Field Of Robotics Research Articles

Inspired by the growth behavior of plants: biomimetic soft robots that just meet the requirements of use

Soft robots are usually manufactured using the pouring method and can only be configured with a fixed execution area, which often faces the problem of insufficient or wasteful performance in real-world applications, and cannot be reused for other tasks. In order to overcome this limitation, we propose a simple and controllable rather than redesigned method inspired by the bionic growth behavior of plants, and prepare bionic soft robots that can just meet the requirements of use, and transform biological intelligence into mechanical intelligence. Based on finite element method, we establish a theoretical model of soft robot performance. And the experimental platform is designed to conduct experimental research on the prototype of the soft robot. Compared with the results obtained through the theoretical model, it is found out that the experimental bending angle and elongation are slightly smaller than the simulation results. (The maximum error of elongation prediction for soft robots (Fashion 1-4) is 5.7%, 5.9%, 6%, and 6%, and the maximum error of bending angle prediction is 7.1%, 7.5%, 7.6%, and 7.6%, respectively). The high consistence between our theoretical model and the experimental results shows that the theoretical model is applicable to accurately predict the performance of soft robots. It is worth pointing out that this design as proposed in this paper can be extended to the wider field of soft robotics as a generic one.

Revolutionizing HRM: a review of human-robot collaboration in HRM functions and the imperative of change readiness

PurposeThe purpose of the paper is to conduct a review of the literature on human-robot collaboration across different functions and activities of human resource management (HRM) and discuss its importance for change readiness in organizations.Design/methodology/approachA bibliometric analysis was conducted to identify emerging research themes in the fields of human resources (HR) and robotics, including change readiness. Based on the initial results of the bibliometric analysis, a systematic literature review was subsequently performed to gain a more specific understanding of research across various HRM functions and change readiness.FindingsThe results from bibliometric analysis and systematic review highlight that technological progression in HRM, such as AI-driven staffing and training techniques, improves effectiveness and personalization but raises concerns about privacy and job scrutiny. AI and robotics in performance evaluation enhance objectivity and reduce subjectivity, which can lead to disengagement. Generational differences, cultural factors and emotional quotient complicate readiness to adopt new technologies. The research emphasizes balancing technological effectiveness with employee involvement and meaningfulness to ensure successful implementation and engagement.Originality/valueThis paper synthesizes existing research, including literature, theoretical concepts and models, to identify best practices and successful strategies for implementing human-robot collaboration in HRM functions. It highlights gaps in the current literature and suggests areas for future research to advance the field of human-robot collaboration in HRM. By doing so, this paper enhances theoretical understanding while offering practical insights essential for effective change management.

Modular Robotics Configurator: A MATLAB Model-Based Development Approach

In recent years, modularity has become increasingly present in the field of robotics and mechatronics. The need to easily calculate and generate modular robots in an easier and faster way and for a wide range of robotics projects has increased. This paper aims to present a new modular software development method for an automatic configurator of serial robots through the model-based development technique using the MATLAB Simulink R2024b software. Using this functionality, the user has the possibility to configure, generate, and analyze serial robots, starting from a kinematic scheme that complies with the development requirements of the project. Having a high degree of flexibility and avoiding multiple instances of debugging, caused by the need to use different environments, as well as connectivity problems between them or a lack of support in development, the user has the possibility to configure and reconfigure serial robots, easily adapting to the high degree of dynamism in the development of current projects. Because of the modularity on which the software development is based, the user has the possibility to optimize and improve the quality and performance of the system, along with easy adaptation to the speed of technological advancement.

