Nature-inspired and sampling algorithm towards 3D path planning for autonomous vehicles: a review

Abstract

The biggest challenge to autonomous mobile robot navigation is planning an obstacle-free trajectory from an initial point to the target. All environments are prompt to change which arises obstacles that add more complexity to the autonomous navigation systems, especially for tasks such as parcel delivery, law enforcement, and first aid in urban areas. The most of current algorithms for autonomous system path planning are drawn from pre-existing models and focus mostly on Ground Autonomous Vehicles, employing 2D techniques that must be converted to 3D in the case of Aerial Vehicles. The race to solve those challenging tasks, over the past few decades, has led to a promising range of improved and hybrid robot path planning. The main objective of this article is to provide a comprehensive and conclusive review of two of the most successful three-dimensional robotic path planning algorithms developed in recent years. Each algorithm is investigated and evaluated in terms of time efficiency, executable area, and capacity to deal with both static and dynamic obstacles.