RecHap: An Interactive Recommender System For Navigating Large Dataset of Mid-Air Haptic Designs

Abstract

Designing haptics is a difficult task especially when the user attempts to design a sensation from scratch for a novel experience. In the fields of visual and audio design, designers often use large example libraries for inspiration, supported by intelligent systems like recommender systems. In this thesis, we contribute a corpus of 5327 mid-air haptic designs (two orders of magnitude larger than existing haptic libraries), and use it to explore a new approach for both novices and experienced hapticians to use these examples in mid-air haptic design. RecHap design tool utilises an autoencoder-based recommendation system that suggests preexisting examples by sampling various regions of the encoded latent space. The tool also provides a graphical user interface for designers to visualize the sensation in 3D view, select previous designs, and bookmark favourites. According to the study conducted, it was evident that the tool allowed designers to quickly sketch ideas and experience them right away. Design suggestions encouraged collaboration, expression, exploration, and enjoyment, which improved creativity.