Towards Customizable Robotic Disinfection With Structure-Aware Semantic Mapping

In the current COVID-19 pandemic, people expect to use robots replace humans complete disinfection work in public places. Since different regions environment have risks, addition conventional SLAM capability, robot also needs be able recognize and distinguish objects scene customizable tasks. this paper, we propose a LiDAR-based semantic mapping system that can used for robotic By using prior information about structure, our extract levels of from raw point cloud, so as not only construct an occupancy grid map navigation, but hierarchical meets tasks, including setting navigation waypoints, distances time. The effectiveness proposed is proved real-world metro applications.