Robot Applications Research Articles

Impact of industrial robot on labour productivity: Empirical study based on industry panel data

This empirical analysis explores the impact of industrial robots on labour productivity using panel data of 17 Chinese industries from 2006 to 2021. The results reveal that the development of industrial robots significantly improves labour productivity; a series of robustness tests validate this outcome. However, the impact of industrial robots on labour productivity varies across industry types. The influence coefficient of the low-density robotics industry is larger than that of the high-density robotics industry. Furthermore, although the scale of industrial robot usage before 2012 was smaller than that after 2012, its effect on labour productivity was more significant. Our findings indicate the possibility of diminishing marginal effect of industrial robots in promoting labour productivity. The mechanism analysis demonstrates that human capital level has a complete intermediating effect between industrial robots and labour productivity. Thus, industrial robot applications can contribute to labour productivity by optimising human capital structure. These findings provide crucial insights for governments and policy makers to improve labour productivity and economic growth.

Multi-scene application of intelligent inspection robot based on computer vision in power plant

As industries develop, the automation and intelligence level of power plants is constantly improving, and the application of patrol robots is also increasingly widespread. This research combines computer vision technology and particle swarm optimization algorithm to build an obstacle recognition model and obstacle avoidance model of an intelligent patrol robot in a power plant respectively. Firstly, the traditional convolutional recurrent neural network is optimized, and the obstacle recognition model of an intelligent patrol robot is built by combining the connection timing classification algorithm. Then, the artificial potential field method optimizes the traditional particle swarm optimization algorithm, and an obstacle avoidance model of an intelligent patrol robot is built. The performance of the two models was tested, and it was found that the highest precision, recall, and F1 values of the identification model were 0.978, 0.974, and 0.975. The highest precision, recall, and F1 values of the obstacle avoidance model were 0.97, 0.96, and 0.96 respectively. The two optimization models designed in this research have better performance. In conclusion, the two models in this study are superior to the traditional methods in recognition effect and obstacle avoidance efficiency, providing an effective technical scheme for intelligent patrol inspection of power plants.

Simplified Strategy for Trajectory Tracking Application of a Passive Suspension Rover-Type Mobile Robot

In the present work, based on an approximate modelling of a rover-type robot and a proportional control law, a simplified trajectory tracking strategy for a passive suspension rover-type mobile robot was developed. This strategy achieves trajectory tracking and the autonomous displacement of a rover, of which its configuration involves complex kinematics and dynamics. All these lineaments reduce the complexity of the analysis, the number of electronic components to implement, the computational requirements and the energy consumption. The robotic system used is based on the Shrimp rover, which is a robot with a passive suspension that is capable of carrying out displacements over rough terrain. The tests were performed using numerical simulations with different desired trajectories, and also using experimental tests using a passive suspension rover-type mobile robot.

Enhancing the Mobility of Small-Scale Robots Via Nonlinear Structural Springs Exhibiting Negative Stiffness

Abstract Compared to traditional robotic systems, small-scale robots, ranging from several millimeters to micrometres in size, are capable of reaching narrower and vulnerable regions with minimal damage. However, conventional small-scale robots’ limited maneuverability and controlability hinder their ability to effectively navigate in the intricate environments, such as the gastrointestinal tract. Self-propelled capsule robots driven by vibrations and impacts emerge as a promising solution, holding the potentials to enhance diagnostic accuracy, enable targeted drug delivery, and alleviate patient discomfort during gastrointestinal endoscopic procedures. This paper builds upon our previous work on self-propelled capsule robots, exploring the potential of nonlinear connecting springs to enhance its propulsion capabilities. Leveraging a mathematical model for self-propelling robots with a von Mises truss spring, which is verified using a finite element model, we investigate the effects of negative stiffness and snap-back within the nonlinear structural spring on the robots’ propelling speed. Our analysis reveals that the negative stiffness of the von Mises truss can significantly reduce the sensitivity of the propelling speed to excitation frequency. As a result, the capsule robot exhibits a remarkably wider operational band where it maintains a high average propelling speed, surpassing its linear counterpart. This work sheds light on the potential for developing customized nonlinear structural systems for diverse scenarios in small-scale robot applications, opening up new possibilities for enhanced functionality and maneuverability in various biomedical applications.

