possible to mention the applicability in the public administration in which the robot assists in the rescue or assistance of the employees.