Refine Search

New Search

Results in Journal Advanced Intelligent Systems: 474

(searched for: journal_id:(4221874))
Page of 10
Articles per Page
by
Show export options
  Select all
Priyanka Sharan, Charlie Maslen, Berk Altunkeyik, Ivan Rehor, , Thomas D. Montenegro-Johnson
Published: 28 July 2021
Advanced Intelligent Systems; doi:10.1002/aisy.202100068

Abstract:
Hydrogels have received increased attention due to their biocompatible material properties, adjustable porosity, ease of functionalization, tuneable shape, and Young's moduli. Initial work has recognized the potential that conferring out-of-equilibrium properties to these on the microscale holds and envisions a broad range of biomedical applications. Herein, a simple strategy to integrate multiple swimming modes into catalase-propelled hydrogel bodies, produced via stop-flow lithography (SFL), is presented and the different dynamics that result from bubble expulsion are studied. It is found that for “Saturn” filaments, with active poles and an inert midpiece, the fundamental swimming modes correspond to the first three fundamental shape modes that can be obtained by buckling elastic filaments, namely, I, U, and S-shapes.
Published: 28 July 2021
Advanced Intelligent Systems; doi:10.1002/aisy.202100063

Abstract:
The space environment offers unique challenges for robotic grippers and controllable attachment mechanisms. Applications include satellite and orbital debris capture, perching for free-floating robots inside the International Space Station, climbing rocky surfaces in planetary exploration tasks, and grasping asteroids and other rough substrates for drilling and sample collection operations. Many traditional adhesive technologies, such as pressure-sensitive adhesives, suction, and electromagnetism, are not tenable in the space environment due to the lack of an atmosphere (e.g., pressure-sensitive adhesives outgas and suction requires a pressure differential) or suitable substrates (e.g., materials for space applications are rarely ferromagnetic). Instead, a number of other technologies have shown promise for space, including bio-inspired fibrillar dry adhesives that offer controllable adhesion on both flat and curved smooth surfaces, electrostatic adhesives that work on smooth surfaces but also rougher surfaces and fabrics, and microspines for rocky and rough substrates. Herein, a review of these technologies, focusing on their operation and providing examples of the technologies applied to space and other extraterrestrial missions is presented.
Yi Yu, Ran Peng, Zihe Chen, , Jinhua Li, Jianying Wang, Xinyu Liu, , Xianbao Wang
Published: 23 July 2021
Advanced Intelligent Systems; doi:10.1002/aisy.202100012

Abstract:
Soft robots, intelligent structures built up of smart soft materials, are capable of being programmed to perform delicate work. Recently, plenty of biomimetic soft robots with functionalities of grasping, sensing, searching, and transporting have been exploited by emulating activities of living creatures adapting to ecological environments. However, mass production of biomimetic soft robots has remained a grand challenge while maintaining stable pre-engineered functionalities under distinct circumstances, which significantly constrains their practical applications. To this end, a facile and scalable approach that can be utilized for mass-producing sandwich-structured photoresponsive polyimide (PI)/Au/low-density polyethylene (LDPE) nanocomposite films is reported. Attributed to the remote and precise-driven mode, reversible and stable actuation behavior, and the ultrarobust mechanical properties of the sandwich-structured PI/Au/LDPE nanocomposite films, it was possible to devise a variety of photoresponsive biomimetic soft robots such as artificial flytrap, directionally moveable caterpillar-inspired walker, and dolphin-like cruisable and loadable swimmer via simply tailoring them into predesigned geometries.
, Yanning Dai, Arokia Nathan
Published: 11 July 2021
Advanced Intelligent Systems; doi:10.1002/aisy.202100074

Abstract:
Touch and vision perception are two important functions humans use to interact with the real world. To mimic human-like abilities, tactile- and visual-sensing-based intelligent humanoids have emerged and are going through a fast phase of development. Studies have demonstrated that the combination of tactile and visual information not only enables humanoids to better learn the environment, but also allows them to have pseudocognitive ability. Being a new and rapidly developing field of research, a significant growth in articles reporting different aspects of sensing and related machine learning is being witnessed. To help readers comprehensively understand the fundamentals and insights, and the current state of the art, this review is compiled to explain the working mechanisms of tactile and visual sensing, introduce the application of intelligent humanoids in diverse scenarios, discuss current challenges, and predict future trends.
Shaohua Chen, Matthew Wei Ming Tan, Xuefei Gong,
Published: 11 July 2021
Advanced Intelligent Systems; doi:10.1002/aisy.202100075

Abstract:
Soft electrical actuators driven by low voltages are promising for interactive human–machine interfaces (iHMI) applications including executing orders to complete various tasks and communicating with humans. The attractive features of low-voltage soft electrical actuators include their good safety, low power consumption, small system size, and nonrigid or deformable characteristics. This review covers three typical classes of electrical actuators, namely, electrochemical, electrothermal, and other electrical (dielectric, electrostatic, ferroelectric, and plasticized gel) actuators according to their mechanism and working potential range. For each kind of actuators, the advantages, working principle, device configuration/design, materials selection, recent progress, and potential applications for iHMI are summarized, with the strategies for enhancing the actuation performance under low voltages being highlighted. Finally, the challenges for those soft actuators and possible solutions are discussed.
Chengjun Wang, Min Cai, Zengming Hao, Shuang Nie, Changying Liu, Honggen Du, Jian Wang, Weiqiu Chen,
Advanced Intelligent Systems; doi:10.1002/aisy.202100031