AirCanvas using OpenCV and MediaPipe

Human-Computer Interaction (HCI) has undergone significant transformations with the advent of Artificial Intelligence (AI) and Machine Learning (ML), enhancing the ways in which users engage with computing systems. This paper introduces AirCanvas, a novel hands-free digital interaction tool that leverages air gestures for intuitive and seamless computer control. The system uses advanced image processing techniques, specifically OpenCV for visual data analysis and MediaPipe for accurate hand gesture recognition, enabling users to manipulate virtual environments without physical touch. By integrating a standard webcam as the primary sensor, AirCanvas offers an accessible solution for gesture-based interaction, eliminating the need for specialized external hardware like motion sensors or gloves. Users can perform a variety of tasks such as virtual drawing, cursor control, and presentation navigation with simple hand gestures in 3D space. The system's gesture recognition capabilities are powered by deep learning models trained on large datasets of hand movements, ensuring robust performance in diverse lighting and environmental conditions. The potential applications of AirCanvas are far-reaching, ranging from interactive art creation to more practical uses in assistive technology, where people with mobility impairments can benefit from hands-free control. In the field of robotics, the tool can enable more natural human-robot interaction, while in gaming, it can introduce new forms of immersive gameplay through gesture-based interfaces. Furthermore, the tool's open-source nature allows for further customization and enhancement, fostering innovation and collaboration in various industries. As human-computer interaction continues to evolve, AirCanvas represents a significant step forward in making technology more intuitive, engaging, and accessible for all users.

High sensitivity flexible strain sensor for motion monitoring based on MWCNT@MXene and silicone rubber

Research on flexible strain sensors has grown rapidly and is widely applied in the fields of soft robotics, body motion detection, wearable sensors, health monitoring, and sports. In this study, MXene was successfully synthesized in powder form and combined with multi-walled carbon nanotube (MWCNT) to develop MWCNT@MXene conductive network-based flexible strain sensors with silicone rubber (SR) substrate. Combining MWCNTs with MXene as a conductive material has been shown to significantly improve the sensor performance, due to MXene’s high conductivity properties that strengthen the MWCNT conductive pathway, increase sensitivity, and improve sensor stability. The sensor is fabricated by a sandwich method consisting of three layers, which enables more accurate and reliable detection of strain changes. The main innovation of this research is the utilization of MWCNT@MXene as a conductive material that optimizes the performance of flexible strain sensors, overcomes the limitations of previous materials, and makes it a more effective solution for long-term applications. Furthermore, the sensor was evaluated to test its performance through sensitivity, linearity, response time, and durability tests. The results showed that the sensor exhibited excellent performance with a high sensitivity of 39.97 over a strain range of 0-100% and excellent linearity (0.99) over a strain of 0–50%. The sensor also has a fast response time of about 70 ms, it also has good stability during low (1–5%) and high (20–100%) strain cycle testing and can withstand up to 1200 loading and unloading cycles. In addition, the sensor effectively detects a wide range of body movements, including finger, wrist and knee movements. These findings show that the electromechanical properties of strain sensors are significantly improved through the use of MWCNT@MXene as a conductive material, so these sensors are considered a promising solution for applications in wearables and body motion monitoring.

Efficient Robot Localization Through Deep Learning-Based Natural Fiduciary Pattern Recognition

This paper introduces an efficient localization algorithm for robotic systems, utilizing deep learning to identify and exploit natural fiduciary patterns within the environment. Diverging from conventional localization techniques that depend on artificial markers, this method capitalizes on the inherent environmental features to enhance both accuracy and computational efficiency. By integrating advanced deep learning frameworks with natural scene analysis, the proposed algorithm facilitates robust, real-time localization in dynamic and unstructured settings. The resulting approach offers significant improvements in adaptability, precision, and operational efficiency, representing a substantial contribution to the field of autonomous robotics. We are aiming at analyzing an automotive manufacturing scenario to achieve robotic localization related to a moving target. To work with a simpler and more accessible scenario we have chosen a demonstrative context consisting of a laboratory wall containing some elements. This paper will focus on the first part of the case study, with a continuation planned for future work. It will demonstrate a scenario in which a camera is mounted on a robot, capturing images of the underside of a car (which we assume to be represented by a gray painted surface with specific elements to be described in Materials and Methods). These images are processed by a convolutional neural network (CNN), designed to detect the most distinctive features of the environment. The extracted information is crucial, as the identified characteristic areas will serve as reference points for the real-time localization of the industrial robot. In this work, we have demonstrated the potential of leveraging natural fiduciary patterns for efficient and accurate robot localization. By utilizing deep learning, specifically convolutional neural networks. The experimental results suggest that this approach is not only feasible but also scalable across a wide range of applications, including industrial automation autonomous vehicles, and aerospace navigation. As robots increasingly operate in environments where computational efficiency and adaptability are paramount, our methodology offers a viable solution to enhance localization without compromising accuracy or speed. The proposal of an algorithm that enables the application of the proposed method for natural fiduciary patterns based on neural networks to more complex scenarios is highlighted, along with the efficiency of the method for robot localization compared to others.

