Integrating Task and Motion Planning for Unmanned Aerial Vehicles

This paper investigates the problem where a fixed-winged unmanned aerial vehicle is required to find the shortest flyable path to traverse over multiple targets. The unmanned aerial vehicle is modeled as a Dubins vehicle: a vehicle with a minimum turn radius and the inability to go backward. This problem is called the Dubins traveling salesman problem, an extension of the well-known traveling salesman problem. We propose and compare different algorithms that integrate the task planning and the motion planning aspects of the problem, rather than treating the two separately. An upper bound on calculating kinematic satisfying paths for setting costs in the search algorithm is investigated. The proposed integrated algorithms are compared to hierarchical algorithms that solve the search aspect first and then solve the motion planning aspect second. Monte Carlo simulations are performed for a range of vehicle turn radii. The simulations results show the viability of the integrated approach and that using two plausible kinematic satisfying paths as an upper bound to determine the cost-so-far into a search algorithm generally improves performance in terms of the shortest path cost and search complexity.