Asynchronous vehicle pose correction using visual detection of ground features

27th International Conference on CADCAM, Robotics and Factories of the Future 2014

工业技术;机械制造

Harnarinesingh, Randy E. S.^1 ; Syan, Chanan S.^1

Department of Mechanical and Manufacturing Engineering, University of the West Indies, St. Augustine, Trinidad and Tobago^1

关键词: Autonomous Vehicles;    Error mitigation;    Laboratory environment;    Pose estimation errors;    Position errors;    Vehicle position;    Visual detection;    Visual odometry;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/65/1/012021/pdf
DOI  :  10.1088/1757-899X/65/1/012021

学科分类：工业工程学

来源: IOP

【 摘 要 】

The inherent noise associated with odometry manifests itself as errors in localization for autonomous vehicles. Visual odometry has been previously used in order to supplement classical vehicle odometry. However, visual odometry is limited in its ability to reduce errors in localization for large travel distances that entail the cumulative summing of individual frame-to-frame image errors. In this paper, a novel machine vision approach for tiled surfaces is proposed to address this problem. Tile edges in a laboratory environment are used to define a travel trajectory for the Quansar Qbot (autonomous vehicle) built on the iRobot iRoomba platform with a forward facing camera. Tile intersections are used to enable asynchronous error recovery for vehicle position and orientation. The proposed approach employs real-time image classification and is feasible for error mitigation for large travel distances. The average position error for an 8m travel distance using classical odometry was measured to be 0.28m. However, implementation of the proposed approach resulted in an error of 0.028m. The proposed approach therefore significantly reduces pose estimation error and could be used to supplement existing modalities such as GPS and Laser-based range sensors.