Home /Research /Geometric Recognition of Diverse Terrain in Real-Time for a Six-Wheeled Robot based on Laser Scanning Sensors
OTHER

Geometric Recognition of Diverse Terrain in Real-Time for a Six-Wheeled Robot based on Laser Scanning Sensors

Nabih Pico, Eui-Chan Kim, Sang-Hyeon Park, Meseret Tadese, Huy Nguyen Tran, Beomjoon Lee, Hyungpil Moon

Year
2022
Citations
4

Abstract

Wheeled robots are involved in different applications due to their adaptability to different terrains. The stability of the robot is related to the permanent contact of the wheels with the ground. This paper presents the method to recognize the geometry terrains in real-time when the wheel has contact at one or multiple contact points with the soil by using laser scanning sensors and measuring the contact angle between the wheel-ground. Furthermore, the robot can recognize when its wheel loses contact with the terrain. Thus, we can create a proper robot control by obtaining the Jacobian matrix and its inverse related to the terrain information. In consequence, the robot can overcome diverse terrains and move safely. The method is validated in experimental results when the six-wheeled robot recognizes a rocky terrain and a slope with a step.

Keywords

TerrainRobotComputer visionArtificial intelligenceLaser scanningComputer scienceMobile robotJacobian matrix and determinantEngineeringLaser

Related papers

Browse all OTHER papers