Bioinspired Tactile Object Identification Leveraging Deep Learning and Soft Body Compliance

Tactile object identification is a fundamental human skill, underlying several core aspects of human intelligence. Humans display a range of remarkable haptic skills, enabled by the synergistic interactions of the somatosensory system with higher‐level cognitive processes. In contrast, robotics’ haptic sensing solutions have historically lacked the ability to achieve human‐level perceptive capabilities, lacking in both the sensory system and its cognitive digital counterpart. Herein, part of this challenge is addressed by leveraging the success of the fields of soft robotics and deep learning to show how a soft robotic hand, equipped with low‐resolution tactile sensing, can be used to accurately identify a diverse set of objects. In particular, ROSE‐Net, a neural network that leverages multiple grasps to enable accurate pose‐invariant object recognition, is developed. The multi‐grasp haptic discrimination solution can lead to a significant increase in performance. The versatility and adaptability of this approach are also tested in two scenarios: a learning transfer scenario and a fault tolerance scenario. Finally, the framework is tested in an online discrimination task, where this approach is shown to naturally require additional grasps for objects that are more challenging to identify using a single grasp and low spatial resolution tactile sensing.

Modelling and optimization of small - scale soft magnetic robots for enhanced locomotion

Small-scale soft robots are vital in medical scenarios requiring access to confined spaces. This study explores motion optimization for such robots, emphasizing magnetically responsive materials that enable shape changes through controlled magnetic fields. These materials provide robots with versatile and agile locomotion capabilities. Using genetic algorithms, we present a novel approach to optimize magnetic field parameters and robot dimensions. In magnetic field optimization, the results validate prior experimental observations while providing new insights into determining optimal magnetic field characteristics for walking motions. Deviations from optimal magnetic field magnitudes directly affect walking velocity, revealing a non-linear relationship between magnetic fields and locomotion speed, diverging from linear modeling results. Furthermore, we find that both excessively low and high robot heights hinder walking speed lower heights reduce surface friction, while higher heights compromise agility. This comprehensive optimization strategy advances the capabilities of small-scale soft magnetic robots. Our work in motion modeling and optimization enhances the understanding of these robots' dynamics and unlocks new possibilities for deployment in complex environments. These findings reaffirm the significance of soft robots in medical and confined-space applications, offering a robust foundation for further innovations in this evolving field.

A travelable area boundary dataset for visual navigation of field robots

Travelable area boundaries not only constrain the movement of field robots but also indicate alternative guiding routes for dynamic objects. Publicly available road boundary datasets have outlined boundaries by binary segmentation labels. However, hard post-processes have to be done to extract from detected boundaries further semantics including the shapes of the boundaries and guiding routes, which poses challenges to a real-time visual navigation system without detailed prior maps. In addition, boundary detectors suffer from insufficient data collected from complex roads with severe occlusion and of different shapes. In this paper, a travelable area boundary dataset is semi-automatically built. 82.05% of the data is collected from bends, crossroads, T-shape roads and other irregular roads. Novel guiding semantics labels, shape labels and scene complexity labels are assigned to boundaries. With the support of the new dataset, travelable area boundary detectors could be trained, evaluated and fairly compared. The dataset can also be used to train, evaluate or test detectors for the road boundary detection task.

