Uav guidance algorithms via partially observable markov decision processes

Abstract

The goal here is to design a path-planning algorithm to guide unmanned aerial vehicles (UAVs) for tracking multiple ground targets based on the theory of partially observable Markov decision processes (POMDPs). This study shows how to exploit the generality and flexibility of the POMDP framework by incorporating a variety of features of interest naturally into the framework, which is accomplished by plugging in the appropriate models. Specifically, this study shows how to incorporate the following features by appropriately formulating the POMDP action space, state-transition law, and objective function: (1) control UAVs with both forward acceleration and bank angle subject to constraints, (2) account for the effect of wind disturbance on UAVs, (3) avoid collisions between UAVs and obstacles and among UAVs, (4) track targets while evading threats, (5) track evasive targets, and (6) mitigate track swaps.