首页|Reports on Robotics Findings from Xi’an University of Science and Technology Pro vide New Insights (Visual SLAM keyframe selection method with multiple constrain ts in underground coal mines)
Reports on Robotics Findings from Xi’an University of Science and Technology Pro vide New Insights (Visual SLAM keyframe selection method with multiple constrain ts in underground coal mines)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators discuss new findings in robotics. According to news reporting from Xi’an, People’s Republic of China, by NewsRx journalists, research stated, “The significant demand of coal mine intel ligence has put forward some higher requirements for the intelligent perception of underground mobile robots in coal mines, and the Visual Simultaneous Localiza tion and Mapping (VSLAM) is a key technology for the intelligent perception of c oal mine robots. However, due to unstructured environmental features, weak textu res, uneven illumination, and small space in underground coal mines, the existin g methods that rely on heuristic thresholds for keyframe selection cannot meet t he localization and mapping requirements of visual SLAM in underground coal mine s.” The news correspondents obtained a quote from the research from Xi’an University of Science and Technology: “Therefore, a visual SLAM keyframe selection method with multiple constraints in underground coal mines was proposed, which achieves a real-time and robust pose estimation of mobile robot in coal mines and provid es data for digital twin in coal mines. Firstly, the proposed method was constra ined according to geometric structure, adaptive thresholding was used instead of static heuristic thresholding for keyframe selection to achieve the effectivene ss and robustness of keyframe selection. Secondly, the distribution of effective feature points was homogenized by the balance of gravity principle to further e nsure the stability of keyframe selection and the denseness and accuracy of crea ted map points. Finally, the steering place was further constrained by using the heading angle threshold to reduce the impact of viewpoint abrupt change on the visual SLAM accuracy. In order to verify the effectiveness of the proposed metho d, an experimental analysis was conducted in indoor scenes and underground coal mines respectively using an independently designed mobile robot data acquisition platform. Then, the qualitative and quantitative evaluations were made from Abs olute Trajectory Error (ATE) and Root Mean Square Error (RMSE).”
Xi’an University of Science and Technolo gyXi’anPeople’s Republic of ChinaAsiaEmerging TechnologiesMachine Lear ningNano-robotRobotRobotics
NETL
NSTL