Toward Universal Embodied Planning in Scalable Heterogeneous Field Robots Collaboration and Control

ABSTRACTMulti‐robot systems offer substantial enhancements in efficiency, scalability, robustness, and flexibility for executing complex tasks through collaborative efforts. However, existing methodologies are constrained by their lack of generalizability, the need for extensive modeling, and most importantly, limitations in their applicability in complex scenarios. This paper presents a novel approach to multi‐robot task planning and coordination, introducing a comprehensive pipeline encompassing data generation, supervised fine‐tuning, and rigorous error analysis using the Multi‐Robot collaboration Error Diagnostic (MRED) metrics. Bridging the gap between natural language commands and physical groundings in robot collaboration tasks, we present MultiPlan: the first data set specifically designed for LLM fine‐tuning. The MultiPlan data set encompasses 100 distinct indoor and outdoor scenarios, ranging from office to garden. Experiments underscore the efficacy of the proposed methodology, including comparative analyses against state‐of‐the‐art LLMs and generalization studies on previously unseen tasks. Results reveal that the fine‐tuned model achieves a 24.8% relative improvement over the GPT‐4 model in addressing complex multi‐robot planning scenarios. We also conducted field evaluations in both office and urban settings to demonstrate the deployment performance of the proposed method. These results demonstrate the model's superior capabilities in task decomposition, error management, and adaptation to novel contexts.

Multijoint Continuous Motion Estimation for Human Lower Limb Based on Surface Electromyography

The estimation of multijoint angles is of great significance in the fields of lower limb rehabilitation, motion control, and exoskeleton robotics. Accurate joint angle estimation helps assess joint function, assist in rehabilitation training, and optimize robotic control strategies. However, estimating multijoint angles in different movement patterns, such as walking, obstacle crossing, squatting, and knee flexion–extension, using surface electromyography (sEMG) signals remains a challenge. In this study, a model is proposed for the continuous motion estimation of multijoint angles in the lower limb (CB-TCN: temporal convolutional network + convolutional block attention module + temporal convolutional network). The model integrates temporal convolutional networks (TCNs) with convolutional block attention modules (CBAMs) to enhance feature extraction and improve prediction accuracy. The model effectively captures temporal features in lower limb movements, while enhancing attention to key features through the attention mechanism of CBAM. To enhance the model’s generalization ability, this study adopts a sliding window data augmentation method to expand the training samples and improve the model’s adaptability to different movement patterns. Through experimental validation on 8 subjects across four typical lower limb movements, walking, obstacle crossing, squatting, and knee flexion–extension, the results show that the CB-TCN model outperforms traditional models in terms of accuracy and robustness. Specifically, the model achieved R2 values of up to 0.9718, RMSE as low as 1.2648°, and NRMSE values as low as 0.05234 for knee angle prediction during walking. These findings indicate that the model combining TCN and CBAM has significant advantages in predicting lower limb joint angles. The proposed approach shows great promise for enhancing lower limb rehabilitation and motion analysis.

A Versatile Dual-Responsive Shape-Memory Gripper via Additive Manufacturing Toward High-Performance Cross-Scale Objects Maneuvering.