Abstract:
The concurrent collection of surface electromyography (sEMG) and strain signals is important for many applications, such as human–machine interaction, sign language recognition, and clinical evaluation of muscle function. Nevertheless, the conventional sensor systems made of rigid, bulky components cannot provide a reliable, conformal interface for accurate, continuous measurements of the epidermal physiological signals. Herein, a skin-interfaced, multifunctional epidermal sensor patch with characteristics of mechanical softness, large stretchability, and wearable conformability for multimodal measurements of sEMG signals and associated skin deformations from various muscle activities and joint motions is reported. The sensor patch features two pairs of stretchable sEMG electrodes and two thin, miniaturized strain sensors, which are connected by stretchable filamentary serpentine interconnects in an open-meshed structure. Experimental and computational studies reveal the design and operation of the sensor patch, which exhibit stable and repetitive performance even under a 30% stretching strain level. Demonstrations of the sensor patch on the wrist for simple sign language recognition and on the lower back for the flexion-relaxation phenomenon illustrate its potential for the comprehensive assessment of the muscle activities and related motions of muscle joints.
Vivek Ramachandran, , ,
Advanced Intelligent Systems; doi:10.1002/aisy.202100043

Abstract:
People learn motor activities best when they are conscious of their errors and make a concerted effort to correct them. While haptic interfaces can facilitate motor training, existing interfaces are often bulky and do not always ensure post-training skill retention. Herein, a programmable haptic sleeve composed of textile-based electroadhesive clutches for skill acquisition and retention is described. Its functionality in a motor learning study where users control a drone's movement using elbow joint rotation is shown. Haptic feedback is used to restrain elbow motion and make users aware of their errors. This helps users consciously learn to avoid errors from occurring. While all subjects exhibited similar performance during the baseline phase of motor learning, those subjects who received haptic feedback from the haptic sleeve committed 23.5% fewer errors than subjects in the control group during the evaluation phase. The results show that the sleeve helps users retain and transfer motor skills better than visual feedback alone. This work shows the potential for fabric-based haptic interfaces as a training aid for motor tasks in the fields of rehabilitation and teleoperation.
Pengli Dong, Weizhong Xu, Zhongwen Kuang, Youxing Yao, Zhiqin Zhang, Daoyou Guo, Huaping Wu, ,
Advanced Intelligent Systems; doi:10.1002/aisy.202100030

Abstract:
Smart hydrogel actuators with programmable anisotropic structures present fascinating prospects considering their distinctive shape transformation and controllable environmental responsiveness under external stimuli. However, the design of anisotropic hydrogels with simple and universal fabrication and programmable functionality is challenging for their valuable applications in smart actuators and soft robots. Herein, a simple, green, and devisable strategy is proposed to construct a heterogeneous porous hydrogel system by the different liquid diffusion (such as amyl alcohol, water, and ethanol) into a monomeric precursor solution of thermosensitive hydrogels. The well-defined micro/nanoporous gradient and patterned structures related to selective liquid stratification and interfacial diffusion favor the fast response and accurate programmable deformation of hydrogels under temperature stimuli. Inspiringly, this simple diffusion-driven tactic can be perfectly applicable for different responsive hydrogels with programmable multifunctionality by adding functional nanomaterials into the diffusible liquid. This green, general, and facile diffusion-driven strategy provides significant guidance for fabricating environmentally responsive hydrogels with tailorable functionality for their multipurpose applications in drug delivery, bioengineering, smart actuators, and soft robots.
Zhedong Wang, Chao Qian, Tong Cai, Longwei Tian, Zhixiang Fan, Jian Liu, Yichen Shen, Li Jing, Jianming Jin, Er-Ping Li, et al.
Advanced Intelligent Systems; doi:10.1002/aisy.202100066

Andrew Y. Chen, Elizabeth Pegg, Ailin Chen, Zeqing Jin,
Advanced Intelligent Systems; doi:10.1002/aisy.202100019

Abstract:
In recent years, the intersection of 3D printing and “smart” stimuli-responsive materials has led to the development of 4D printing, an emerging field that is a subset of current additive manufacturing research. By integrating existing printing processes with novel materials, 4D printing enables the direct fabrication of sensors, controllable structures, and other functional devices. Compared to traditional manufacturing processes for smart materials, 4D printing permits a high degree of design freedom and flexibility in terms of printable geometry. An important branch of 4D printing concerns electroactive materials, which form the backbone of printable devices with practical applications throughout biology, engineering, and chemistry. Herein, the recent progress in the 4D printing of electroactive materials using several widely studied printing processes is reviewed. In particular, constituent materials and mechanisms for their preparation and printing are discussed, and functional electroactive devices fabricated using 4D printing are highlighted. Current challenges are also described and some of the many data-driven opportunities for advancement in this promising field are presented.
Janek Buhl, Ala Cojocaru,
Advanced Intelligent Systems; doi:10.1002/aisy.202100037

Abstract:
Organic light-emitting diodes (OLEDs) offer novel and unique possibilities for illumination. The realization of transparent and flexible devices facilitates integration in everyday objects such as windows, clothing, or packaging labels, while posing new challenges to product engineering. Innovative OLED light sources, fulfilling multiple purposes additional to lighting, are likely to be touched and consciously observed far more frequently than conventional illuminants. Herein, a polymer coating used to customize tactile and visual perceptions of OLED substrate surfaces is demonstrated. Tetrapodal zinc oxide particles and color pigments are incorporated in a poly(methyl methacrylate) matrix to modify surface roughness and color impression of the coating. Variation of the particle content and composition yields different combinations of roughness characteristics, thus altering tactile surface perception and light scattering. Utilization of color pigments exhibiting low transmission dispersion allows for changes of the coating color while maintaining the original OLED emission color. The presented coating concept is expected to be a promising approach to adjust haptic and optical device properties to specific application requirements while maintaining spectral OLED emission characteristics.
Tanyong Wei, Junyang Li, Liushuai Zheng, Cheng Wang, Feng Li, Hua Tian,
Advanced Intelligent Systems; doi:10.1002/aisy.202100052

