Real-time instance-aware semantic mapping

Abstract

The semantic information helps robots to understand its surroundings like human beings and enables robots to achieve human-robot interaction. In recent years, there have been many interests in semantic mapping. Numerous approaches manage to build a semantic map and achieve good accuracy, but the existing mapping methods which create the metric semantic map ignore the subsequent applications of the semantic map. However, the metric map with the simple semantic class label has no direct benefit to localization. In this paper, we propose an approach to construct an object-centric map with promising applications. Employing the traditional metric and deep learning methods, we can extract objects from the environment and along with semantics. This object representation of the semantic map can be useful in other applications of robots, our local map and global map framework can be useful for navigation. At last, we report on the quality and speed of our object-centric mapping method.