Ellipsoidal Path Planning for Unmanned Aerial Vehicles

Carlos Villaseñor,Nancy Arana-Daniel,Alberto A Gallegos,Javier Gomez-Avila,Gehova Lopez-Gonzalez,Jesus Hernandez-Barragan

doi:10.3390/app11177997

Abstract

The research in path planning for unmanned aerial vehicles (UAV) is an active topic nowadays. The path planning strategy highly depends on the map abstraction available. In a previous work, we presented an ellipsoidal mapping algorithm (EMA) that was designed using covariance ellipsoids and clustering algorithms. The EMA computes compact in-memory maps, but still with enough information to accurately represent the environment and to be useful for robot navigation algorithms. In this work, we develop a novel path planning algorithm based on a bio-inspired algorithm for navigation in the ellipsoidal map. Our approach overcomes the problem that there is no closed formula to calculate the distance between two ellipsoidal surfaces, so it was approximated using a trained neural network. The presented path planning algorithm takes advantage of ellipsoid entities to represent obstacles and compute paths for small UAVs regardless of the concavity of these obstacles, in a very geometrically explicit way. Furthermore, our method can also be used to plan routes in dynamical environments without adding any computational cost.

Highlights

Autonomous Unmanned Aerial Vehicles (UAVs) play an important role in both military and civilian applications
Besides distance, are considered, the path planning problem can been stated as an optimization problem, and population based algorithms have been used in many cases to solve it successfully [4,5,6,7,8]
In [9], we described a novel algorithm for path planning, which uses conformal geometric algebra to generate maps using spheres

Summary

Introduction

Autonomous Unmanned Aerial Vehicles (UAVs) play an important role in both military and civilian applications. An important problem to solve in order to achieve a certain level of autonomy is path planning. Besides distance, are considered, the path planning problem can been stated as an optimization problem, and population based algorithms have been used in many cases to solve it successfully [4,5,6,7,8]. In [9], we described a novel algorithm for path planning, which uses conformal geometric algebra to generate maps using spheres. We gain in terms of the number of parameters needed for representing the maps and these maps are rich in information. The spheres are easy to operate in conformal geometric algebra

Objectives

Results

Conclusion