Abstract
Data-driven haptic modeling is an emerging technique where contact dynamics are simulated and interpolated based on a generic input-output matching model identified by data sensed from interaction with target physical objects. In data-driven modeling, selecting representative samples from a large set of data in a way that they can efficiently and accurately describe the whole dataset has been a long standing problem. This paper presents a new algorithm for the sample selection where the variances of output are observed for selecting representative input-output samples in order to ensure the quality of output prediction. The main idea is that representative pairs of input-output are chosen so that the ratio of the standard deviation to the mean of the corresponding output group does not exceed an application-dependent threshold. This output- and standard deviation-based sample selection is very effective in applications where the variance or relative error of the output should be kept within a certain threshold. This threshold is used for partitioning the input space using Binary Space Partitioning-tree (BSP-tree) and k-means algorithms. We apply the new approach to data-driven haptic modeling scenario where the relative error of the output prediction result should be less than a perceptual threshold. For evaluation, the proposed algorithm is compared to two state-of-the-art sample selection algorithms for regression tasks. Four kinds of haptic related behavior–force datasets are tested. The results showed that the proposed algorithm outperformed the others in terms of output-approximation quality and computational complexity.
Highlights
In the last couple of decades, owing to its remarkable developments, virtual reality (VR) systems have found applications in most scientific fields
The haptic feedback is calculated via physics simulation that determines the feedback based on haptic models for the simulation and user’s actions
Several spikes appear on the relative error curve of D-ENN for high reference forces for most datasets, which causes instability
Summary
In the last couple of decades, owing to its remarkable developments, virtual reality (VR) systems have found applications in most scientific fields. The haptic model can be either physics based [1,2,3,4,5,6,7] or generic interpolation models [8,9,10]. Measurement-based modeling using a generic interpolation model, namely data-driven modeling, is emerging in the haptics research field [8,9,10]. This can prove highly beneficial for people with special needs [13]. In this approach, input-output data pairs collected with sensors, are pre-processed, e.g., sample selection, and are fed into the interpolation model training algorithm. Data-driven approaches can deal with very complex behaviors, e.g., inhomogeneous stiffness with large deformation, using a relatively simple and unified framework
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
