An interconnected architecture for an emergency medical response unmanned aerial system

In the case of a medical emergency such as an out-of-hospital cardiac arrest, the chances of a person's survival decrease rapidly if they are not attended to immediately. Modern hospitals are well equipped to deal with such a situation; however, an ambulance may get stuck in traffic and it may take responders time to reach locations deep within a building. Each year between 180,000 and 400,000 people die due to cardiac arrest. However, it is possible to reduce this number. Unmanned Aerial Vehicles (UAV) have regularly been used for remote sensing and aerial imagery collection, but the technology exists to allow the use of drones to respond to medical emergencies. To ensure that drones can reach the victim and provide medical aid, a framework for reacting to emergency circumstances, is required. This paper proposes a system-of-systems-based framework that is capable of responding to one of the most acute medical emergencies, a heart attack. The proposed architecture consists of twelve systems that work in coordination to ensure that the drone can achieve safe flight and provide medical aid. An autonomous command and control system is discussed. This system also allows manual control from a remote location to perform complex work using the robotic arm. The proposed system also includes a robotic arm that uses visual feedback to assist the individual suffering from cardiac arrest. The image recognition system uses depth image sensing techniques to locate appropriate points where defibrillator pads can be administered. Before placing defibrillator pads on the person's chest, the system has to detect if the person is suffering from ventricular fibrillation. The robotic arm system supports this by performing a pre-examination using on-board sensors. On-board software, contained within the automatic external defibrillator unit, is designed to recognize if the person is suffering from ventricular fibrillation. To support autonomous flight, the path planning system uses on-board GPS to track its movement and reach its destination. Once inside a building, the system can be guided using video imagery to ensure that it reaches the desired location. It uses visible light imagery and ultrasonic sensor data to avoid obstacles in its path. The UAV's actuation system receives information from the path planning system and the command unit and controls the drone's hardware systems, which includes motors, IMU sensors for flight stability and the robotic arm. An emergency response system is incorporated to guarantee that the drone will be able to land securely in a suitable area, if it malfunctions. This system is capable of identifying the seriousness of the failure. It sends command to the drone's control unit to perform response and recovery operations. The proposed framework also considers cybersecurity needs so that it is prepared to deal with potential attackers that may attempt to access locally available route controls and reroute the UAS to satisfy unauthorized objectives. It incorporates strong encryption for passwords and other credentials, a firewall, and a limited intrusion detection system.

[1]  Lei Yan,et al.  The design and experiments of a small wheel-legged mobile robot system with two robotic arms , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[2]  Hui Liu,et al.  A new method for mobile robot arm blind grasping using ultrasonic sensors and Artificial Neural Networks , 2013, 2013 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[3]  Hui Lin,et al.  Depth image enhancement for Kinect using region growing and bilateral filter , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[4]  Jumana Abu-Khalaf,et al.  The design and analysis of a six-degree of freedom robotic arm , 2015, 2015 10th International Symposium on Mechatronics and its Applications (ISMA).

[5]  Ran Wei,et al.  Locating AED Enabled Medical Drones to Enhance Cardiac Arrest Response Times , 2016, Prehospital emergency care : official journal of the National Association of EMS Physicians and the National Association of State EMS Directors.

[6]  Marco Ceccarelli,et al.  An Optimum Design Procedure for Two-Finger Grippers: A Case of Study , 2002 .

[7]  Enrico Pagello,et al.  A mobile robot for transport applications in hospital domain with safe human detection algorithm , 2009, 2009 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[8]  J. Ornato,et al.  Improving survival from sudden cardiac arrest , 1991 .

[9]  Mikkel Rath Pedersen,et al.  Using human gestures and generic skills to instruct a mobile robot arm in a feeder filling scenario , 2012, 2012 IEEE International Conference on Mechatronics and Automation.

[10]  Lei Yang,et al.  3D depth image analysis for indoor fall detection of elderly people , 2016, Digit. Commun. Networks.

[11]  C. Albert,et al.  Epidemiology and genetics of sudden cardiac death. , 2012, Circulation.

[12]  Nazil Perveen,et al.  An Overview on Template Matching Methodologies and its Applications , 2013 .

[13]  Alivelu M. Parimi,et al.  Automation of end effector guidance of robotic arm for dental implantation using computer vision , 2016, 2016 IEEE Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER).

[14]  P. J. Wang,et al.  Improving survival from sudden cardiac arrest: the role of the automated external defibrillator. , 2001, JAMA.

[15]  Sebastian Thrun,et al.  Real-time identification and localization of body parts from depth images , 2010, 2010 IEEE International Conference on Robotics and Automation.