Artificial Robotics Research Articles

Bioinspired structural color striped pattern from scalable assembly

Surface patterns are widespread in many organisms, providing the abilities of camouflage, recognition, sexual selection, and survival in creatures. Inspired by these features, structural color stripes over large and complex surfaces were presented based on a meniscus rapidly receding assembly process triggered by lowered pressure and heat. The pattern method allows building blocks to rapidly self-organize into structural color stripes with adjustable morphology and color within several minutes on 2D or complex 3D surfaces. We demonstrate that the structural color striped pattern can be used in anti-counterfeiting, mimicking structural color organisms, and manipulation of stem cell behaviors at multiple levels. This lowered pressure and heat triggered pattern method for engineering scalable structural color stripes provides a powerful tool which cannot be achieved by conventional methods and will promote the wide application of structural color pattern in sensing, artificial robots, anti-counterfeiting, and so on.

Artificial Intelligence-Entrepreneurship Future Research and Opportunities for New Business Model

Artificial Intelligence (AI) is a capability related to intelligent creatures in the form of artificial robots which are fully controlled by digital computers. The presence of Artificial Intelligence (AI) certainly changes the structure of human life which affects the effectiveness of human performance such as in the field of entrepreneurship. The main scope in artificial intelligence technology is gaining strategic advantage in digital business, human resources, market research, customer relations, accounting and finance, sales, marketing, and others. The investigation of this work is centered to understand more about Artificial Intelligence, opportunities for using Artificial Intelligence for entrepreneurship, perspectives that support AI technology as part of the new model of business, perspectives against the development of artificial intelligence, as well as future opportunities from artificial intelligence technology.

Smart insect-computer hybrid robots empowered with enhanced obstacle avoidance capabilities using onboard monocular camera

Insect-computer hybrid robots are receiving increasing attention as a potential alternative to small artificial robots due to their superior locomotion capabilities and low manufacturing costs. Controlling insect-computer hybrid robots to travel through terrain littered with complex obstacles of various shapes and sizes is still challenging. While insects can inherently deal with certain obstacles by using their antennae to detect and avoid obstacles, this ability is limited and can be interfered with by control signals when performing navigation tasks, ultimately leading to the robot being trapped in a specific place and having difficulty escaping. Hybrid robots need to add additional sensors to provide accurate perception and early warning of the external environment to avoid obstacles before getting trapped, ensuring smooth navigation tasks in rough terrain. However, due to insects’ tiny size and limited load capacity, hybrid robots are very limited in the sensors they can carry. A monocular camera is suitable for insect-computer hybrid robots because of its small size, low power consumption, and robust information acquisition capabilities. This paper proposes a navigation algorithm with an integrated obstacle avoidance module using a monocular camera for the insect-computer hybrid robot. The monocular cameras equipped with a monocular depth estimation algorithm based on deep learning can produce depth maps of environmental obstacles. The navigation algorithm generates control commands that can drive the hybrid robot away from obstacles according to the distribution of obstacle distances in the depth map. To ensure the performance of the monocular depth estimation model when applied to insect-computer hybrid robotics scenarios, we collected the first dataset from the viewpoint of a small robot for model training. In addition, we propose a simple but effective depth map processing method to obtain obstacle avoidance commands based on the weighted sum method. The success rate of the navigation experiment is significantly improved from 6.7% to 73.3%. Experimental results show that our navigation algorithm can detect obstacles in advance and guide the hybrid robots to avoid them before they get trapped.