Abstract:
Microrobots with simultaneously improved degradability and mechanical strength are highly demanded in performing in vivo delivery tasks in clinical applications. The properties of degradability and mechanical strength are contradictory for many materials used to make microrobots. This article proposes a new design that can result in 3D cell culture microrobots with improved degradability and mechanical strength from the following perspectives. First, the mechanical strength of a microrobot is improved using triangle patterns to replace hexagon pattern in the microrobot structure, which can provide more supporting grids to obtain increased mechanical strength. Second, the relationship between structural design and material composition in relation to the mechanical strength of microrobot is investigated. The study reveals that triangle-patterned microrobots have increased mechanical strength compared with hexagon-patterned microrobots, thereby allowing high composition of degradable material that leads to the fast degradation of the microrobot. It is also shown that the triangle-patterned microrobots can maintain the same structural integrity and cell capacity as hexagon-patterned microrobots. Finally, the demonstration shows that the triangle-patterned microrobot can be precisely navigated in microfluidic channels. This article successfully demonstrates that the degradability and mechanical strength can be improved simultaneously through the microrobot structural design.
Wei Zhang, Lunshuai Pan, Xuelong Yan, Guangchao Zhao, Hong Chen, Xingli Wang, Beng Kang Tay, , Jiangyu Li,
Published: 5 July 2021
by 10.1002
Advanced Intelligent Systems; doi:10.1002/aisy.202100041

Abstract:
Memristors offer great advantages as a new hardware solution for neuromorphic computing due to their fast and energy-efficient matrix vector multiplication. However, the nonlinear weight updating property of memristors makes it difficult to be trained in a neural network learning process. Several compensation schemes have been proposed to mitigate the updating error caused by nonlinearity; nevertheless, they usually involve complex peripheral circuits design. Herein, stochastic and adaptive learning methods for weight updating are developed, in which the inaccuracy caused by the memristor nonlinearity can be effectively suppressed. In addition, compared with the traditional nonlinear stochastic gradient descent (SGD) updating algorithm or the piecewise linear (PL) method, which are most often used in memristor neural network, the design is more hardware friendly and energy efficient without the consideration of pulse numbers, duration, and directions. Effectiveness of the proposed method is investigated on the training of LeNet-5 convolutional neural network. High accuracy, about 93.88%, on the Modified National Institute of Standards and Technology handwriting digits datasets is achieved (with typical memristor nonlinearity as ±1), which is close to the network with complex PL method (94.7%) and is higher than the original nonlinear SGD method (90.14%).
Hyungyo Kim, Joon Hwang, Dongseok Kwon, Jangsaeng Kim, Min-Kyu Park, Jiseong Im, ,
Published: 5 July 2021
by 10.1002
Advanced Intelligent Systems; doi:10.1002/aisy.202100064

Abstract:
On-chip training of neural networks (NNs) is regarded as a promising training method for neuromorphic systems with analog synaptic devices. Herein, a novel on-chip training method called direct gradient calculation (DGC) is proposed to substitute conventional backpropagation (BP). In this method, the gradients of a cost function with respect to the weights are calculated directly by sequentially applying a small temporal change to each weight and then measuring the change in cost value. DGC achieves a similar accuracy to that of BP while performing a handwritten digit classification task, validating its training feasibility. In particular, DGC can be applied to analog hardware-based convolutional NNs (CNNs), which is considered to be a challenging task, enabling appropriate on-chip training. A hybrid method is also proposed that efficiently combines DGC and BP for training CNNs, and the method achieves a similar accuracy to that of BP and DGC while enhancing the training speed. Furthermore, networks utilizing DGC maintain a higher level of accuracy than those using BP in the presence of variations in hardware (such as synaptic device conductance and neuron circuit component variations) while requiring fewer circuit components.
Beilei Wang, Wenxin Wei, Zhuo Shao, Qin Qin, Zhiyong Wang, Yin Jia, Jie Guo, Yanan Pang, Lei Jiang, Gang Jin, et al.
Advanced Intelligent Systems; doi:10.1002/aisy.202100033

Huihan Li, Shaocong Wang, Xumeng Zhang, Wei Wang, Rui Yang, Zhong Sun, Wanxiang Feng, Peng Lin, Zhongrui Wang, , et al.
Advanced Intelligent Systems; doi:10.1002/aisy.202100017

Abstract:
The emergence of memristors with potential applications in data storage and artificial intelligence has attracted wide attentions. Memristors are assembled in crossbar arrays with data bits encoded by the resistance of individual cells. Despite the proposed high density and excellent scalability, the sneak-path current causing cross interference impedes their practical applications. Therefore, developing novel architectures to mitigate sneak-path current and improve efficiency, reliability, and stability may benefit next-generation storage-class memory (SCM). Moreover, conventional digital computers face the von-Neumann bottleneck and the slowdown of transistors’ scaling, imposing a big challenge to hardware artificial intelligence. Memristive crossbar features colocation of memory and processing units, as well as superior scalability, making it a promising candidate for hardware accelerating machine learning and neuromorphic computing. Herein, first, crossbar architecture is introduced. Then, for storage, the origin of sneak-path current is reviewed and techniques to mitigate this issue from the angle of materials and circuits are discussed. Computing wise, the applications of memristive crossbars in both machine learning and neuromorphic computing are surveyed, focusing on the structure of unit cells, the network topology, and the learning types. Finally, a perspective on future engineering and applications of memristive crossbars is discussed.
Shengshun Duan, Binghao Wang, Yucheng Lin, Yinghui Li, Di Zhu, , Jun Xia, Wei Lei, Baoping Wang
Published: 1 July 2021
by 10.1002
Advanced Intelligent Systems; doi:10.1002/aisy.202100056

