Unmanned Aircraft Systems (UASs) for Civilian and Public Domain Applications: Challenges and the role of AI
Advances in unmanned aviation have reached unprecedented levels within a very short period. Technology has matured to the level that makes design, development, prototyping, testing, and subsequently commercialization of unmanned aerial robotic platforms easier and less challenging compared to ten - twenty years ago. Regardless of the name one may use for such platforms, i.e., UAV, UAS, RPAS, the truth is that the explosion of computational power, AI, data analytics and data mining, as well as the ability to implement in (almost hard) real-time learning techniques, have made modeling and sensor-based navigation and control of unmanned aerial vehicles more effective and more accurate. Consequently, current research and development now allows for mathematical models to include a model-based and a data-driven component, the latter being updated as the vehicle functions, which, in turn, allows for better controller designs and for enhanced performance.
Additional current advances in the field include major cost reduction and miniaturization of the essential on-board components (sensors, batteries, motors, processors, cameras, etc.) needed to ‘assemble’ and ‘integrate’ the overall vehicle. Thus, unmanned aerial robotic platforms of any size, weight and type can now be manufactured and subsequently used for a wide range of civilian and public domain applications.
A recent research direction centers on ‘the role of AI in the cockpit of UAVs’ (or UAS, RPAS). Although it is natural to consider that this basically refers to ‘larger’ UASs, which are and will be suitable for military applications, the same technology is also applicable to all types and classes of UASs used for commercial applications. A common challenge to both, is autonomy, or the level of autonomy, or autonomous functionality of the vehicle itself. Stated differently, the challenge is to know how and when to shift delegation of authority for decision making from the human operator to the machine. The answer is debatable; it has been debated for years, it is being discussed today, and the prediction is that it will continue in at least the near future. Progress in technology and AI will continue, which means that at some point we will be able to build fully autonomous unmanned vehicles that will operate in completely unknown environments – this is not science fiction, it is reality. And this ‘new reality’ brings AI at center-stage of any new development.
Moreover, this new reality dictates that ethical AI and robot ethics be considered very seriously. A new ‘policy making framework’ may also be required, and fast, to ‘regulate’ and provide for ‘checks and balances’ when it comes to implementing and using such technology in everyday applications – just see what Amazon and Google do! I have repeatedly stated that standards are needed alongside regulations, ethical, privacy and legal frameworks that allow for unmanned aviation (and robotics in general) to be part of everyday life and perhaps improve quality and safety of life.
I conclude by repeating that we, as a global society, are far from establishing a common ground. Steps to address all the above non-technology related challenges have started. But we need to think outside the box and put humankind first. Any decisions (to be made by humans for the time being) must be human-centric, not robot-centric.
The Journal of Intelligent and Robotic Systems devotes a special section on unmanned systems in each issue. Our recent efforts focus on publishing original, per reviewed, papers that deal with regulation, policy, ethical and legal issues related to unmanned aviation. By doing so, we believe we provide a valuable service to our readers and to the technical community at large.
Prof. Kimon P. Valavanis is John Evans Professor, Director, Research and Innovation, and Director of the Unmanned Systems Research Institute, D. F. Ritchie School of Engineering and Computer Science, University of Denver. His research interests span Unmanned Systems, Distributed Intelligence Systems, Robotics and Automation. He has published over 400 book chapters, journal/transaction papers, and referred conference papers; he has co-authored and edited 19 books, including the Handbook on UAVs (5 Volumes), Springer, the 2nd Edition of which is forthcoming in 2019. Dr. Valavanis served as Editor-in-Chief of the Robotics and Automation Magazine from 1996-2005, and since 2006, he has been Editor-in-Chief of the Journal of Intelligent and Robotic Systems, Springer. He serves as co-chair/chair of the Aerial Robotics and Unmanned Aerial Vehicles Technical Committee since 2008. He founded/launched the International Conference on Unmanned Aircraft Systems, which he runs annually. He was Distinguished Speaker in the IEEE Robotics and Automation Society, he is Fellow of the American Association for the Advancement of Science, Fellow of the U.K Institute of Measurement and Control, Senior Member of IEEE, VP of the Mediterranean Control Association (MCA), and Fulbright Scholar.