Composite continuum robots: Accurate modeling and model reduction

Models of continuum robots often trade off accuracy and speed. The constant curvature assumption model can perform fast calculations but with poor accuracy. Static models can obtain good calculation accuracy but with slower computation speed. In this paper, a precise and efficient method for establishing a non-constant curvature kinematic model for composite continuum robots is proposed. First, an algorithm based on the Beam Constraint Model is proposed to establish the static model of the continuum robot. The situation in which friction changes gradually in continuum robots is considered in the static model. Then, the Kepler elliptic curve is used to simplify the static model to build a non-constant curvature kinematic model of the continuum robot. Then, complex inverse kinematics solutions are transformed into explicit sets of equations by mathematical transformation. Finally, simulations and experiments are designed to demonstrate the algorithm proposed in this paper. The simulation results show that the proposed algorithm is 1572 times faster than the Levenberg–Marquardt algorithm. The experimental results show that the average error of the static model is 0.065 mm, accounting for 0.13% of its length. The maximum error is 0.309 mm, accounting for 0.618% of its length. The positioning accuracy of the non-constant curvature model proposed in this paper is 2.02 times that of the constant curvature model. The results show that the simplified kinematic model algorithm based on the static model has high accuracy and computational efficiency. This research is crucial for the practical application of continuum robots in engineering.

Electronic skin with shape sensing and Bending-Insensitive pressure sensing for soft robotic grippers object recognition

Soft robotic grippers rely on accurate contact surface information to perform gripping and sorting tasks safely. Difficulty in obtaining accurate contact surface information for recognizing objects with a single type of sensor hinders the advanced capabilities of soft robotic grippers. To obtain contact surface information more accurately for object recognition, in this paper a shape-pressure dual-mode electronic skin for contact surface detection of soft robotic grippers is proposed. It consists of pressure sensing units and curvature sensing units. The pressure sensing unit is insensitive to curvature through an ingenious structural design. It can detect pressure in the range of 0–––7.5 N with a measurement error of 3.92 %. The curvature sensing unit can detect curvature in the range of 0–––0.5 cm−1 with a sensitivity of 63.66 % / cm-1. The experimental results show that the electronic skin can help the soft robotic gripper obtain information on the contact surface. The electronic skin is expected to accelerate the application of soft robots in advanced tasks such as recognition and classification.

A soft robot tactile fingertip for grasping surface posture detection

Abstract The application field of robots is gradually extending from traditional industrial manufacturing to commercial services, medical care and other fields. Stable grasping is a necessary prerequisite for various complex robot application scenarios. The existing research on robot tactile sensor mainly focus on sensing tactile information, such as pressure or sliding. However, grasping surface posture as a tactile information that has a significant impact on the stability of grasping is often ignored. This study proposed a novel soft robot tactile fingertip that can not only detect the grasping force but also simultaneously detect the grasping surface posture. It is capable of recognizing 19 grasping surface postures in real-time using Mamdani fuzzy control method. The soft robot tactile fingertip has a simple structure and easy to fabricate at low cost. The application example of the two-finger mechanical hand using the soft tactile fingertip samples for stable grasping is demonstrated. This study shows that the soft robot tactile fingertip has great application prospects in the filed of robot intelligent grasping.

Deep reinforcement learning and decoupling proportional-integral-derivative control of a humanoid cable-driven hybrid robot

Aiming at the application of robots in service, medical treatment, rehabilitation, and other fields, a humanoid cable-driven hybrid robot by imitating the structure of human arm is designed in this article. The robot is composed of a cable–spool–pulley system, series mechanism, and coaxial spherical parallel mechanism, which can achieve six degrees of freedom movement in space. A challenge with cable driving is that the movement of the rear end joints (such as pitch and roll) can alter the length or tension of the cable driven by the frontend joints, resulting in joint coupling. This interference can lead to a decrease in the motion accuracy of the robotic arm. In addition, it also affects the durability of cables or mechanical components such as bearings and pulleys. Considering the joint motion coupling phenomenon caused by the cable-driven, the decoupling method is proposed, and the kinematic model of the robot is established. To solve the nonlinear coupling characteristics and the uncertainty of the dynamics parameters, a controller is proposed for the humanoid cable-driven hybrid robot, combining proportional-integral-derivative (PID) control based on decoupling method (DC-PID) and the double delay deep deterministic policy gradient (TD3) deep reinforcement learning algorithm. The trajectory tracking of the end-effector position and orientation are controlled by using DC-PID and TD3. And the simulation results show that the proposed control method has good trajectory tracking and convergence performance according to trajectory tracking error and training reward. Finally, the humanoid cable-driven hybrid robot prototype is developed. The experimental results of coupling compensation show that the average maximum error of the joint is reduced by 77.58% after considering the coupling compensation of the joint. The results of the controller validation experiments show that the DC-PID controller reduces the maximum error in each axis by 11.54%, 35.29%, and 40.16%, respectively, compared to the open-loop experiments.

