Home /Research /Highly Maneuverable Ground Reconnaissance Robot Based on Machine Learning
OTHER

Highly Maneuverable Ground Reconnaissance Robot Based on Machine Learning

Peixuan Wang, Xiaorui Peng, Jiayu Chen, Jiacheng Chen

Year
2018
Citations
3

Abstract

This article mainly introduces the application of a reconnaissance robot's mechanical design, motion control algorithm and image processing program. In the mechanical structure, it adopts a motor system that drives a Mecanum wheel with double wishbone independent suspension to ensure that the robot has high speed and high mobility. The robot is equipped with a two-degree-of-freedom pan/tilt for installing a wireless video camera, which can acquire images with free viewing angles to facilitate remote control of operators and obtain on-site intelligence. The image processing program uses the machine learning method of the HOG feature and the SVM classifier to identify target objects such as enemy forces or certain types of explosive objects in disaster scenarios to reduce the pressure on operators and increase the reaction speed.

Keywords

RobotComputer scienceArtificial intelligenceComputer visionMobile robotImage processingMachine visionSimulationImage (mathematics)

Related papers

Browse all OTHER papers