In Wilderness Search and Rescue (WiSAR), the incident commander (IC) creates a probability distribution map of the likely location of the missing person. This map is important because it guides the IC in allocating search resources and coordinating efforts, but it often depends almost exclusively on prior experience and subjective judgment. We propose a Bayesian model that utilizes publicly available terrain features data to help model lost-person behaviors. This approach enables domain experts to encode uncertainty in their prior estimations and also make it possible to incorporate human-behavior data collected in the form of posterior distributions, which are used to build a first-order Markov transition matrix for generating a temporal, posterior predictive probability distribution map. The map can work as a base to be augmented by search and rescue workers to incorporate additional information. Using a Bayes Chi-squared test for goodness-of-fit, we show that the model fits a synthetic dataset well. This model also serves as a foundation of a larger framework that allows for easy expansion to incorporate additional factors such as season and weather conditions that affect the lost-person's behaviors. Once a probability distribution map is in place, areas with higher probabilities are searched first in order to find the missing person in the shortest expected time. When using a Unmanned Aerial Vehicle (UAV) to support search, the onboard video camera should cover as much of the important areas as possible within a set time. We explore several algorithms (with and without set destination) and describe some novel techniques in solving this path-planning problem and compare their performances against typical WiSAR scenarios. This problem is NP-hard, but our algorithms yield high quality solutions that approximate the optimal solution, making efficient use of the limited UAV flying time. The capability of planning a path with a set destination also enables the UAV operator to plan a path strategically while letting the UAV plan the path locally.



College and Department

Physical and Mathematical Sciences; Computer Science



Date Submitted


Document Type





UAV, WiSAR, path planning, Bayesian modeling