Abstract
Sensing and mapping its surroundings is an essential requirement for a mobile robot. Geometric maps endow robots with the capacity of basic tasks, e.g., navigation. To co-exist with human beings in indoor scenes, the need to attach semantic information to a geometric map, which is called a semantic map, has been realized in the last two decades. A semantic map can help robots to behave in human rules, plan and perform advanced tasks, and communicate with humans on the conceptual level. This survey reviews methods about semantic mapping in indoor scenes. To begin with, we answered the question, what is a semantic map for mobile robots, by its definitions. After that, we reviewed works about each of the three modules of semantic mapping, i.e., spatial mapping, acquisition of semantic information, and map representation, respectively. Finally, though great progress has been made, there is a long way to implement semantic maps in advanced tasks for robots, thus challenges and potential future directions are discussed before a conclusion at last.
Highlights
Sensing and modeling its surroundings is an essential requirement for a mobile robot.When moving through an indoor environment, a robot needs to plan a safe path to the destination, without collisions with obstacles
One impressive example is the success of Visual-Inertial Odometry (VIO) [53,54], which fuses camera data with inertial measurement units to localize with higher precision
According to definitions in different works, semantic mapping consists of three modules, namely spatial mapping, acquisition of semantic information, and map representation
Summary
Sensing and modeling its surroundings is an essential requirement for a mobile robot. A robot may have to interact with the environment as some complex tasks are required, like a robot may be asked to go to another room with a door closed, the robot has to open the door to arrive the destination It is reasonable for a mobile robot to understand oral commands from its hosts, like “fetch an apple from the fridge”. The survey [3] is a comprehensive work, which reviewed the topic of semantic mapping of robotics, both in indoor and outdoor scenes. In this survey, references about semantic mapping were categorized by their primary characteristics. Semantic mapping is divided into three modules, namely spatial mapping, acquisition of semantic information, and map representation, according to its definitions
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have