Strengthening artificial muscle of oil-water composite network by nanotechnology

Artificial muscle, as a new technology, has a broad application prospect and market in the future, which is more effectively applied to the medical repair of human muscle damage, enhance the strength performance of human muscle, and enrich the function of artificial robots. Nanotechnology is also a high-precision technology that can be added to artificial muscles to make expansion and contraction more reliable. Currently, nanotechnology is constantly innovating in artificial muscles. There have been examples of using artificial muscles to add touch systems for real-time interaction and temperature changes, as well as combining sacrificial coordination keys with mechanical training processes to allow artificial muscles to bear more than their own multiple weights. Carbon catheters using nanotechnology have been shown to contract by as much as 20%. However, while focusing on enhancing the performance of artificial muscles, the bionic ability of the material itself has been neglected, and the elasticity and stretch of the muscle is a major difficulty. Therefore, there are still some shortcomings and areas that can be improved in this field. In this paper, we discuss how to use carbon conduit nanotechnology to strengthen artificial muscles, which provides effective reference materials for human beings to better understand the application of artificial muscle nanotechnology.

Batch fabrication of ultrathin flexible pressure sensors enabled by full printed technique

Flexible pressure sensors have gained significant attention in recent years owing to their versatile applications in health monitoring, human-machine interfaces, and artificial robotics. Geometric microengineering of the active layer, including micropatterned structures, porous layers, and multilayered packed structures has been investigated to improve the sensing performance. However, accompanying challenges such as increased thickness and difficulties in achieving mass production still persist. This work presents a full printed technique for fabricating high-performance piezoresistive pressure sensors. Thermal-treated graphene oxide (TGO) colloid was selected as the printing ink. Combined with an in-situ chemical foaming strategy, structural microengineering of the piezoresistive layer was achieved. The obtained hierarchical protruding micro-domes endow the piezoresistive pressure sensors with a wide sensing range of 550 kPa and ultrathin features (18 μm). In addition, the full-printed manufacturing method enables the batch-producible fabrication of pressure sensors. These sensors can be employed for human motion detection and pressure mapping applications.

RETURNING TO THE SCIENTIFIC PUBLICATION OF THE CANDIDATE OF LEGAL SCIENCES, PROFESSOR ZH. TLEMBAYEVA «SOME APPROACHES TO THE LEGAL REGULATION OF ARTIFICIAL INTELLIGENCE»

This article analyzes the article by Candidate of Legal Sciences, Professor Zh. Tlembayeva «Some approaches to the legal regulation of artificial intelligence», which was published in the scientific and legal journal «Bulletin of the Institute of Legislation and Legal Information of the Republic of Kazakhstan» No. 2 (65)-2021. In modern society, issues of legal regulation of artificial intelligence are becoming an integral part of the discussion on technology development. This topic represents a current and complex challenge that requires an in-depth analysis of various approaches to the formation of legal norms and standards in the field of artificial intelligence. The article analyzes the definition of the concept of «artificial intelligence», the definition of the concept of «artificial robot» established in the Law of the Republic of Kazakhstan «On Informatization». The author concluded that when developing a definition of this concept, one should take into account the types of artificial intelligence systems, the peculiarities of the use of artificial intelligence technologies in each specific area, as well as the different levels of application of technologies and the characteristics of the legal system of the state. The article discusses examples from different countries and organizations, international acts on issues related to the regulation of artificial intelligence. The author of the article notes that currently the use of artificial intelligence is practically not provided with a proper international basis. Zh. Tlembayeva points out the importance of a gradual and adaptive approach to the legal regulation of artificial intelligence, ensuring a balance between stimulating innovation and protecting the interests of society, as well as the flexibility of laws to adapt to the rapid development of technologies in this area. The article provides valuable research for legal, technology, and public policy professionals concerned with the implementation of artificial intelligence.

Bio-Hybrid Magnetic Robots: From Bioengineering to Targeted Therapy.

Magnetic robots possess an innate ability to navigate through hard-to-reach cavities in the human body, making them promising tools for diagnosing and treating diseases minimally invasively. Despite significant advances, the development of robots with desirable locomotion and full biocompatibility under harsh physiological conditions remains challenging, which put forward new requirements for magnetic robots' design and material synthesis. Compared to robots that are synthesized with inorganic materials, natural organisms like cells, bacteria or other microalgae exhibit ideal properties for in vivo applications, such as biocompatibility, deformability, auto-fluorescence, and self-propulsion, as well as easy for functional therapeutics engineering. In the process, these organisms can provide autonomous propulsion in biological fluids or external magnetic fields, while retaining their functionalities with integrating artificial robots, thus aiding targeted therapeutic delivery. This kind of robotics is named bio-hybrid magnetic robotics, and in this mini-review, recent progress including their design, engineering and potential for therapeutics delivery will be discussed. Additionally, the historical context and prominent examples will be introduced, and the complexities, potential pitfalls, and opportunities associated with bio-hybrid magnetic robotics will be discussed.

