Abstract
The semantic localization problem in robotics consists in determining the place where a robot is located by means of semantic categories. The problem is usually addressed as a supervised classification process, where input data correspond to robot perceptions while classes to semantic categories, like kitchen or corridor.In this paper we propose a framework, implemented in the PCL library, which provides a set of valuable tools to easily develop and evaluate semantic localization systems. The implementation includes the generation of 3D global descriptors following a Bag-of-Words approach. This allows the generation of fixed-dimensionality descriptors from any type of keypoint detector and feature extractor combinations. The framework has been designed, structured and implemented to be easily extended with different keypoint detectors, feature extractors as well as classification models.The proposed framework has also been used to evaluate the performance of a set of already implemented descriptors, when used as input for a specific semantic localization system. The obtained results are discussed paying special attention to the internal parameters of the BoW descriptor generation process. Moreover, we also review the combination of some keypoint detectors with different 3D descriptor generation techniques.
Highlights
The semantic localization problem can be defined as the problem of determining the place where a robot is located by means of semantic categories
The problem is usually addressed as a supervised classification process, where input data correspond to robot perceptions while classes to semantic categories, like kitchen or corridor
The problem is usually addressed as a supervised classification process, where input data correspond to robot perceptions, and classes to semantic room/place categories like kitchen, bathroom, or corridor
Summary
The semantic localization problem can be defined as the problem of determining the place where a robot is located by means of semantic categories. The problem is usually addressed as a supervised classification process, where input data correspond to robot perceptions, and classes to semantic room/place categories like kitchen, bathroom, or corridor. This classification process is tackled by using models that require fixed-dimensionality inputs, such as SVMs [17] or Bayesian Network classifiers [34]. To transform robot perception into fixed-dimensionality descriptors, we can choose for using global features or build them from a set of local features following the well-known Bag-of-Words (BoW) approach [33]. The semantic information about the place where the robot is located can be very helpful for more specific robotic tasks like autonomous navigation, high-level planning, simultaneous location and mapping (SLAM), or human-robot interaction
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
