Predicting Perceptual Haptic Attributes of Textured Surface from Tactile Data Based on Deep CNN-LSTM Network
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
This paper introduces a framework to predict multi-dimensional haptic attribute values that humans use to recognize the material by using the physical tactile signals (acceleration) generated when a textured surface is stroked. To this end, two spaces are established: a haptic attribute space and a physical signal space. A five-dimensional haptic attribute space is established through human adjective rating experiments with the 25 real texture samples. The physical space is constructed using tool-based interaction data from the same 25 samples. A mapping is modeled between the aforementioned spaces using a newly designed CNN-LSTM deep learning network. Finally, a prediction algorithm is implemented that takes acceleration data and returns coordinates in the haptic attribute space. A quantitative evaluation was conducted to inspect the reliability of the algorithm on unseen textures, showing that the model outperformed other similar models.
Originalsprog | Engelsk |
---|---|
Titel | VRST 2023 - 29th ACM Symposium on Virtual Reality Software and Technology |
Forlag | Association for Computing Machinery, Inc. |
Publikationsdato | 9 okt. 2023 |
Artikelnummer | 33 |
ISBN (Elektronisk) | 9798400703287 |
DOI | |
Status | Udgivet - 9 okt. 2023 |
Eksternt udgivet | Ja |
Begivenhed | 29th ACM Symposium on Virtual Reality Software and Technology, VRST 2023 - Christchurch, New Zealand Varighed: 9 okt. 2023 → 11 okt. 2023 |
Konference
Konference | 29th ACM Symposium on Virtual Reality Software and Technology, VRST 2023 |
---|---|
Land | New Zealand |
By | Christchurch |
Periode | 09/10/2023 → 11/10/2023 |
Sponsor | 100% Pure New Zealand, Autodesk, et al., Human Interface Technology Lab New Zealand (HITLabNZ), Niantic, University of Canterbury (UC) |
Navn | Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST |
---|
Bibliografisk note
Publisher Copyright:
© 2023 ACM.
ID: 388954624