Learning dexterity from human hand motion in internet videos

To build general robotic agents that can operate in many environments, it is often useful for robots to collect experience in the real world. However, unguided experience collection is often not feasible due to safety, time, and hardware restrictions. We thus propose leveraging the next best thing as real world experience: videos of humans using their hands. To utilize these videos, we develop a method that retargets any 1st person or 3rd person video of human hands and arms into the robot hand and arm trajectories. While retargeting is a difficult problem, our key insight is to rely on only internet human hand video to train it. We use this method to present results in two areas: First, we build a system that enables any human to control a robot hand and arm, simply by demonstrating motions with their own hand. The robot observes the human operator via a single RGB camera and imitates their actions in real-time. This enables the robot to collect real-world experience safely using supervision. See these results at https://robotic-telekinesis.github.io. Second, we retarget in-the-wild human internet video into task-conditioned pseudo-robot trajectories to use as artificial robot experience. This learning algorithm leverages action priors from human hand actions, visual features from the images, and physical priors from dynamical systems to pretrain typical human behavior for a particular robot task. We show that by leveraging internet human hand experience, we need fewer robot demonstrations compared to many other methods. See these results at https://video-dex.github.io

Evaluation of the Implementation of the Independent Curriculum with a Technology-based Learning Model

The implementation of the independent Curriculum in the field of education through the utilization of technology models oriented towards Society 5.0 era, such as Internet of Things (IoT) or Artificial Intelligence (AI), big data, and artificial robots that will fulfill human needs to address other requirements. This research analyze three perspectives: students, teachers, and institutions related to implementation of the independent Curriculum oriented towards Society 5.0 era. This study uses a mixed method research approach. The data collection technique in this study used random sampling techniques. Data analysis is inductive or qualitative, and the results of this study emphasize meaning rather than generalization. From the student's perspective, there is a significant difference indicating a significant difference between the previous curriculum-13 and the implementation of the Merdeka Curriculum in terms of students' development at school. From the teacher's perspective, indicates a significant difference, meaning that access to relevant educational resources and participation in professional activities are evident. From the institution's perspective, 97.9% of schools and teachers have accessed the digital platform of the independent Curriculum, with only 2.02% remaining to implement it. The implementation of the Merdeka Curriculum allows schools, teachers, and students the freedom to organize and develop their own curriculum while encouraging the use of technology in learning.

Nano/Micromotors for Cancer Diagnosis and Therapy: Innovative Designs to Improve Biocompatibility.

Nano/micromotors are artificial robots at the nano/microscale that are capable of transforming energy into mechanical movement. In cancer diagnosis or therapy, such "tiny robots" show great promise for targeted drug delivery, cell removal/killing, and even related biomarker sensing. Yet biocompatibility is still the most critical challenge that restricts such techniques from transitioning from the laboratory to clinical applications. In this review, we emphasize the biocompatibility aspect of nano/micromotors to show the great efforts made by researchers to promote their clinical application, mainly including non-toxic fuel propulsion (inorganic catalysts, enzyme, etc.), bio-hybrid designs, ultrasound propulsion, light-triggered propulsion, magnetic propulsion, dual propulsion, and, in particular, the cooperative swarm-based strategy for increasing therapeutic effects. Future challenges in translating nano/micromotors into real applications and the potential directions for increasing biocompatibility are also described.

