Real path planning based on genetic algorithm and Voronoi diagrams

Abstract

In the context of Mobile Robotics, the efficient resolution of the Path Planning problem is a key task. The model of the environment and the search algorithm are basic issues in the resolution of the problem. This paper highlights the main features of Path Planning proposal for mobile robots in static environments. In our proposal, the path planning is based on Voronoi diagrams, where obstacles in the environment are considered as the generating points of the diagram, and a genetic algorithm is used to find a path without collisions from the robot initial to target position. This work combines some ideas presented by Roque and Doering, who use Voronoi diagrams for modelling the environment, and other ideas presented by Zhang et al. who adopt a genetic algorithm for computing paths on a regular grid based environment, considering certain quality attributes. The main results were probed both in simulated and real environments.

Energy efficient path planning for Unmanned Surface Vehicle in spatially-temporally variant environment

“…Inspired by the Voronoi-GA shortest path planning algorithm in (Benavides et al, 2011), the Vornoi-GA energy efficient (VGAEE) path planning algorithm is also developed for comparison. The VGAEE can also be treated as the mutant algorithm of VVGAEE.…”

“…However, this approach is not computationally efficient in the case of large-scale spatial environments where islands' sizes and their inter-distances are highly in-homogeneous. Compared to the grid occupancy map, the Voronoi roadmap is known to be more computationally efficient for map representation in the two-dimensional space (Pehlivanoglu, 2012) and better in complex spatial environments (Benavides et al, 2011). The Voronoi-Visibility roadmap and Dijkstra's algorithm were integrated for generating the energy efficient path in (Niu et al, 2018).…”

“…However, this algorithm has only taken spatially variant sea currents into consideration and has not addressed the temporally variant sea current problem. Benavides et al (2011) introduced a path planning algorithm by combining the Voronoi roadmap and GA method, but without taking into account energy consumption.…”

“…In this work, we combine the ideas of Benavides et al (2011) and Niu et al (2018), and propose the Voronoi-Visibility-GA energy efficient (VVGAEE) path planning algorithm. The motivation for the combination in this research is to keep the flexibility and computational efficiency of the Voronoi diagram algorithm in generating the collision free roadmap and also the computational efficiency of the GA algorithm in searching in high dimensional dataset, so as to generate energy efficient paths in spatially-temporally variant environments.…”

“…Inspired by the work of Benavides et al (2011) and Song et al (2017), two other methods, named Voronoi-GA energy efficient (VGAEE) path planning algorithm and Voronoi-Visibility energy efficient path re-planning (VVEEPRE) algorithm, are also proposed and developed for performance comparison. Finally, the Voronoi-Visibility energy efficient (VVEE) algorithm (Niu et al, 2018), VGAEE, VVEEPRE and VVGAEE algorithms are compared using ten USV missions in a complex geographic environment (98 islands) and spatiallytemporally variant sea current scenarios.…”