Contact localization from soft tactile array sensor using tactile image

It is possible to accurately recognize the shape of an object or to grip it by setting soft tactile sensors on a robot's hands. We studied a multichannel soft tactile sensor as an artificial hand and evaluated the pressure's response performance from several directions and the slipping and sliding responses. The tactile sensor consisted of multiple pneumatic sensors and a soft cap with a fingerprint structure that was made of silicone gum and was separated from multiple spaces. Evaluation tests showed that the multiple soft tactile sensors estimate both an object's contact force and its contact location. Our tactile sensor also measured the object's roughness by the slide on surface texture.

Drawing inspiration from the human vision-touch interaction that demonstrates the ability of vision in assisting tactile manipulation tasks, this paper addresses the issue of 3D object recognition from tactile data whose acquisition is guided by visual information. An improved computational visual attention model is initially applied on images collected from multiple viewpoints over the surface of an object to identify regions that attract visual attention. Information about color, intensity, orientation, symmetry, curvature, contrast and entropy are advantageously combined for this purpose. Interest points are then extracted from these regions of interest using an innovative technique that takes into consideration the best viewpoint of the object. As the movement and positioning of the tactile sensor to probe the object surface at the identified interest points take generally a long time, the local data acquisition is first simulated to choose the most promising approach to interpret it. To enable the object recognition, the tactile images are analyzed with the help of various classifiers. A method based on similarity is employed to select the best candidate tactile images to train the classifier. Among the tested algorithms, the best performance is achieved using the k-nearest neighbor classifier both for simulated data (87.89% for 4 objects and 75.82% for 6 objects) and real tactile sensor data (72.25% for 4 objects and 70.47% for 6 objects).

Tactile sensors are essential to robot hands that deal with various objects and interact with the environment. Soft tactile sensors are especially important to capture tactile information about delicate, irregular-shaped, or unknown objects. This paper introduces a soft tactile sensor that can simultaneously estimate the contact force, contact feature, and contact point. Inspired by multifunctional human skin, the proposed design has a dual-layer structure and is multifunctional. The top layer consists of a group of sensing elements that detect the contact location and contact feature enhanced by the bagging classifier based on the k-nearest neighbors. The sensor elements were biomimetically and analytically designed as a pyramid shape that mimicked the mountain ridge-like structure in human skin to improve sensitivity. The bottom layer was made by a piece of Velostat sandwiched between conductive fabrics that can measure the contact force. The relationship between the sensing voltage and the contact force was modeled by the Nadaraya–Watson regressor. The performance of the proposed sensor was verified by a repeatability test. Furthermore, we demonstrated the effectiveness of the proposed sensor on a robotic gripper. The experimental results show that this sensor is able to detect contact information of fragile objects.

An edge detection algorithm for use with tactile sensors is presented in this paper. The algorithm is based on the physical properties of the tactile sensor and tactile data. In addition, the algorithm is computationally efficient, and is thus suitable for real-time data processing. Experimental results from the application of this algorithm to a Lord LTS-210 tactile array sensor are presented. Further, observations about the use of a tactile sensor in a system are discussed. The proposed algorithm is a part of a real-time controller, implemented on CMU DD Arm II, that uses a tactile sensor in the feedback loop.

Contact location and force are among the most useful parameters for grasping and dextrous manipulation. This paper presents the theoretical results of extracting these parameters from a tactile sensor, which is an array of pressure (stress) transducers under an elastic layer. Using the model of a 3-D frictional point force acting on an elastic half-space, moment analysis is employed to interpret a tactile image. Analytical relationship between the first three moments of the tactile image and contact location and force (magnitude and direction) is established for the cases of a single-layer and two-layer one-dimensional tactile sensor and a single layer multi-dimensional tactile sensor. It is shown that the first three moments of a tactile image are sufficient to recover information about point contact. The corresponding inverse models have simple closed form for efficient computation.