Smart grippers serving as soft robotics have garnered extensive attentions owing to their great potentials in medical, biomedical, and industrial fields. Though a diversity of grippers that account for manipulating the small objects (e.g., tiny micrometer-scale droplets) or the big ones (e.g., centimeter-scale screw) has been proposed, however, cross-scale maneuvering of these two species leveraging an all-in-one intelligent gripper is still challenging. Here, a magnet/light dual-responsive shape-memory gripper (DR-SMG) is reported, based on the hybrid of Fe-nanoparticles and shape-memory polymers. Thanks to its photothermal effect, the closed-state DR-SMG switches to the open state under the synergetic cooperation of near-infrared-ray (NIR) and a circinate magnetic field, referring to the temporary state. On the other hand, once the NIR is loaded, the temporary opened DR-SMG would reconfigure to its permanent closed state owing to shape-memory effect. Leveraging this principle, DR-SMG can grasp and release diverse cross-scale objects ranging from micrometers to centimeters including metals, glass balls, polymers, and small liquids. Significantly, this versatile DR-SMG is capable of spatially delivering multifunctional chemical droplets and conductive liquid metals, thereby enabling lab-on-chip and electrical switch applications. This work provides new insights into intelligent grippers and further advances the field of soft robotics.

ZodiAq: An Isotropic Flagella-Inspired Soft Underwater Drone for Safe Marine Exploration.

The inherent challenges of robotic underwater exploration, such as hydrodynamic effects, the complexity of dynamic coupling, and the necessity for sensitive interaction with marine life, call for the adoption of soft robotic approaches in marine exploration. To address this, we present a novel prototype, ZodiAq, a soft underwater drone inspired by prokaryotic bacterial flagella. ZodiAq's unique dodecahedral structure, equipped with 12 flagella-like arms, ensures design redundancy and compliance, ideal for navigating complex underwater terrains. The prototype features a central unit based on a Raspberry Pi, connected to a sensory system for inertial, depth, and vision detection, and an acoustic modem for communication. Combined with the implemented control law, it renders ZodiAq an intelligent system. This article details the design and fabrication process of ZodiAq, highlighting design choices and prototype capabilities. Based on the strain-based modeling of Cosserat rods, we have developed a digital twin of the prototype within a simulation toolbox to simplify analysis and control. To optimize its operation in dynamic aquatic conditions, a simplified model-based controller has been developed and implemented, facilitating intelligent and adaptive movement in the hydrodynamic environment. Extensive experimental demonstrations highlight the drone's potential, showcasing its design redundancy, embodied intelligence, crawling gait, and practical applications in diverse underwater settings. This research contributes significantly to the field of underwater soft robotics, offering a promising new avenue for safe, efficient, and environmentally conscious underwater exploration.

A Bionic Robotic Fish with a Dielectric Elastomer

Abstract Dielectric elastomer actuators (DEAs) are promising enabling devices that can be used in a wide range of robots, artificial muscles and microfluidics. They are characterized by high actuating strain, low cost and noise, and high energy density and efficiency. There are three main challenges for enabling DEs to become actuators: (1) developing suitable and compatible electrode materials; (2) effectively isolating the actuator electrode from the surrounding fluid; and (3) creating a rigid frame that usually requires prestraining of the dielectric layer. The use of robotic fish in water is an important application field of biomimetic soft robots. At present, most underwater robotic fish use spiral propulsion, which has several problems, including propulsion efficiency, position controllability and aquatic organism involvement. To provide solutions, the research and development of underwater robotic fish that imitate the fins and body propulsion of fish and the use of soft underwater robotic fish are in full adoption. This project involves the research and development of a bionic soft underwater robot fish with a software driver, which can imitate swimming via the tail fin and body of a fish, especially with respect to stable swimming propulsion, to successfully develop high-performance soft underwater robot fish. In addition, to imitate the unstable swimming movements of fish, such as turning and sharp acceleration and deceleration, robot fish that use DE drivers with good flexibility and high strain have been researched and developed.

