Data-driven Haptic Modeling and Rendering

Representative image: 
Abstract: 

The ultimate goal of 'Data-driven Haptic Modeling and Rendering' is to recreate a virtual object that feels exactly same to the corresponding real object. Data-driven method is one of the notable approaches for that purpose as the interaction between a user and the object is a very complicated physical process. We apply data-driven method to sophisticated haptic primitives, such as surface textures, viscoelasticity reactions, and thermal properties.

Paper: 

[C87] Data-Driven Modeling of Isotropic Haptic Textures Using Frequency-Decomposed Neural Networks

Sunghwan Shin, Reza Haghighi Osgouei, Ki-Duk Kim, and Seungmoon Choi
In Proceedings of the IEEE World Haptics Conference (WHC), 2015 (movie).

[J37] Data-Driven Haptic Modeling and Rendering of Viscoelastic and Frictional Responses of Deformable Objects

Sunghoon Yim, Seokhee Jeon, and Seungmoon Choi
IEEE Transactions on Haptics, Vol. 9, No. 4, pp. 548-559, 2016.

[C103] Geometry-Based Haptic Texture Modeling and Rendering using Photometric Stereo

Sunghwan Shin and Seungmoon Choi
In Proceedings of the IEEE Haptics Symposium (HAPTICS), pp. 262-269, 2018 (Single-track featured talk; Acceptance rate 13%).

[C105] Data-Driven Thermal Rendering: An Initial Study

Hyejin Choi, Seongwon Cho, Sunghwan Shin, Hojin Lee, and Seungmoon Choi
In Proceedings of the IEEE Haptics Symposium (HAPTICS), pp. 344-350, 2018.