Multi-Objective UAV Path Planning with Refined Reconnaissance and Threat Formulations

Military operations are turning to more complex and advanced automation technology for minimum risk and maximum efficiency. A critical piece to this strategy is unmanned aerial vehicles (UAVs). UAVs require the intelligence to safely maneuver along a path to an intended target, avoiding obstacles such as other aircraft or enemy threats. Often automated path planning algorithms are employed to specify targets for a UAV to investigate. To date, path-planning algorithms have been limited to providing only a single solution (alternate path) without further input from a pilot. This paper improves upon a previously developed multi-objective path planner that uses Particle Swarm Optimization (PSO) to generate multiple solution paths based on predefined criteria. The original path planner consisted of 4 components: fuel efficiency, reconnaissance, threat avoidance, and terrain. In this paper, the focus will be on improvements made to the formulations of the cost functions for reconnaissance and threat avoidance as well as the ability of the pilot to adjust the weights for the mission objectives. The alternate paths can be optimized with a preference towards maximum safety, minimum fuel consumption, or target reconnaissance. The weight adjustment techniques presented enhance the pilot’s ability to find desirable solutions when re-tasking the UAV. Most importantly, the paths were generated in real time to allow efficient decision making by the UAV pilot. These improvements were noted in the simulated test scenarios used to evaluate the path planner.