Soft tactile sensor to detect the slip of a Robotic hand

Soft tactile sensors have been extensively studied due to their promising potential in estimating applied forces while exhibiting mechanical compliance. Such sensors have been fabricated from a variety of composite materials and various techniques to advance their applications. Currently, the development of soft tactile sensors based on carbon nanotubes (CNT)–polydimethylsiloxane (PDMS) gel has yet been investigated. This letter presents the design of a soft tactile sensor based on a CNT-–PDMS-gel composite that is sensitive to external forces. The sensor was composed of an elastomer, a rectangular conductive body made from a PDMS–CNT-gel composite, and a circuit board. The electrical resistance of the composite changed in response to the strain applied. Push and release tests were conducted, and the conductive body with 1% CNT was chosen due to high sensitivity, fast response, and stability in reading output. Experimental results, using a feed-forward neural network, showed that the sensor can estimate the applied normal force based on the changes of resistance.

Wearable tactile sensors are significant in biomedical robotic applications where force feedback is important. In this work, a soft tactile sensor is proposed for force localization. The tactile sensor was manufactured by using layer-by-layer technique that enables flexibility. The sensor has 9 lead zirconate titanate (PZT) elements placed in 3 × 3 matrix form which are 4 × 4 mm2 and the spatial resolution is 3 mm. The voltage values gathered from the sensor were conditioned by a charge amplifier circuit. A human inspired machine learning procedure called Neural Networks was used for force localization. The success rates with respect to different network structures were presented and the maximum success was realized as 80.71%.

Tactile sensing is an emerging technological advancement in surgical robotics in order to probe interactions between confined tissue environments and instruments based on touch information. The tactile sense can assist in improving the efficiency of the whole practice and hence enhance precision, control, and safety during surgery. This paper demonstrates a distinct proof-of-concept therapeutic device equipped with a soft tactile sensor. The tactile sensor was custom-made using flexible piezoresistive materials and conductive ink, wrapped with a biocompatible hydrogel polymer matrix for safer human–tissue interactions. The proposed tactile sensor was then calibrated and its performance was compared with gold standard sensors. It was further tested with a continuous force (5 N) for an extended period of time (about 6 h) to address robustness and repeatability. The sensor showed a sensitivity of 0.833 N−1 and a drift of ≤1%. Successful cadaver experiment demonstrates the efficiency of tactile sensing assistance to clinicians.

The tactile sensor design and data measurements have been playing an important role in surface material recognition. In inevitable unstructured environments, the performance of the material classification is bottlenecked by multimodal deficiency or data collection intermittency. This article investigates the influence of surface tactile data quantity on material classification in unstructured environments. We extracted tactile data features according to the material-surface-texture model and proposed an approach to determine the scope of the time window of tactile data. We utilized the machine learning classifiers to verify the effectiveness of the hand-designed features and the determined time window. Based on the combination of the Mel frequency cepstrum coefficient and statistics, the majority of the algorithms can classify the tactile data of the upper limit (60 ms in this article) with an accuracy of at least 85%. Exploiting tactile data of the lower limit (50 ms in this article), linear discriminant analysis, quadratic discriminant analysis, and support vector machine can achieve about 93% classification accuracy, and area under curve is about 0.99. The accuracy is not significantly improved with the time window beyond the upper limit, while the performance is degraded and unstable with it beneath the lower limit.

This paper presents a review of Tactile Sensing Systems, with an emphasis on their application to the non-invasive characterization of tumors. Emulating the perceptual mechanism of the human skin, the Tactile Sensing Systems characterize tumors using touch sensors by quantifying the mechanical properties such as size and elasticity. The authors survey several tactile transduction methods: capacitive, piezoresistive, piezoelectric, magnetic, and optical. The advantages and disadvantages of different tactile sensors are discussed. The complex human sense of touch is emulated using tactile sensor data, novel data processing algorithms, and near real-time interpretation in a human-readable format. Tactile Sensing Systems utilize tactile sensors and other subsystems to come up with accurate mechanical properties of the touched objects. We review Elasticity Determination Systems, which are a special case of Tactile Sensing Systems. These systems are based on capacitive sensors, piezoelectric sensors, elastography, and optical tactile sensors. Then the optical Tactile Sensing System is discussed in detail; architecture, sensing principle, and algorithms to compute a risk score. Moreover, a survey of multimodal Tactile Sensing Systems, which broaden the capabilities of existing tactile sensing systems, is presented. The paper concludes with discussions and future research directions.