Muscle-inspired soft robots based on bilateral dielectric elastomer actuators

Muscle groups perform their functions in the human body via bilateral muscle actuation, which brings bionic inspiration to artificial robot design. Building soft robotic systems with artificial muscles and multiple control dimensions could be an effective means to develop highly controllable soft robots. Here, we report a bilateral actuator with a bilateral deformation function similar to that of a muscle group that can be used for soft robots. To construct this bilateral actuator, a low-cost VHB 4910 dielectric elastomer was selected as the artificial muscle, and polymer films manufactured with specific shapes served as the actuator frame. By end-to-end connecting these bilateral actuators, a gear-shaped 3D soft robot with diverse motion capabilities could be developed, benefiting from adjustable actuation combinations. Lying on the ground with all feet on the ground, a crawling soft robot with dexterous movement along multiple directions was realized. Moreover, the directional steering was instantaneous and efficient. With two feet standing on the ground, it also acted as a rolling soft robot that can achieve bidirectional rolling motion and climbing motion on a 2° slope. Finally, inspired by the orbicularis oris muscle in the mouth, a mouthlike soft robot that could bite and grab objects 5.3 times of its body weight was demonstrated. The bidirectional function of a single actuator and the various combination modes among multiple actuators together allow the soft robots to exhibit diverse functionalities and flexibility, which provides a very valuable reference for the design of highly controllable soft robots.

Shape-Programmable Liquid-Crystalline Polyurethane-Based Multimode Actuators Triggered by Light-Driven Molecular Motors.

In recent years, light-driven soft actuators have been rapidly developed as enablers in the fabrication of artificial robots and biomimetic devices. However, it remains challenging to amplify molecular isomerization to multiple modes of macroscopic actuation with large amplitude and complex motions. Here, a strategy is reported to build a light-responsive liquid-crystalline polyurethane elastomer by phototriggered overcrowded alkene-based molecular motors. A trifunctional molecular motor modified with an ethylene glycol spacer on the rotor and stator functions as a crosslinker and unidirectional stirrer that amplifies molecular motion into macroscopic movement. The shape-programmable polymeric film presents superior mechanical properties and characteristic shape-memory effect. Furthermore, diverse modes of motions including bending, unwinding, and contracting with tunable actuation speed over a wide range are achieved. Such research is hoped to pave a new way for the design of advanced light-responsive soft actuators and robots.

The use of management accounting and financial accounting in financial management based on multiple linear regression algorithm

Abstract Artificial intelligence has had varying degrees of impact on various industries, and many traditional financial tasks have been replaced by artificial robots, which will inevitably lead to the transformation of financial accounting to management accounting, which is also the key to the continuous development of enterprises. Firstly, this paper proposes a multiple linear regression algorithm, which is solved by the classical least squares method, while the parity results of the least squares method are relatively stable and generally do not have valuation drift. Then, we analyze management accounting and financial accounting, analyze the importance of using both in enterprise financial management and propose some specific application paths based on this to provide help for enterprise financial management. Finally, a multiple regression algorithm is used to analyze management accounting and financial accounting data. The regression analysis results showed that the coefficient of management accounting and financial accounting change and the degree of competition was 0.7952, t=2.4457, F=5.9813, R2=0.0520, and management accounting and financial accounting change were not significantly influenced by the size of the enterprise and competition. This study improves the traditional accounting concept, establishes a perfect accounting system, realizes the integration of organizations, and pays attention to the importance of consolidating original resources to provide some theoretical guidance for the effective improvement of enterprise financial management quality.

In Situ Grown Silver-Polymer Framework with Coordination Complexes for Functional Artificial Tissues.