Abstract:
Wearable sensors with water resistance and mechanical durability are of great value in dealing with long-term movement and remote control in harsh environments. However, achieving high sensitivity with long-term stability and real-time remote control in a watery environment is still a challenge. Herein, the waterproof wearable sensors with good mechanical robustness composed of laser-induced graphene and in situ-coated protective silicone layers are reported. By being integrated with high-capacitance ion-gel dielectrics, the conformal sensors can detect multiple stimuli, including strain, temperature, and pressure. The long-term water resistance of strain sensors is evaluated by continuously monitoring the resistance in underwater, sweat, and saline environment for up to 5.5 h. Underwater wireless remote control of a robotic hand is further demonstrated by mounting five sensor arrays. Moreover, different finger gestures are well recognized, making these sensor devices promising candidates for versatile waterproof wearable electronics and robotics technology.
Anastasia Koivikko, Dirk-Michael Drotlef, Cem Balda Dayan, Veikko Sariola,
Published: 1 July 2021
by 10.1002
Advanced Intelligent Systems; doi:10.1002/aisy.202100034

Abstract:
A 3D-printed pneumatically actuated soft suction gripper with an elastomer film is proposed. Suction in such gripper is actively controlled by applying a negative pressure behind the film. The elastomeric gripper body is 3D-printed, making it easy to customize and integrate into future robotic gripping systems. The gripper can pick a wide variety of objects, such as delicate fruits, small parts, and parts with uneven loads, with high pull-off forces (over 7.4 N with ∅ 20 mm/55 kPa). The achieved pull-off forces are significantly higher than the previously reported suction cup grippers with films and more comparable with commercial vacuum grippers. The pull-off forces show no significant differences with surfaces of varying roughness (up to root-mean-square roughness of 5.66 μm) and the gripper is able to pick and release target objects repeatedly. The gripper is also compared with a commercial vacuum gripper with comparable dimensions. It outperforms the commercial gripper in the case of fragile objects, objects smaller than the gripper diameter, and objects with uneven loads. It can apply high pull-off forces while having controllable release, and is suitable for gripping a wide variety of real-world objects, including heavy, rough, small, thin, and fragile ones.
Published: 29 June 2021
Advanced Intelligent Systems; doi:10.1002/aisy.202100049

Abstract:
Light detection and ranging (LiDAR) systems are becoming crucial for measuring the distance and creating a point cloud of the local environment, critical data for artificial intelligence to enable collision-avoidance mechanisms. However, LiDAR utilizes radiation in the near-infrared (NIR) region of the electromagnetic spectrum, which is prone to complete absorption by typical dark (such as painted by carbon black) colored objects, leading to loss of timely data points. Till date a very limited number of solutions have been put forward to address this. Herein, nanocrystallites of copper (II) oxide with specific prevalence of crystal facets that create nearly perfect black material at visible wavelengths are proposed. The sharp transition of absorbance near 700 nm wavelength light is attributed to the near-unity ratio of (−111)/(111) the crystal facets and a crystal size of around 100 Å for the (−111) plane. Although indistinguishable from carbon black and with the same degree of measured blackness (My value 135.5), the nanocrystalline CuO shows 1500% better detectability by LiDAR. The study paves the way for the unconstrained use of dark objects in future society and infrastructure, moving a step closer toward fully autonomous operation of vehicles and robots.
Zhi Jiang, Ying Jiang, Nuan Chen,
Published: 29 June 2021
Advanced Intelligent Systems; doi:10.1002/aisy.202100071

Abstract:
Artificial visual electronics that mimic the structure and function of human eyes can be a powerful tool to provide visual feedback in the closed-loop sensation/action systems, which can be beneficial to achieve sophisticated functions in a precise and efficient way. Herein, how artificial visual electronics work in the closed-loop sensation/action systems, mimicking the human eyes for human behaviors, followed by how artificial visual electronics are utilized in various fields are introduced. To fully mimic the human eyes, how to achieve the structural similarity of artificial visual electronics with eyeballs is highlighted, and focused on the key component, i.e., retina-like 3D light-detecting imagers. When combined with the machine-learning method, such retina-like 3D imagers are expected to significantly benefit the closed-loop sensation/action systems.
Published: 28 June 2021
Advanced Intelligent Systems, Volume 3; doi:10.1002/aisy.202170053

Kaisong Yuan, Marta Pacheco, ,
Published: 28 June 2021
Advanced Intelligent Systems, Volume 3; doi:10.1002/aisy.202170052

, Muhammad Ilyas,
Published: 26 June 2021
by 10.1002
Advanced Intelligent Systems; doi:10.1002/aisy.202100051

Abstract:
Direct laser lithography (DLL) is a key enabling technology for 3D constructs at the microscale and its potential is rapidly growing toward the development of active microstructures. The rationale of this work is based on the different involved methodology, which is referred as indirect, when passive microstructures become active through postprocessing steps, and direct, when active structures are directly obtained by fabricating microstructures with active materials or by introducing heterogeneous mechanical properties and specific design. An in-depth analysis of both indirect and direct methods is provided. In particular, the wide range of materials and strategies involved in each method is reported, including advantages and disadvantages, as well as examples of fabricated structures and their applications. Finally, the different techniques are briefly summarized, and critically discussed by highlighting how the new synergies between DLL and active materials are opening completely new scenarios, in particular for sensing (e.g., mechanical) and actuation at the microscale.
Brian Elder, ZongHao Zou, Samannoy Ghosh, Oliver Silverberg, Taylor E. Greenwood, Ebru Demir, Vivian Song-En Su, On Shun Pak,
Published: 26 June 2021
by 10.1002
Advanced Intelligent Systems; doi:10.1002/aisy.202100039

