Avoiding Non-Manhattan Obstacles Based on Projection of Spatial Corners in Indoor Environment

作     者：Luping Wang Hui Wei Luping Wang;Hui Wei

作者机构：the School of Mechanical EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China the Laboratory of Algorithms for Cognitive ModelsShanghai Key Laboratory of Data ScienceSchool of Computer ScienceFudan UniversityShanghai 201203China 

出 版 物：《IEEE/CAA Journal of Automatica Sinica》 (自动化学报（英文版）)

年 卷 期：2020年第7卷第4期

页      面：1190-1200页

核心收录：

学科分类：080202[工学-机械电子工程] 08[工学] 0804[工学-仪器科学与技术] 0802[工学-机械工程] 

基　　金：supported by the National Natural Science Foundation of China(61771146,61375122) the National Thirteen 5-Year Plan for Science and Technology(2017YFC1703303) in part by Shanghai Science and Technology Development Funds(13dz2260200,13511504300) 

主　　题：Avoiding obstacle monocular vision navigation non-Manhattan obstacle spatial corner 

摘      要：Monocular vision-based navigation is a considerable ability for a home mobile robot. However, due to diverse disturbances, helping robots avoid obstacles, especially nonManhattan obstacles, remains a big challenge. In indoor environments, there are many spatial right-corners that are projected into two dimensional projections with special geometric configurations. These projections, which consist of three lines,might enable us to estimate their position and orientation in 3 D scenes. In this paper, we present a method for home robots to avoid non-Manhattan obstacles in indoor environments from a monocular camera. The approach first detects non-Manhattan obstacles. Through analyzing geometric features and constraints,it is possible to estimate posture differences between orientation of the robot and non-Manhattan obstacles. Finally according to the convergence of posture differences, the robot can adjust its orientation to keep pace with the pose of detected non-Manhattan obstacles, making it possible avoid these obstacles by itself. Based on geometric inferences, the proposed approach requires no prior training or any knowledge of the camera’s internal parameters,making it practical for robots navigation. Furthermore, the method is robust to errors in calibration and image noise. We compared the errors from corners of estimated non-Manhattan obstacles against the ground truth. Furthermore, we evaluate the validity of convergence of differences between the robot orientation and the posture of non-Manhattan obstacles. The experimental results showed that our method is capable of avoiding non-Manhattan obstacles, meeting the requirements for indoor robot navigation.