A Compliant Active Roller Gripper with High Positional Offset Tolerance for Delicate Spherical Fruit Handling

In the field of agricultural robotics, robotic grippers play an indispensable role, directly influencing the rate of fruit damage and handling efficiency. Currently, traditional agricultural robotic grippers face challenges such as high damage rates and high requirements for position control. A robotic gripper for stable spherical fruit handling with high positional offset tolerance and a low fruit damage rate is proposed in this paper. It adopts a three-finger structure. A flexible active roller is configured at the end of each finger, allowing fruit translation with just a gentle touch. An integrated pressure sensor within the active roller further enhances the gripper’s compliance. To describe the effect of the gripper on the fruit, the interaction model was derived. Taking the tomato as a typical soft and fragile spherical fruit, three experiments were conducted to evaluate the performance of the proposed gripper. The experimental results demonstrated the handling capability of the gripper and the maximum graspable weight reached 2077 g. The average failure rate for the unilateral offset of 9 mm was only 1.33%, and for the bilateral offset of 6-6 mm was 4%, indicating the high positional offset tolerance performance and a low fruit damage rate of the gripper. The preliminary tomato-picking capability of the proposed gripper was also validated in a simplified laboratory scenario.

Program Development for Enhancing Competencies of Vocational College Teachers in Mechatronics and Robotics under the Office of the Vocational Education Commission

The purposes of this research were to 1) study the components and indicators of teacher competency in Mechatronics and Robotics, 2) study the current states, desirable states, and the needs for teacher competency development in the Mechatronics and Robotics Department, 3) design and development of teacher competency-enhancing programs in Mechatronics and Robotics, and 4) study the results of implementing the teacher competency-enhancing program in the Mechatronics and Robotics Department. This research was research and development conducted in 4 phases following the research purposes. The results showed that 1) Components and indicators of teacher competency in Mechatronics and Robotics have 5 components and 36 indicators confirmed by experts are appropriate at the highest level. 2) The current state of teacher competency in the Mechatronics and Robotics Department overall is moderate, and desirable condition overall is at the highest level, The competency development methods consist of (1) Self-study (2) Training (3) Workshops (4) Study visits and (5) Practice in the workplace, and the priorities of the needs to develop competencies are (1) Self-development (2) Ethics and professional ethics of teachers (3) Learning measurement and evaluation (4) Curriculum administration, and learning management (5) Building relationships and cooperation with communities for learning management, respectively. 3) Teacher Competency-enhancing Program in the field of Mechatronics and Robotics consists of (1) Principles, (2) Objectives, (3) Models and methods for development, (4) Content and development activities, amounting to 5 modules, and (5) Evaluation. The program evaluation results by qualified experts are appropriateness, utility, and possibility at the highest level. 4) The results of implementing the teacher competency-enhancing program in Mechatronics and Robotics were found as follows: (1) Pre-development knowledge of teachers in Mechatronics and Robotics education showed an average score of 17.30 out of 30 (57.66%), while post-development knowledge increased to an average score of 26.30 out of 30 (87.67%). (2) Overall, teachers’ competencies improved from a moderate level to the highest level after program implementation. (3) The satisfaction evaluation of program participants indicated the highest level of satisfaction in overall and each aspect.

Industrial applications of collaborative robots

With the advent of the Industry 4.0 era, the application of collaborative robots (cobots) in industrial fields has greatly increased. Intelligent collaborative robots or smart cobots enable high flexibility by combining the human ability to adapt to new tasks with automated robots (precision, repeatability) performance. This paper will analyze the current application status and usage of collaborative robots in the various industrial fields, and its benefits and disadvantages from the discussion. Firstly, this paper the defines collaborative robots and explains the difference between cobots and traditional industrial robots. Then, it analyzes the specific application cases of collaborative robots in automotive manufacturing, electronics and electrical appliances, food and beverage, pharmaceutical and chemical industries. Subsequently, this paper introduces the main technologies linked to collaborative robots, including sensors, Human-Robot Interaction (HRI), machine learning and safety technologies. Through the study of actual application cases, this paper summarizes the significant advantages of collaborative robots to improve productivity, reduce costs, and optimize the working environment. Meanwhile, this paper also discusses the current technical challenges, regulatory and standard issues as well as marketing difficulties for collaborative robots, and looks at future development trends and research directions. The results demonstrate that the utilization of collaborative robots in industry has a promising future and research and practical significance as well