Abstract:
Reinforcement learning control methods can impart robots with the ability to discover effective behavior, reducing their modeling and sensing requirements, and enabling their ability to adapt to environmental changes. However, it remains challenging for a robot to achieve navigation in confined and dynamic environments, which are characteristic of a broad range of biomedical applications, such as endoscopy with ingestible electronics. Herein, a compact, 3D-printed three-linked-sphere robot synergistically integrated with a reinforcement learning algorithm that can perform adaptable, autonomous crawling in a confined channel is demonstrated. The scalable robot consists of three equally sized spheres that are linearly coupled, in which the extension and contraction in specific sequences dictate its navigation. The ability to achieve bidirectional locomotion across frictional surfaces in open and confined spaces without prior knowledge of the environment is also demonstrated. The synergistic integration of a highly scalable robotic apparatus and the model-free reinforcement learning control strategy can enable autonomous navigation in a broad range of dynamic and confined environments. This capability can enable sensing, imaging, and surgical processes in previously inaccessible confined environments in the human body.
Haohua Liang, Yongcheng He, Meihua Chen, Licheng Jiang, Zhishen Zhang, Xiaobo Heng, Lin Yang, Yanpeng Hao, XiaoMing Wei, , et al.
Published: 23 June 2021
Advanced Intelligent Systems; doi:10.1002/aisy.202100035

Abstract:
Strain sensors that can work sustainably and continuously without any external power supply are highly desirable for future wearable and implantable devices. Herein, a self-powered stretchable strain sensor based on the integration of mechanoluminescent phosphors with an elastomer optical fiber is proposed and developed. This mechanoluminescent optical fiber is capable of emitting light just driven by external strain, without the need of an external light source or electric power. The strain-induced emitted light can be collected and guided along the mechanoluminescent optical fiber. The sensor exhibits linear strain response up to 50% and high-accuracy strain measurement (±1%). Moreover, this optical fiber strain sensor displays consistent signals over 10 000 stretch–release motion cycles, which demonstrates the good durability of the sensor. Due to the excellent light confinement of the elastomer optical fiber, this strain sensor is demonstrated in both bright- and dark-field measurements, wearable gloves, and an implantable sensing device, thereby demonstrating potential as a promising technology for future self-powered optical sensor systems.
Qingzhou Wan, Marco Rasetto, Mohammad T. Sharbati, John R. Erickson, Sridhar Reddy Velagala, Matthew T. Reilly, Yiyang Li, ,
Published: 23 June 2021
Advanced Intelligent Systems; doi:10.1002/aisy.202100021

Abstract:
Neuromorphic computing has the great potential to enable faster and more energy-efficient computing by overcoming the von Neumann bottleneck. However, most emerging nonvolatile memory (NVM)-based artificial synapses suffer from insufficient precision, nonlinear synaptic weight update, high write voltage, and high switching latency. Moreover, the spatiotemporal dynamics, an important temporal component for cognitive computing in spiking neural networks (SNNs), are hard to generate with existing complementary metal–oxide–semiconductor (CMOS) devices or emerging NVM. Herein, a three-terminal, LixWO3-based electrochemical synapse (LiWES) is developed with low programming voltage (0.2 V), fast programming speed (500 ns), and high precision (1024 states) that is ideal for artificial neural networks applications. Time-dependent synaptic functions such as paired-pulse facilitation (PPF) and temporal filtering that are critical for SNNs are also demonstrated. In addition, by leveraging the spike-encoded timing information extracted from the short-term plasticity (STP) behavior in the LiWES, an SNNs model is built to benchmark the pattern classification performance of the LiWES, and the result indicates a large boost in classification performance (up to 128×), compared with those NO-STP synapses.
Kyung Seok Woo, Jaehyun Kim, Janguk Han, Jin Myung Choi, Woohyun Kim,
Published: 23 June 2021
Advanced Intelligent Systems; doi:10.1002/aisy.202100062

Abstract:
Herein, a true random number generator (TRNG) based on a CuxTe1−x diffusive memristor (DM) using its threshold switching (TS) behavior is reported. The intrinsic stochasticity of the TS behavior contributes to the randomness of the TRNG system. The switching behavior is discussed through field-induced nucleation theory and surface diffusion dynamics. Demonstrating the performance of TRNG as a hardware security application, the DM-based TRNG passes all 15 National Institute of Standards and Technology randomness tests without any post-processing step, even in high-temperature conditions. Moreover, a nonlinear-feedback shift register is implemented for a high-speed TRNG, producing the highest rate among the reported volatile-memristor-based TRNGs.
, Jing Li, Jie Deng, Shijing Zhang, Weishan Chen, Hui Xie, Jie Zhao
Published: 19 June 2021
Advanced Intelligent Systems; doi:10.1002/aisy.202100015

Abstract:
Miniaturization, fast motion, high resolution, high agility, and good adaptability are relatively contradictory characteristics in mobile robot design. It is indeed a challenge to satisfy these performances at the same time. Inspired by the arthropod metamerism in nature, herein, a millirobot composed of three piezoelectric segments is proposed. The millirobot is tethered for power, and the whole size of the millirobot is 58 × 44 × 12 mm; it uses several principles of arthropod locomotion, can carry loads and cross obstacles, and also has the rapidity and agility like a centipede through the coordination of multiple piezoelectric segments. Fast motion with a maximum speed of 516 mm s−1 is realized by operating at resonant mode, and stepping motion with a resolution of 0.44 μm is achieved by the pulsed sinusoidal mode. The widest speed range among published reports of millirobots is achieved (from 4.5e−3 to 9 BL s−1). Its agility surpasses other piezoelectric millirobots; the linear, steering, and rotational motions are performed and switched flexibly. The results show that fast motion, high resolution, wide speed range, high agility, large load capacity, good adaptability, and miniaturization are successfully achieved by the millirobot.
Can Cuhadar, Genevieve Pui Shan Lau,
Advanced Intelligent Systems; doi:10.1002/aisy.202100055