Enormous benefits of using 4D printing technology referring to added dimension time combining 3D printing technology with high level smart material shape changing, engineering software has currently enhanced its applicability in industry. Triggered by external stimuli 4D printed parts are pleated & unpleated by adding geometric coding & its pressure and resistance is measured by mechanically compliant soft tactile sensor by the physical interaction with environmental dynamics & ambiguity using piezo resistive technique for its electrical resistance distinct electric potential.This paper designs Mechanical walker 4D printed which will be integral part of robotic system helpful for path tracking in automated guided vehicle for automate route system with the use of tactile sensors utilizing haptic touch module.This walker will incorporate the safety intelligence using sensing stimulus by NiTinol providing close proximity interaction procedure.

In this study, we developed a dynamic positioning sensing (DPS) system for estimating size and depth of embedded objects. The DPS System is comprised of a tactile imaging sensor (TIS), a near infrared diffuse optical imaging (DOI) unit. The TIS have a flexible and transparent sensing probe, a LED (light emitting diode) module, and a CCD camera with lens. The light from the LED-illuminated probe is scattered when a force is applied to the probe, and captured by the camera as a tactile image. TIS determined the tumor size by correlating applied force, depth and number of pixel in tactile image. On the other hand, using a near infrared laser as source and the CCD camera as detector, we obtained the diffuse optical images. From these images, we computed the absorption coefficient of the embedded tumor phantom. We maneuvered the source-detector simultaneously for collecting diffuse optics information. We termed this maneuver as dynamic positioning. The TIS provided a priori location information. The combination of the absorption coefficient, tactile data, and dynamic positioning method improved the size and depth estimation. The experimental results showed that the TIS estimated the tumor phantom size with 7.23% error, while the DPS System measured the size with 0.8% error. The TIS depth estimation error was 41.83%, and the DPS System reduced depth measurement error to 20.67%.

Robot grasping and manipulation relies mainly on two types of sensory data: vision and tactile sensing. Localisation and recognition of the object is typically done through vision alone, while tactile sensors are commonly used for grasp control. Vision performs reliably in uncluttered environments, but its performance may deteriorate when the object is occluded, which is often the case during a manipulation task, when the object is in-hand and the robot fingers stand between the camera and the object. This paper presents a method to use the robot's sense of touch to refine the knowledge of a manipulated object's pose from an initial estimate provided by vision. The objective is to find a transformation on the object's location that is coherent with the current proprioceptive and tactile sensory data. The method was tested with different object geometries and proposes applications where this method can be used to improve the overall performance of a robotic system. Experimental results show an improvement of around 70% on the estimate of the object's location when compared to using only vision.

This article presents the artificial intelligence for object recognition by touching method with the tactile sensor, which has similar structural characteristics as the human hand. The object recognition uses a tactile glove sensor with small tactile sensors to spread throughout the glove, and there are touching points similar to human hands. Using the glove sensor to grasp the object that will obtain an image, there is tactile image. These images were used to compare recognition performance with two techniques: the Bag of Word (BoW) and the Convolutional Neural Network (CNN). In the experiment, the tactile glove performs 20 different objects. The BoW technique, the Scale Invariant Feature Transform (SIFT), has been used to feature extraction and then classified with K Nearest Neighbors (KNN) to evaluate the performance. The results illustrate that the accuracy of BoW and CNN is 70.80% and 97.20%, respectively. When comparing both techniques, it was found that the CNN had higher accuracy of about 26.40%. The results clearly show that CNN was more performance than BoW. Therefore, it is suitable to analyze tactile glove recognition, which can be applied to the recognition system of humanoid robots.