Self-sensing actuators are critical to artificial robots with biomimetic proprio-/exteroception properties of biological neuromuscular systems. Existing add-on approaches, which physically blend heterogeneous sensor/actuator components, fall short of yielding satisfactory solutions, considering their suboptimal interfaces, poor adhesion, and electronic/mechanical property mismatches. Here, a single homogeneous material platform is reported by creating a silver-polymer framework (SPF), thus realizing the seamless sensing-actuation unification. The SPF-enabled elastomer is highly stretchable (1200%), conductive (0.076Sm-1 ), and strong (0.76MPa in-strength), where the stretchable polymer matrix synthesis and in situ silver nanoparticles reduction are accomplished simultaneously. Benefiting from the multimodal sensing capability from its architecture itself (mechanical and thermal cues), self-sensing actuation (proprio-deformations and external stimuli perceptions) is achieved for the SPF-based pneumatic actuator, alongside an excellent load-lifting attribute (up to 3700 times its own weight), substantiating its advantage of the unified sensing-actuation feature in a single homogenous material. In view of its human somatosensitive muscular systems imitative functionality, the reported SPF bodes well for use with next-generation functional tissues, including artificial skins, human-machine interfaces, self-sensing robots, and otherwise dynamic materials.

A bidirectional thermal sensory leaky integrate-and-fire (LIF) neuron model based on bipolar NbOx volatile threshold devices with ultra-low operating current.

Brain-like artificial intelligence (AI) will become the main form and important platform in future computing. It will play an important and unique role in simulating brain functions, efficiently implementing AI algorithms, and improving computing power. Developing artificial neurons that can send facilitation/depression signals to artificial synapses, sense, and process temperature information is of great significance for achieving more efficient and compact brain-like computing systems. Herein, we have constructed a NbOx bipolar volatile threshold memristor, which could be operated by 1 μA ultra-low current and up to ∼104 switching ratios. By using a leaky integrate-and-fire (LIF) artificial neuron model, a bipolar LIF artificial neuron is constructed, which can realize the conventional threshold-driven firing, all-or-nothing spiking, refractory periods, and intensity-modulated frequency response bidirectionally at the positive/negative voltage stimulation, which will give the artificial synapse facilitation/depression signals. Furthermore, this bipolar LIF neuron can also explore different temperatures to output different signals, which could be constructed as a more compact thermal sensory neuron to avoid external harm to artificial robots. This study is of great significance for improving the computational efficiency of the system more effectively, achieving high integration density and low energy consumption artificial neural networks to meet the needs of brain-like neural computing.

Biotissue‐Inspired Anisotropic Carbon Fiber Composite Hydrogels for Logic Gates, Integrated Soft Actuators, and Sensors with Ultra‐High Sensitivity

AbstractNatural biotissues like muscles, ligaments, and nerves have highly aligned structures, which play critical roles in directional signal transport, sensing, and actuation. Inspired by anisotropic biotissues, composite hydrogels with outstanding mechanical properties and conductivity are developed by compositing thermo‐responsive poly (N‐isopropylacrylamide) (PNIPAM) hydrogels with highly aligned carbon fibers (CFs). The anisotropic hydrogels show superior tensile strength (3.0 ± 0.3), modulus (74 ± 7.0 MPa), excellent electrical conductivity (≈670 S m−1), and ultra‐high sensitivity (gauge factor up to 647) along CFs, with an anisotropic ratio (AR) up to 740 over those in perpendicular direction. The extremely high AR in conductivity (more than 400) produces high‐level output in parallel direction and low‐level output in perpendicular direction with a direct current (DC) power supply, which is used to fabricate AND and OR gates. Moreover, the composite hydrogels are converted into thermo‐responsive actuators with CFs twisted before compositing with PNIPAM/clay network. The pre‐twisted CF helices impart internal stress that drives reversible actuation of hydrogel helices upon thermo‐stimulating. The actuation is self‐sensed due to the extremely high sensitivity of the composite hydrogels. Such biomimetic anisotropic self‐sensing hydrogel actuators resemble natural biotissues with both actuation and sensing capabilities, and have promise applications for artificial robotics.