Abstract:
Convolutional neural networks (CNNs) have attracted much attention in recent years due to their outstanding performance in image classification. However, changes in lighting conditions can corrupt image segmentation conducted by CNN, leading to false object detection. Even though this problem can be mitigated using a more extensive CNN training set, the immense computational and energy resources required to continuously run CNNs during always-on applications, such as surveillance or self-navigation, pose a serious challenge for battery-reliant mobile systems. To tackle this longstanding problem, a vision sensor capable of autonomously correcting for sudden variations in light exposure, without invoking any complex object detection software, is proposed. Such video preprocessing is efficiently achieved using photovoltaic pixels tailored to be insensitive to specific ranges of light intensity alterations. In this way, the pixels behave similarly to neurons, wherein the execution of object detection software is only triggered when light intensities shift above a certain threshold value. This proof-of-concept device allows for efficient fault-tolerant object detection to be implemented with reduced training data as well as minimal energy and computational costs and demonstrates how hardware engineering can complement software algorithms to improve the overall energy efficiency of computer vision.
Fu-Xiang Liang, I-Ting Wang,
Advanced Intelligent Systems; doi:10.1002/aisy.202100007

Abstract:
The sustainability of ever more sophisticated artificial intelligence relies on the continual development of highly energy-efficient and compact computing hardware that mimics the biological neural networks. Recently, the neural firing properties have been widely explored in various spiking neuron devices, which could emerge as the fundamental building blocks of future neuromorphic/in-memory computing hardware. By leveraging the intrinsic device characteristics, the device-based spiking neuron has the potential advantage of a compact circuit area for implementing neural networks with high density and high parallelism. However, a comprehensive benchmark that considers not only the device but also the peripheral circuit necessary for realizing complete neural functions is still lacking. Herein, the recent progress of emerging spiking neuron devices and circuits is reviewed. By implementing peripheral analog circuits for supporting various spiking neuron devices in the in-memory computing architecture, the advantages and challenges in area and energy efficiency are discussed by benchmarking various technologies. A small or even no membrane capacitor, a self-reset property, and a high spiking frequency are highly desirable.
Xin Shu, Sameera Sansare, Di Jin, Xiangxiang Zeng, Kai-Yu Tong, , Renjie Zhou
Advanced Intelligent Systems; doi:10.1002/aisy.202000277

Abstract:
Leukocyte differential test is a widely carried out clinical procedure for screening infectious diseases. Existing hematology analyzers require labor-intensive work and a panel of expensive reagents. Herein, an artificial-intelligence-enabled reagent-free imaging hematology analyzer (AIRFIHA) modality is reported that can accurately classify subpopulations of leukocytes with minimal sample preparation. AIRFIHA is realized through training a two-step residual neural network using label-free images of isolated leukocytes acquired from a custom-built quantitative phase microscope. By leveraging the rich information contained in quantitative phase images, not only high accuracy is achieved in differentiating B and T lymphocytes, but also CD4 and CD8 T cells are classified, therefore outperforming the classification accuracy of most current hematology analyzers. The performance of AIRFIHA in a randomly selected test set is validated and is cross-validated across all blood donors. Due to its easy operation, low cost, and accurate discerning capability of complex leukocyte subpopulations, AIRFIHA is clinically translatable and can also be deployed in resource-limited settings, e.g., during pandemic situations for the rapid screening of infectious diseases.
Advanced Intelligent Systems; doi:10.1002/aisy.202100025

Abstract:
Reliable image perception is critical for living organisms. Biologic sensory organs and nervous systems evolved interdependently to allow apprehension of visual information regardless of spatial orientation. By contrast, convolutional neural networks usually have limited tolerance to rotational transformations. There are software-based approaches used to address this issue, such as artificial rotation of training data or preliminary image processing. However, these workarounds require a large computational effort and are mostly done offline. This work presents a bioinspired, robotic vision system with inherent rotation-invariant properties that may be taught either offline or in real time by feeding back error indications. It is successfully trained to counter the move of a human player in a game of Paper Scissors Stone. The architecture and operation principles are first discussed alongside the experimental setup. This is followed by performance analysis of pattern recognition under misaligned and rotated conditions. Finally, the process of online, supervised learning is demonstrated and analyzed.
, Emmanuel Dean-Leon, Julio Rogelio Guadarrama-Olvera, Florian Bergner,
Advanced Intelligent Systems; doi:10.1002/aisy.202100038

Abstract:
For physical human–robot interaction (pHRI) where multi-contacts play a key role, both robustness to achieve robot-intended motion and adaptability to follow human-intended motion are fundamental. However, there are tradeoffs during pHRI when their intentions do not match. This paper focuses on bipedal walking control during pHRI, which handles such tradeoff when a human and a humanoid robot having different footsteps locations and durations. To resolve this, a force-reactive walking controller is proposed by adequately combining ankle and stepping strategies. The ankle strategy maintains the robot's intention based on an analytically-optimal center of pressure, leading the robot to oppose resistance to multiple contacts from the human. Based on the robot's kinodynamic constraints and/or the confidence of the robot's intention, the stepping strategy updates the robot's footsteps based on the human's intention implied by the multiple contact forces. Consequently, the proposed walking control on pHRI mutually exchanges human–robot intentions in real-time, thereby achieving coordinated steps. With a full-sized humanoid robot that is able to detect multi-contacts in real-time, we succeeded in performing a long-term “box-step” with multi-contacts pHRI, demonstrating the robustness of our approach.
Yuyang Ji, Congcong Luan, Xinhua Yao, Jianzhong Fu,
Advanced Intelligent Systems; doi:10.1002/aisy.202000271

Abstract:
Recently, considerable achievements have been made with the advancements of smart structures, which are known for their controlled deformation, self-repair, and sensing characteristics. Such capabilities have significant potential in the field of bionics. 3D printing methods have revolutionized the high-resolution integrated manufacturing of complex smart structures, resulting in new types of soft robots, actuators, wearable flexible electronics, and biomedical equipment. There is therefore a need for academia and industry to receive an update on the status of these tools. For this reason, herein, a comprehensive overview of the latest progress in printing methods, materials, and applications of various smart structures is provided. Temperature- and electromagnetic-responsive smart structures are highlighted, in addition to self-healing and smart-sensing devices. Current exigencies and future development trends of 3D printing methods and smart structures are also summarized.
Rudra Mukherjee, Priyanka Ganguly,
Advanced Intelligent Systems; doi:10.1002/aisy.202100036

