Estimation of Grip Force and Slip Behavior During Robotic Grasp Using Data Fusion and Hypothesis Testing: Case Study with a Matrix Sensor

Stochastic model-based grasp synthesis: New logistics for data fusion with dissimilar sensor-cells

“…We need to consider a comparatively larger value of ' ', as the level of uncertainty is more in the present model, compared to that in our earlier work [18]. Finally, from eqn.…”

“…5, {u i-1 } |i=1 = 0 and {u i+1 } |i=n =0. It may be noted that this model is essentially taxel-specific, unlike the previous models [18], wherein cumulative effect of the taxels are reflected only. In contrast, the relative dependency of one taxel over the neighbouring ones is getting priority in the present model.…”

“…It is termed as "Hypothesis Error Based Threshold Evaluation Method" (HEBTEM) [18]. The proposed method relies on the selection of the confidence level, as stipulated by probability of Type I error.…”

“…HEBTEM becomes advantageous since it doesn't include the concept of Bayesian Risk, which inherently involves the computation related to Probability of False Alarm (P f ) and Probability of Miss (P m ) [18]. The concept of Bayesian Risk is suitable only to cases where a large group of field-sensors are either attempting to evaluate the presence or absence of a single object or tracking a single target.…”

“…Also, we advocate for a dynamic threshold-band in the model, that can be suitably adapted depending upon the endapplication during fusion. Unlike dedicated threshold mark, as postulated with our earlier fusion-models [18], here we will consider a distinct fuzzy-zone, equaling the width of the threshold-band, in order to compensate for the finite number of sensory signals involved in the fusion process. This fuzzy-zone will, no doubt, generate an in-decision regarding the object's presence /absence, but, can be tackled by our model.…”