Playing with robots in a nursery: a sociomaterial focus on interaction and learning

In the field of educational robotics, it is important to understand the processes trough which child-robot interactions are established during play activities. In terms of socio-material characteristics, robots can vary widely, from more mechanical robots to more anthropomorphic ones. Research has shown that the degree of anthropomorphization of the robot has an impact on how children perceive and interact with the robot. The role of the socio-material characteristics is still poorly explore in the 18–36-month age group. The aim of the study was to investigate how the presence of two robots, which differed in their socio-material characteristic of anthropomorphization, shapes both the individual and group play activities of 25 children aged 18–36 months. The children were observed during free group play sessions in which they had access to two types of robots: Idol, with more human-like features, and Pixy, a more mechanical robot with minimal anthropomorphism. Observations made through video recordings were transcribed. Qualitative analysis was conducted, and six units of analysis of children’s interaction with robots were identified. The main finding from our study is that children as early as 18 months are sensitive to the socio-material characteristics of the robotic artefact, influencing the way they interact with the robot and with each other. Notably, children displayed more imitation behaviors and social interactions with Idol, the more anthropomorphic robot, while Pixy, the mechanical robot, was primarily explored for its mechanical features. From an educational point of view, we highlight the importance of the construction of the learning environment and the choice of materials to propose to the children in play; the robot could be used to reinforce symbolic play, imitation, and to support group interaction.

Long, Fibrous, and Tailorable Dielectric Elastomer Artificial Muscles via Mask‐Free Stamping of Carbon Nanotube Electrodes

AbstractHigh‐performance, large‐size artificial muscles are in great demand in the field of robotics. This work reports a comprehensive approach for fabricating, actuating, sensing, and controlling a 180 mm‐long fibrous dielectric elastomer (DE) artificial muscle. The fabrication process introduces a novel method for patterning large‐area, uniform electrodes using vacuum filtration followed by mask‐free stamping on DE substrates. To address the challenge of long charging times that impair dynamic performance, an amplitude modulation algorithm is developed for high‐frequency actuation, which increased generated strain by 64% at a resonant frequency of 10 Hz. Additionally, the hollow space within the rolled artificial muscle is used to integrate a waveguide that serves as a strain sensor. This combined actuation‐sensing structure maintains flexibility and actuation capabilities while enabling self‐sensing and feedback control. The versatility of the DE artificial muscle is further demonstrated by segmenting a single long muscle into three shorter units and employing these units to construct two multi‐actuator machines: a tensegrity‐based gimbal and a rotary engine. This work advances the large‐scale production and application of DE artificial muscles.

Self-Powered, Flexible, Transparent Tactile Sensor Integrating Sliding and Proximity Sensing.

Tactile sensing is currently a research hotspot in the fields of intelligent perception and robotics. The method of converting external stimuli into electrical signals for sensing is a very effective strategy. Herein, we proposed a self-powered, flexible, transparent tactile sensor integrating sliding and proximity sensing (SFTTS). The principle of electrostatic induction and contact electrification is used to achieve tactile response when external objects approach and slide. Experiments show that the material type, speed, and pressure of the perceived object can cause the changes of the electrical signal. In addition, fluorinated ethylene propylene (FEP) is used as the contact electrification layer, and indium tin oxide (ITO) is used as the electrostatic induction electrode to achieve transparency and flexibility of the entire device. By utilizing the transparency characteristics of this sensor to integrate with optical cameras, it is possible to achieve integrated perception of tactile and visual senses. This has great advantages for applications in the field of intelligent perception and is expected to be integrated with different types of optical sensors in the future to achieve multimodal intelligent perception and sensing technology, which will contribute to the intelligence and integration of robot sensing.