Abstract:
On-board sources of energy are critically needed for autonomous robots to work in unstructured environments for extended periods. Thus far, the power requirement of robots has been met through lead-acid and Li-ion batteries and energy harvesters. However, few advances such as light weight, the shape, and size of the batteries used in robotics have remained unchanged for several decades, even though if the research in energy storage has led to devices with flexible form factors. Besides being slow at adopting new energy technologies, robotics also appears to have settled with the idea of centralized energy, as evident from the battery backpack designs of several humanoids. This is in contrast with the biological world, where energy sources are distributed all over the body. Although several attempts have been made to imitate the distributed tactile skin, the energy distribution has strangely not caught attention. A robotic platform can benefit from increased energy density, lesser design complexities, improved body dynamics, and operational reliability with distributed energy. By focusing on the distributed energy, herein, the first comprehensive review supporting the benefits of bioinspired distributed energy in robotics and various energy-storage and energy-harvesting technologies that are available or are tuned to attain the same are presented.
William P. Weston-Dawkes, Iman Adibnazari, Yi-Wen Hu, Michael Everman, ,
Advanced Intelligent Systems; doi:10.1002/aisy.202100001

Abstract:
Controllable adhesion has the capability to enable mobile robots to move freely across vertical and inverted surfaces for applications such as inspection, exploration, and cleaning. Previous methods for generating controllable adhesion have relied on fluidic adhesion through suction forces, electromagnetic adhesion through magnetic or electrical interactions, or dry fibrillar structures. Herein, a new method for achieving controllable adhesion by vibrating a flexible plate near a surface, which generates a strong and controllable attraction force, is presented. This adhesion mechanism has the unique property of providing strong adhesion normal to a surface, but very low resistance to motion parallel to the surface, making it attractive for mobile robots. Adhesive capabilities of vibration-based adhesion (VBA) to characterize adhesive force dependence on vibration frequency and surface size are studied. Spatial pressure measurements within the adhesive zone, in combination with visualization of surface vibration modes, demonstrate that adhesion is localized to the center of the disk and decreases radially. A mobile robot to highlight the capabilities and robustness of VBA for payload transport, climbing to inversion transitions, and adhesion control is developed. Overall, a novel physical mechanism for robot-surface adhesion that is robust, controllable, and enables rapid low-friction locomotion is presented herein.
Hyunwoo Kim, JiHyeong Ma, Minki Kim, Jongseok Nam,
Advanced Intelligent Systems, Volume 3; doi:10.1002/aisy.202170045

Jiaojiao Wang, Xiaotian Zhang, Junehu Park, Insu Park, Evin Kilicarslan, Yongdeok Kim, Zhi Dou, ,
Advanced Intelligent Systems, Volume 3; doi:10.1002/aisy.202170049

Xin Ma, , Song Liu, Jingwen Zhang, Shengnan Liu, Teng Cao, Wenbin Lin, Dong Wu, Natan Roberto de Barros, Mohammad Reza Zare, et al.
Advanced Intelligent Systems, Volume 3; doi:10.1002/aisy.202170047

Advanced Intelligent Systems, Volume 3; doi:10.1002/aisy.202170048

Jiaqi Zhu, Liangxiong Lyu, Yi Xu, Huageng Liang, Xiaoping Zhang, Han Ding,
Advanced Intelligent Systems, Volume 3; doi:10.1002/aisy.202170046

, Eduardo Esmanhotto, Niccolo Castellani, Damien Querlioz, Elisa Vianello
Advanced Intelligent Systems; doi:10.1002/aisy.202000103

Abstract:
Neural networks cannot typically be trained locally in edge-computing systems due to severe energy constraints. It has, therefore, become commonplace to train them “ex situ” and transfer the resulting model to a dedicated inference hardware. Resistive memory arrays are of particular interest for realizing such inference hardware, because they offer an extremely low-power implementation of the dot-product operation. However, the transfer of high-precision software parameters to the imprecise and random conductance states of resistive memories poses significant challenges. Here, it is proposed that Bayesian neural networks can be more suitable for model transfer, because, such as device conductance states, their parameters are described by random variables. The ex situ training of a Bayesian neural network is performed, and then, the resulting software model is transferred in a single programming step to an array of 16 384 resistive memory devices. On an illustrative classification task, it is observed that the transferred decision boundaries and the prediction uncertainties of the software model are well preserved. This work demonstrates that resistive memory-based Bayesian neural networks are a promising direction in the development of resistive memory compatible edge inference hardware.
Yuting Wu, John Moon, Xiaojian Zhu,
Advanced Intelligent Systems; doi:10.1002/aisy.202000276

Abstract:
The advances of neural recording techniques have fostered rapid growth of the number of simultaneously recorded neurons, opening up new possibilities to investigate the interactions and dynamics inside neural circuitry. The high recording channel counts, however, pose significant challenges for data analysis because the required time and computational resources grow superlinearly with the data volume. Herein, the feasibility of real-time reconstruction of neural functional connectivity using a second-order memristor network is analyzed. Spike-timing-dependent plasticity, natively implemented by the internal dynamics of the memristor device, leads to the successful discovery of temporal correlations between pre- and postsynaptic spikes of the simulated neural circuits in an unsupervised fashion. The proposed system demonstrates high classification accuracy under a wide range of parameter settings considering indirect connections, synaptic weights, transmission delays, connection density, and so on, and enables the capturing of dynamic connectivity evolutions. The influence of device nonideal factors on detection accuracy is systematically evaluated, and the system shows robustness to initial weight randomness, and cycle-to-cycle and device-to-device variations. The proposed method allows direct mapping of neural connectivity onto the artificial memristor network and can lead to efficient front-end data analysis of high-density neural recording systems and potentially directly coupled bioartificial networks.
Kaisong Yuan, Marta Pacheco, ,
Advanced Intelligent Systems, Volume 3; doi:10.1002/aisy.202100002

