Visual stimuli are essential in many applications in human robot interaction. However, such tasks are usually computationally intensive. Also, data received from the various sensors on a robot require different data representation and processing techniques, which increases the complexity and makes the fusion of sensory data for decision making more difficult. An alternative approach is the use of the Lattice Computing (LC) paradigm for hybrid mathematical modelling based on mathematical lattice theory that unifies rigorously numerical data and non-numerical data. This paper presents an application of this approach, and more specifically a novel method for head pose estimation using LC techniques, as an initial step towards using LC as a unified methodology in social robot interaction applications.
Kaburlasos, V.G., Lytridis, C., Bazinas, C., Chatzistamatis, S., Sotiropoulou, K., Najoua, A., Youssfi, M., Bouattane, O.: Head Pose Estimation Using Lattice Computing Techniques. In: 2020 International Conference on Software, Telecommunications and Computer Networks (SoftCOM). pp. 1–5 (2020). https://doi.org/10.23919/SoftCOM50211.2020.9238315.