In the past few years, soft robotics has rapidly become an emerging research topic, opening new possibilities for addressing real-world tasks Perception can enable robots to effectively explore the unknown world, and interact safely with humans and the environment Among all extero- and proprioception modalities, the detection of mechanical cues is vital, as with living beings A variety of soft sensing technologies are available today, but there is still a gap to effectively utilize them in soft robots for practical applications Here, the developments in soft robots with mechanical sensing are summarized to provide a comprehensive understanding of the state of the art in this field Promising sensing technologies for mechanically perceptive soft robots are described, categorized, and their pros and cons are discussed Strategies for designing soft sensors and criteria to evaluate their performance are outlined from the perspective of soft robotic applications Challenges and trends in developing multimodal sensors, stretchable conductive materials and electronic interfaces, modeling techniques, and data interpretation for soft robotic sensing are highlighted The knowledge gap and promising solutions toward perceptive soft robots are discussed and analyzed to provide a perspective in this field

https://onlinelibrary.wiley.com/doi/pdf/10.1002/advs.201800541

Toward Perceptive Soft Robots: Progress and Challenges

Over the last two decades, considerable scientific and technological efforts have been devoted to developing tactile sensing based on a variety of transducing mechanisms, with prospective applications in many fields such as human–machine interaction, intelligent robot tactile control and feedback, and tactile sensorized minimally invasive surgery. This paper starts with an introduction of human tactile systems, followed by a presentation of the basic demands of tactile sensors. State-of-the-art tactile sensors are reviewed in terms of their diverse sensing mechanisms, design consideration, and material selection. Subsequently, typical performances of the sensors, along with their advantages and disadvantages, are compared and analyzed. Two major potential applications of tactile sensing systems are discussed in detail. Lastly, we propose prospective research directions and market trends of tactile sensing systems.

Recent Progress in Technologies for Tactile Sensors

We propose a new type of tactile sensor that can detect both the contact force and hardness of an object. It consists of a diaphragm with a mesa structure, a piezo-resistive displacement sensor on the diaphragm, and a chamber for pneumatic actuation. An array of these sensors can detect the two-dimensional contact force-distribution and hardness-distribution information and the surface texture of the contacted object. We theoretically analyzed the operation of the tactile sensor, and designed its specifications for a device for detecting the touch of a human finger. We fabricated devices of several different sizes by micromachining technologies to prove the principle. The sensor element is 6.0 mm x 6.0 mm x 0.4 mm, and it has a displacement sensor element of piezo-resistance at the periphery of the diaphragm structure. We experimentally confirmed the characteristics of the device by using pneumatic actuation.

Active tactile sensor for detecting contact force and hardness of an object

Tactile Internet (TI) is envisioned to create a paradigm shift from the content-oriented communications to steer/control-based communications by enabling real-time transmission of haptic information (i.e., touch, actuation, motion, vibration, surface texture) over Internet in addition to the conventional audiovisual and data traffics. This emerging TI technology, also considered as the next evolution phase of Internet of Things (IoT), is expected to create numerous opportunities for technology markets in a wide variety of applications ranging from teleoperation systems and Augmented/Virtual Reality (AR/VR) to automotive safety and eHealthcare towards addressing the complex problems of human society. However, the realization of TI over wireless media in the upcoming Fifth Generation (5G) and beyond networks creates various non-conventional communication challenges and stringent requirements in terms of ultra-low latency, ultra-high reliability, high data-rate connectivity, resource allocation, multiple access and quality-latency-rate tradeoff. To this end, this paper aims to provide a holistic view on wireless TI along with a thorough review of the existing state-of-the-art, to identify and analyze the involved technical issues, to highlight potential solutions and to propose future research directions. First, starting with the vision of TI and recent advances and a review of related survey/overview articles, we present a generalized framework for wireless TI in the Beyond 5G Era including a TI architecture, the main technical requirements, the key application areas and potential enabling technologies. Subsequently, we provide a comprehensive review of the existing TI works by broadly categorizing them into three main paradigms; namely, haptic communications, wireless AR/VR, and autonomous, intelligent and cooperative mobility systems. Next, potential enabling technologies across physical/Medium Access Control (MAC) and network layers are identified and discussed in detail. Also, security and privacy issues of TI applications are discussed along with some promising enablers. Finally, we present some open research challenges and recommend promising future research directions.

/pdf/toward-tactile-internet-in-beyond-5g-era-recent-advances-3w8qex819e.pdf

Toward Tactile Internet in Beyond 5G Era: Recent Advances, Current Issues, and Future Directions

The coupling of waves between the piezoelectric generators, detectors, and propagating media is challenging due to mismatch in the acoustic properties. The mismatch leads to the reverberation of waves within the transducer, heating, low signal-to-noise ratio, and signal distortion. Acoustic impedance matching increases the coupling largely. This article presents standard methods to match the acoustic impedance of the piezoelectric sensors, actuators, and transducers with the surrounding wave propagation media. Acoustic matching methods utilizing active and passive materials have been discussed. Special materials such as nanocomposites, metamaterials, and metasurfaces as emerging materials have been presented. Emphasis is placed throughout the article to differentiate the difference between electric and acoustic impedance matching and the relation between the two. Comparison of various techniques is made with the discussion on capabilities, advantages, and disadvantages. Acoustic impedance matching for specific and uncommon applications has also been covered.

A Review of Acoustic Impedance Matching Techniques for Piezoelectric Sensors and Transducers.

