Hybrid Methodology for Path Planning and Computational Vision Applied to Autonomous Mission: A New Approach

被引：11

作者：

Coelho, Fabricio O. ^{[1
]}

Pinto, Milena F. ^{[1
]}

Souza, Joao Pedro C. ^{[2
]}

Marcato, Andre L. M. ^{[1
]}

机构：

[1] Univ Fed Juiz de Fora, Dept Elect Engn, Juiz De Fora, Brazil

[2] Univ Porto, Fac Engn, Porto, Portugal

来源：

ROBOTICA | 2020年 / 38卷 / 06期

关键词：

Autonomous missions; Artificial intelligence; Localisation; Mobile robots; Path planning; BRIDGE DECK INSPECTION;

D O I：

10.1017/S0263574719001206

中图分类号：

TP24 [机器人技术];

学科分类号：

080202 ; 1405 ;

摘要：

In recent years, mobile robots have become increasingly frequent in daily life applications, such as cleaning, surveillance, support for the elderly and people with disabilities, as well as hazardous activities. However, a big challenge arises when the robotic system must perform a fully autonomous mission. The main problems of autonomous missions include path planning, localisation, and mapping. Thus, this research proposes a hybrid methodology for mobile robots on an autonomous mission involving an offline approach that uses the Direct-DRRT* algorithm and the artificial potential fields algorithm as the online planner. The experimental design covers three scenarios with an increasing degree of accuracy in respect of the real world. Additionally, an extensive evaluation of the proposed methodology is reported.

引用

页码：1000 / 1018

页数：19