A Model for Estimating Tactile Sensation by Machine Learning Based on Vibration Information Obtained while Touching an Object

The Dynamic Target Motion Perception Mechanism of Tactile-Assisted Vision in MR Environments

In the mixed reality (MR) environment, the task of target motion perception is usually undertaken by vision. This approach suffers from poor discrimination and high cognitive load when the tasks are complex. This cannot meet the needs of the air traffic control field for rapid capture and precise positioning of the dynamic targets in the air. Based on this problem, we conducted a multimodal optimization study on target motion perception judgment by controlling the hand tactile sensor to achieve the use of tactile sensation to assist vision in MR environment. This allows it to adapt to the requirements of future development-led interactive tasks under the mixed reality holographic aviation tower. Motion perception tasks are usually divided into urgency sensing for multiple targets and precise position tracking for single targets according to the number of targets and task division. Therefore, in this paper, we designed experiments to investigate the correlation between tactile intensity-velocity correspondence and target urgency, and the correlation between the PRS (position, rhythm, sequence) tactile indication scheme and position tracking. We also evaluated it through comprehensive experiment. We obtained the following conclusions: (1) high, higher, medium, lower, and low tactile intensities would bias human visual cognitive induction to fast, faster, medium, slower, and slow motion targets. Additionally, this correspondence can significantly improve the efficiency of the participants' judgment of target urgency; (2) under the PRS tactile indication scheme, position-based rhythm and sequence cues can improve the judgment effect of human tracking target dynamic position, and the effect of adding rhythm cues is better. However, when adding rhythm and sequence cues at the same time, it can cause clutter; (3) tactile assisted vision has a good improvement effect on the comprehensive perception of dynamic target movement. The above findings are useful for the study of target motion perception in MR environments and provide a theoretical basis for subsequent research on the cognitive mechanism and quantitative of tactile indication in MR environment.

Nonlinear Tactile Estimation Model Based on Perceptibility of Mechanoreceptors Improves Quantitative Tactile Sensing

Tactile sensing has attracted significant attention as a tactile quantitative evaluation method because the tactile sensation is an important factor while evaluating consumer products. Although the human tactile perception mechanism has nonlinearity, previous studies have often developed linear regression models. In contrast, this study proposes a nonlinear tactile estimation model that can estimate sensory evaluation scores from physical measurements. We extracted features from the vibration data obtained by a tactile sensor based on the perceptibility of mechanoreceptors. In parallel, a sensory evaluation test was conducted using 10 evaluation words. Then, the relationship between the extracted features and the tactile evaluation results was modeled using linear/nonlinear regressions. The best model was concluded by comparing the mean squared error between the model predictions and the actual values. The results imply that there are multiple evaluation words suitable for adopting nonlinear regression models, and the average error was 43.8% smaller than that of building only linear regression models.