Qualitative spatial logic descriptors from 3D indoor scenes to generate explanations in natural language

Abstract

The challenge of describing 3D real scenes is tackled in this paper using qualitative spatial descriptors. A key point to study is which qualitative descriptors to use and how these qualitative descriptors must be organized to produce a suitable cognitive explanation. In order to find answers, a survey test was carried out with human participants which openly described a scene containing some pieces of furniture. The data obtained in this survey are analysed, and taking this into account, the QSn3D computational approach was developed which uses a XBox 360 Kinect to obtain 3D data from a real indoor scene. Object features are computed on these 3D data to identify objects in indoor scenes. The object orientation is computed, and qualitative spatial relations between the objects are extracted. These qualitative spatial relations are the input to a grammar which applies saliency rules obtained from the survey study and generates cognitive natural language descriptions of scenes. Moreover, these qualitative descriptors can be expressed as first-order logical facts in Prolog for further reasoning. Finally, a validation study is carried out to test whether the descriptions provided by QSn3D approach are human readable. The obtained results show that their acceptability is higher than 82%.

Special issue on cognitive robotics

“…The interaction between robot and user is the other problem addressed on this special issue. If the framework by Melidis et al (2017) is an original proposal for easing the user to control a tele-operated robot, the approaches of Manso et al (2017) and Falomir and Kluth (2017) focus on autonomous robots, able to understand the scene and to use this knowledge for interacting with humans. The QSn3D allows a robot to build internal semantic representation, which can be shared with humans.…”

“…On the other hand, the challenge of internalizing a scene and processing this information using natural language is tackled in the works by Falomir and Kluth (2017), and by Manso et al (2017). In the first work, the authors propose a framework which is able to automatically generate explanations in natural language of complex indoor scenes.…”