A UAV-based Algorithm to Assist Ground SAR Teams in Finding Lost Persons Living with Dementia

Unmanned Aerial Vehicles (UAV) are now used in many applications. Our focus in this paper is on their use in public safety, specifically in search and rescue (SAR) operations involving lost persons living with dementia (LPLWD). When it comes to saving lives, there are many human factors associated with UAV operations that impact the performance of expert human SAR that could be improved through forms of automation. These include tasks associated with piloting and search/flight management during SAR operations with the assistance of analysis performed on data from similar incidents in the past. A LPLWD may not be interested in assisting in their own rescue as they may not know they are lost. As such, it has been observed that they tend to keep walking until they are faced with an obstacle that bars their further progress. Knowing this behavior allows us to make predictions. Our approach in developing a people finding algorithm is to identify higher probability locations where an LPLWD might be found through informed, behavior-based analysis of the given terrain. We develop an algorithm to fly a UAV to the vicinity of these higher probability locations. We have validated our algorithm through field testing. In this paper, we present the results from both our data collection and the field tests. In addition, validation tests are presented and compared.

[1]  Zoubin Ghahramani,et al.  An Introduction to Hidden Markov Models and Bayesian Networks , 2001, Int. J. Pattern Recognit. Artif. Intell..

[2]  José Manuel Andújar Márquez,et al.  Intelligent UAV Map Generation and Discrete Path Planning for Search and Rescue Operations , 2018, Complex..

[3]  Dianxiang Xu,et al.  A Petri Net Based Software Architecture for UAV Simulation , 2004, Software Engineering Research and Practice.

[4]  M. Rahim,et al.  A Structural Equations Model of Leaders' Social Intelligence and Creative Performance , 2014 .

[5]  Michael A. Goodrich,et al.  UAV intelligent path planning for Wilderness Search and Rescue , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[6]  David O. Wallin,et al.  Introduction to Markov Models , 2002 .

[7]  Andreas M. Kunz,et al.  Using Locomotion Models for Estimating Walking Targets in Immersive Virtual Environments , 2015, 2015 International Conference on Cyberworlds (CW).

[8]  Alexander Ferworn,et al.  POLICE LEARNING: EXAMINING THE USE OF SIMULATIONS IN POLICE TRAINING AND THE ASSOCIATED LEARNING THEORIES , 2017 .

[9]  Darius Burschka,et al.  Toward a Fully Autonomous UAV: Research Platform for Indoor and Outdoor Urban Search and Rescue , 2012, IEEE Robotics & Automation Magazine.

[10]  Gerald Cook,et al.  ResQuad: Toward a semi-autonomous wilderness search and rescue unmanned aerial system , 2016, 2016 International Conference on Unmanned Aircraft Systems (ICUAS).

[11]  Tadao Murata,et al.  Petri nets: Properties, analysis and applications , 1989, Proc. IEEE.

[12]  J. L. Roux.  An Introduction to the Kalman Filter , 2003 .

[13]  Michael A. Goodrich,et al.  A Bayesian approach to modeling lost person behaviors based on terrain features in Wilderness Search and Rescue , 2010, Comput. Math. Organ. Theory.

[14]  Alexander Ferworn,et al.  Data Analytics to Predict the Survivability of a Lost Person with Dementia Using R , 2019, 2019 IEEE 10th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON).

[15]  Rosemarie E. Yagoda,et al.  How to work and play with robots: An approach to modeling human-robot interaction , 2012, Computers in Human Behavior.

[16]  G C Dean,et al.  An Introduction to Kalman Filters , 1986 .

[17]  Ronald L. Rivest,et al.  Introduction to Algorithms , 1990 .

[18]  Shiladitya Pujari,et al.  Petri Net: A Tool for Modeling and Analyze Multi-agent Oriented Systems , 2012 .