Controlled tactile exploration and haptic object recognition

Abstract

In this paper we propose a novel method for in-hand object recognition. The method is composed of a grasp stabilization controller and two exploratory behaviours to capture the shape and the softness of an object. Grasp stabilization plays an important role in recognizing objects. First, it prevents the object from slipping and facilitates the exploration of the object. Second, reaching a stable and repeatable position adds robustness to the learning algorithm and increases invariance with respect to the way in which the robot grasps the object. The stable poses are estimated using a Gaussian mixture model (GMM). We present experimental results showing that using our method the classifier can successfully distinguish 30 objects. We also compare our method with a benchmark experiment, in which the grasp stabilization is disabled. We show, with statistical significance, that our method outperforms the benchmark method.

Tactile Model O: Fabrication and Testing of a 3D-Printed, Three-Fingered Tactile Robot Hand

“…For a final comment, we note that the T-MO is able to perform well in comparison with other tactile hands even though it has a much lower cost (costing us less than £1100 to make). We have demonstrated comparable results in tactile perception to previous work that utilizes more expensive robot systems such as the BarrettHand, 28 Schunk, 26 and iCub 24 hands. Most of the T-MO's cost is actually its motors, followed by the 3D printing and camera costs, so it may be possible to reduce these costs still further.…”

“…That said, a direct comparison between studies is not possible because the hands and tactile sensors differ, along with the objects and experiments. In particular, our T-MO picked objects off a table, whereas other studies such as Regoli et al 24 obtain up to 98% on a smaller set of 21 objects that were passed to static mounted hands, which does not control against the human help providing a better grasp for object classification.…”

“…Regoli et al 24 achieve an accuracy of 97.6% by using a kernel regularized least-squares method on data collected over 21 objects from the YCB set. Here, objects are placed into an iCub hand and tactile data from two fingers are gathered during exploratory grasping and wrapping actions.…”

An Application of Deep Learning to Tactile Data for Object Recognition under Visual Guidance

“…As such, the center of each model is chosen as one of the three required points for formation of all planes. It is worth mentioning that such an implementation does not necessarily require visual data since supplementary tactile explorations such as the grasp stabilization method used in Regoli et al [23] or a reinforcement learning as described in Pape et al [24] can assist in determination of such contours. The acquisition of tactile information by exploration is both expensive in time and robot programming effort.…”

Visual–tactile object recognition of a soft gripper based on faster Region-based Convolutional Neural Network and machining learning algorithm

“…[23][24][25] Angle and pressure sensors are utilized to analyze the bending information of the finger for recognizing different objects. 26 In summary, the influence of scaling can be removed in the tactile recognition as the real dimension and shape of the interacted object are mapped to the tactile sensor directly. In addition, tactile recognition can be used to capture properties like texture, roughness, spatial features, compliance, and friction, 27,28 which are difficult to be recognized by vision.…”