During the last decades, smart tactile sensing systems based on different sensing techniques have been developed due to their high potential in industry and biomedical engineering. However, smart tactile sensing technologies and systems are still in their infancy, as many technological and system issues remain unresolved and require strong interdisciplinary efforts to address them. This paper provides an overview of smart tactile sensing systems, with a focus on signal processing technologies used to interpret the measured information from tactile sensors and/or sensors for other sensory modalities. The tactile sensing transduction and principles, fabrication and structures are also discussed with their merits and demerits. Finally, the challenges that tactile sensing technology needs to overcome are highlighted.

https://www.mdpi.com/1424-8220/17/11/2653/pdf

Novel Tactile Sensor Technology and Smart Tactile Sensing Systems: A Review.

In this study, a multiple kernel learning support vector machine algorithm is proposed for the identification of EEG signals including mental and cognitive tasks, which is a key component in EEG-based brain computer interface (BCI) systems. The presented BCI approach included three stages: (1) a pre-processing step was performed to improve the general signal quality of the EEG; (2) the features were chosen, including wavelet packet entropy and Granger causality, respectively; (3) a multiple kernel learning support vector machine (MKL-SVM) based on a gradient descent optimization algorithm was investigated to classify EEG signals, in which the kernel was defined as a linear combination of polynomial kernels and radial basis function kernels. Experimental results showed that the proposed method provided better classification performance compared with the SVM based on a single kernel. For mental tasks, the average accuracies for 2-class, 3-class, 4-class, and 5-class classifications were 99.20%, 81.25%, 76.76%, and 75.25% respectively. Comparing stroke patients with healthy controls using the proposed algorithm, we achieved the average classification accuracies of 89.24% and 80.33% for 0-back and 1-back tasks respectively. Our results indicate that the proposed approach is promising for implementing human-computer interaction (HCI), especially for mental task classification and identifying suitable brain impairment candidates.

https://www.mdpi.com/1424-8220/14/7/12784/pdf

Classification of EEG signals using a multiple kernel learning support vector machine.

The early detection of subjects with probable cognitive deficits is crucial for effective appliance of treatment strategies. This paper explored a methodology used to discriminate between evoked related potential signals of stroke patients and their matched control subjects in a visual working memory paradigm. The proposed algorithm, which combined independent component analysis and orthogonal empirical mode decomposition, was applied to extract independent sources. Four types of target stimulus features including P300 peak latency, P300 peak amplitude, root mean square, and theta frequency band power were chosen. Evolutionary multiple kernel support vector machine (EMK-SVM) based on genetic programming was investigated to classify stroke patients and healthy controls. Based on 5-fold cross-validation runs, EMK-SVM provided better classification performance compared with other state-of-the-art algorithms. Comparing stroke patients with healthy controls using the proposed algorithm, we achieved the maximum classification accuracies of 91.76% and 82.23% for 0-back and 1-back tasks, respectively. Overall, the experimental results showed that the proposed method was effective. The approach in this study may eventually lead to a reliable tool for identifying suitable brain impairment candidates and assessing cognitive function.

/pdf/identifying-patients-with-poststroke-mild-cognitive-1egc72034c.pdf

Identifying patients with poststroke mild cognitive impairment by pattern recognition of working memory load-related ERP.

A brain computer interface (BCI) system translates a person's brain activity into useful control or communication signals. In this paper, an effective P300-based BCI identification algorithm using median filtering and Bayesian classifier is proposed to improve the classification accuracy and computation efficiency of P300-based BCI. Median filtering is firstly applied to remove noises and Bayesian Linear Discriminant Analysis (BLDA) is then employed for classification. Testing on the P300 speller paradigm in dataset II of 2004 BCI Competition III, we show that a 90% average classification accuracy can be achieved and the highest accuracy is 100%. The proposed method is also computationally efficient and thus it represents a practical implementation for man-computer communication control, especially for on-line applications.

A P300-based BCI classification algorithm using median filtering and Bayesian feature extraction

To explore the change of brain connectivity in schizophrenics (SCZ), the resting-state EEG source functional connections of SCZ and healthy control (HC) were investigated in this paper. Different band single-layer networks, multilayer networks, and improved multilayer networks were constructed and their topological attributes were extracted. The topological attributes of SCZ and HC were automatically distinguished using ensemble learning methods called Ensemble Learning based on Trees and Soft voting method, and the effectiveness of different network construction methods was compared based on the classification accuracy. The results showed that the classification accuracy was 89.38% for α band network, 82.5% for multilayer network, and 86.88% for improved multilayer network. Comparing patients with SCZ to those with Alzheimer’s disease (AD), the classification accuracy of improved multilayer network was the highest, which was 88.12%. The power spectrum in the α band of SCZ was significantly lower than HC, whereas there was no significant difference between SCZ and AD. This indicated that the improved multilayer network can effectively distinguish SCZ and other groups not only when their power spectrum was significantly different. The results also suggested that the improved multilayer topological attributes were regarded as biological markers in the clinical diagnosis of patients with schizophrenia and even other mental disorders.

/pdf/abnormality-of-functional-connections-in-the-resting-state-23jnpkhx.pdf

Xiaoou Li

Papers

Novel Tactile Sensor Technology and Smart Tactile Sensing Systems: A Review.

Classification of EEG signals using a multiple kernel learning support vector machine.

Identifying patients with poststroke mild cognitive impairment by pattern recognition of working memory load-related ERP.

A P300-based BCI classification algorithm using median filtering and Bayesian feature extraction

Abnormality of Functional Connections in the Resting State Brains of Schizophrenics