A Versatile Ionomer‐Based Soft Actuator with Multi‐Stimulus Responses, Self‐Sustainable Locomotion, and Photoelectric Conversion

AbstractThe prospects of endowing artificial robotics or devices with increasingly complex and emergent life‐like behaviors have attracted growing interest in the soft functional materials that mimic the versatile motions of living creatures in the iridescent nature. However, despite the flourishing achievements so far, soft actuators capable of sensitive multi‐stimulus responses and self‐sustainable movements, have been extensively pursued to reduce control complexity yet remains a challenging target. Here, through material‐structural synergistic design incorporating stress‐mismatching structure, high pseudo‐negative coefficient of thermal expansion of perfluoro‐sulfonic acid ionomer, comprehensive converting properties of carbon nanotube, and anisotropic large thermal expansion of PE polymer, an ionomer‐based bilayer actuator is proposed, presenting high‐performance actuation of various forms and nice stability, responsive to light (including sunlight without focusing, LED light), low voltage, mild heating, and humidity/solvent change. With a built‐in structural feedback loop, the actuation performances are further explored to realize intelligent systems, including: 1) self‐sustainable locomotion under sunlight irradiation with adjustable photophobic and phototropic direction as well as adaption to different topographies and loading conditions, 2) self‐sustainable oscillation and solar‐electric generating, and 3) bionic floristic reaction according to environmental change. These diversified actuation modes allow promising following‐up designs for bio‐hybrid soft robotics fueled by and harmonized with natural environments.

Biomimetic Gradient Hydrogel Actuators with Ultrafast Thermo-Responsiveness and High Strength.

Most current hydrogel actuators suffer from either poor mechanical properties or limited responsiveness. Also, the widely used thermo-responsive poly-(N-isopropylacrylamide) (PNIPAM) homopolymer hydrogels have a slow response rate. Thus, it remains a challenge to fabricate thermo-responsive hydrogel actuators with both excellent mechanical and responsive properties. Herein, ultrafast thermo-responsive VSNPs-P(NIPAM-co-AA) hydrogels containing multivalent vinyl functionalized silica nanoparticles (VSNPs) are fabricated. The ultrafast thermo-responsiveness is due to the mobile polymer chains grafted from the surfaces of the VSNPs, which can facilitate hydrophobic aggregation, inducing the phase transition and generating water transport channels for quick water expulsion. In addition, the copolymerization of NIPAM with acrylic acid (AA) decreases the transition temperature of the thermo-responsive PNIPAM-based hydrogels, contributing to ultrafast thermo-responsive shrinking behavior with a large volume change of as high as 72.5%. Moreover, inspired by nature, intelligent hydrogel actuators with gradient structure can be facilely prepared through self-healing between the ultrafast thermo-responsive VSNPs-P(NIPAM-co-AA) hydrogel layers and high-strength VSNPs-PAA-Fe3+ multibond network (MBN) hydrogel layers. The obtained well-integrated gradient hydrogel actuators show ultrafast thermo-responsive performance within only 9 s in 60 °C water, as well as high strength, and can be used for more practical applications as intelligent soft actuators or artificial robots.

Systems of collaboration: challenges and solutions for interdisciplinary research in AI and social robotics

This article examines the challenges and opportunities that arise when engaging with research across disciplines, contributing to the growth of social robotics and artificially intelligent systems. Artificial intelligence has a significant role to play in human–machine communication; however, there are barriers to its adoption and considerations towards systematic implementation for the good of people and societies. This perspective piece considers the position of artificial intelligence in systems of human–machine communication. The study of artificial intelligent systems is one of discovery, trial, and error through a melting pot of methodologies, and this interdisciplinary nature is explored through the perspective of researchers at the centre of collaboration coming from artificial intelligence, robotics, and communication.

CNTs based capacitive stretchable pressure sensor with stable performance

In recent years, with the increasing demand for artificial robots and smart devices, flexible pressure sensors have attracted much attention. In this paper, to solve the problem of insufficient stretchability and complicated microstructure fabrication process, a capacitive pressure sensor based on flexible electrodes with wrinkle structure and composite dielectric layer was designed and prepared. The as-prepared sensor exhibits a sensitivity of 2.13 kPa−1 and the response time is about 0.1 s. During the loading-unloading test, the capacitive flexible sensor showed stable sensing performance and good repeatability with minor hysteresis effect. The research is of great significance for the application of flexible sensors in fields such as soft robots, E-skin and medical monitoring in the future.