Abstract:
Micro‐ and nanomotors are micro‐ and nanostructures capable of autonomous movement and collective behavior, mimicking natural counterparts. This review aims to give a recent perspective on micro‐ and nanomotors driven by intelligent mechanisms in action under the cooperative effect of the swarm of micromotors as their distinctive feature. Different energy sources and the factors that can influence cooperative micromotor motion are comprehensively covered, along with the underlying phenomena and related applications. The motion ability of micro/nanomotors, along with capabilities to reach a targeted destination, holds considerable promise to address remaining challenges in the environmental and biomedical fields.
Bruno Miguel Gil Rosa, Salzitsa Anastasova,
Advanced Intelligent Systems, Volume 3; doi:10.1002/aisy.202100053

Abstract:
Monitoring of intrabody cardiovascular parameters can benefit from implantation of miniature devices close to anatomical targets, thereby surpassing signal attenuation problems related to the propagation toward body surface while allowing localized sensing at the target site with higher precision. With proper electronic miniaturization, packaging, robustness, and power consumption reduction, such devices can harvest enough energy from the surrounding environment for proper operation. Herein, a near‐field communication (NFC)‐powered implantable device with acquisition channels for electrocardiogram, arterial pulse, and temperature measurements is introduced. It has been successfully deployed inside rodents for a 72‐h trial period to assess external powering and data communication in living animals. Experimental results obtained by this device demonstrate the potential for providing more reliable diagnostic information than that of external wearable devices.
Christopher M. Shaffer, Atharva Deo, Andrew Tudor, Rahul Shenoy, Cameron D. Danesh, Dhruva Nathan, Lawren L. Gamble, Daniel J. Inman,
Advanced Intelligent Systems; doi:10.1002/aisy.202100016

Abstract:
Unlike artificial intelligent systems based on computers which have to be programmed for specific tasks, the human brain “self-programs” in real time to create new tactics and adapt to arbitrary environments. Computers embedded in artificial intelligent systems execute arbitrary signal-processing algorithms to outperform humans at specific tasks, but without the real-time self-programming functionality, they are preprogrammed by humans, fail in unpredictable environments beyond their preprogrammed domains, and lack general intelligence in arbitrary environments. Herein, a synaptic resistor circuit that self-programs in arbitrary and unpredictable environments in real time is demonstrated. By integrating the synaptic signal processing, memory, and correlative learning functions in each synaptic resistor, the synaptic resistor circuit processes signals and self-programs the circuit concurrently in real time with an energy efficiency about six orders higher than those of computers. In comparison with humans and a preprogrammed computer, the self-programming synaptic resistor circuit dynamically modifies its algorithm to control a morphing wing in an unpredictable aerodynamic environment to improve its performance function with superior self-programming speeds and accuracy. The synaptic resistor circuits potentially circumvent the fundamental limitations of computers, leading to a new intelligent platform with real-time self-programming functionality for artificial general intelligence.
Advanced Intelligent Systems, Volume 3; doi:10.1002/aisy.202100022

Abstract:
Soft robots require actuators with integrated sensing components that perceive unstructured, dynamic environments without compromising their performance. However, many soft robotic systems still rely on external sensors, which affect the functionality, response time, and payload. To overcome these issues, herein a sensorized foam actuator (SFA) with a foam core that acts as both an actuator and a proprioception-sensing element is developed. The integrated modules can sense direct actuation and passive deformation due to extrinsic stresses through a specific pore shape evolution, which leads to a distinct variation in the resistivity pattern. In addition, a fiber-reinforced skin encapsulating the SFA facilitates a fast and efficient response. The SFA is able to lift more than 500 times its own weight with a load-withstanding capacity of 235 N, linear contraction up to 70% strain, and a recovery speed of 13.3 mm s−1. In addition, the SFA is lightweight (34 g), has low hysteresis (<4%), and can self-sense its current deformation state. As proof of concept, various soft robotic applications are presented such as compression piston-like motion, modular inchworm-like crawling locomotion, and a robotic trunk-like manipulation.
, Kittamet Pradidarcheep, Yu Kuwajima, Yumeta Seki, Shingo Maeda,
Advanced Intelligent Systems; doi:10.1002/aisy.202100004

Abstract:
Autonomous soft robots require compact actuators generating large strokes and high forces. Electro‐fluidic actuators are especially promising, they combine the advantages of electroactive polymers (low‐power consumption, fast response, and electrical powering) with the versatility of fluidic systems (force/stroke amplification). EHD (electrohydrodynamic) actuators are electro‐fluidic actuators whose motion results from charges being induced and accelerated in a liquid. They are extremely compact, silent, and low power (≤10 mW). They have been recently demonstrated in stretchable pumps and for the wireless propulsion of simple floating robots. This study demonstrates simultaneous wireless propulsion (2.5 mm s−1) and control of a 1 cm sized robot using a single DC signal. Voltage is applied between an electrode on the floating robot and a fixed one, both exposed to a dielectric liquid. Results support the underlying physical mechanism as EHD and characterize robot motion with different fluorocarbon liquids and voltages between 400 and 1800 V. Path following is demonstrated with a 3 × 3 array of electrodes. EHD actuators prove to be a simple, compact, low power alternative to magnetic and acoustic actuators for wireless powering and control of miniaturized robots, with applications in precision assembling at the micro/mesoscale, lab‐on‐chip, tactile displays, and active surfaces.
Page of 10
Articles per Page
by
Show export options
  Select all
Back to Top Top