Gas source localization using Dueling Deep Q-Network with an olfactory quadruped robot

Gas source localization is one of the most common applications of a gas-sensitive mobile robot. However, most of the existing work focuses on rule-based algorithms for wheeled robots, which are difficult to apply in complex terrain with obstacles. In this article, we propose an olfactory quadruped robot to perform the gas source localization task using the Dueling Deep Q-Network (Dueling DQN) algorithm. For training, we designed a set of environments and imported gas dispersion data from computational fluid dynamics (CFD) software to construct a simulator. The olfactory quadruped robot was trained in this simulator using the Dueling DQN algorithm to learn how to find the gas source. The trained neural network was then deployed on the olfactory quadruped robot. Our method has been tested in both simulation and real environments. The olfactory quadruped robot can traverse rugged terrain in real experiments and efficiently find gas sources, demonstrating that our method is highly robust and has important practical value.

Shadow Detection and Elimination for Robot and Machine Vision Applications

Shadow removal is crucial for robot and machine vision as the accuracy of object detection is greatly influenced by the uncertainty and ambiguity of the visual scene. In this paper, we introduce a new algorithm for shadow detection and removal based on different shapes, orientations, and spatial extents of Gaussian equations. Here, the contrast information of the visual scene is utilized for shadow detection and removal through five consecutive processing stages. In the first stage, contrast filtering is performed to obtain the contrast information of the image. The second stage involves a normalization process that suppresses noise and generates a balanced intensity at a specific position compared to the neighboring intensities. In the third stage, the boundary of the target object is extracted, and in the fourth and fifth stages, respectively, the region of interest (ROI) is highlighted and reconstructed. Our model was tested and evaluated using realistic scenarios which include outdoor and indoor scenes. The results reflect the ability of our approach to detect and remove shadows and reconstruct a shadow free image with a small error of approximately 6%.

Fast loop closure detection using probabilistic integration of pose and appearance similarity

Loop closure detection is a key technique for robots to minimize the accumulated localization and mapping errors after long-time explorations of simultaneous localization and mapping. However, the requirement for efficiency and accuracy performance for mobile robot applications is not well satisfied. In this article, we propose a fast and accurate loop closure detection method by exploiting both pose-based and appearance-based information in a probabilistic manner, inspired by the complementarity between the pose-based and the appearance-based information. Our approach formulates a probability framework combing the pose-based loop closure detection probability and the appearance-based loop closure detection probability. In the proposed framework, the pose-based loop closure detection model is firstly derived from the nonlinear optimization model of odometry. Then the appearance-based loop similarity and the pose-based loop similarity are combined into a joint framework to improve the loop closure detection performance. We implemented our approach using C++ and ROS and thoroughly tested it on the publicly available datasets. The experiments presented in this article suggest that the proposed method can achieve high efficiency and accuracy performance on loop closure detection.

Flatness‐based control in successive loops for mechatronic motion transmission systems

AbstractMechatronic systems with nonlinear dynamics are met in motion transmission applications for vehicles and robots. In this article, the control problem for the nonlinear dynamics of mechatronic motion transmission systems is solved with the use of a flatness‐based control approach which is implemented in successive loops. The state‐space model of these systems is separated into a series of subsystems, which are connected between them in cascading loops. Each one of these subsystems can be viewed independently as a differentially flat system, and control about it can be performed with inversion of its dynamics as in the case of input–output linearized flat systems. In this chain of subsystems, the state variables of the subsequent ( )‐th subsystem become virtual control inputs for the preceding ‐th subsystem and so on. In turn, exogenous control inputs are applied to the last subsystem and are computed by tracing backwards the virtual control inputs of the preceding subsystems. The whole control method is implemented in successive loops, and its global stability properties are also proven through Lyapunov stability analysis. The validity of the control method is confirmed in the following two case studies: (a) control of a permanent magnet linear synchronous motor (PMLSM)‐actuated vehicle's clutch and (ii) control of a multi‐Degrees of Freedom (multi‐DOF) flexible joint robot.

Deep learning-based predicting and compensating method for the pose deviations of parallel robots

The static pose accuracy is regarded as a crucial performance indicator for parallel robots, which is inevitably affected by the geometric and nongeometric errors. However, an accurate error model for parallel robots is highly complex, especially for mathematical modeling and identifying non-geometric errors. This limitation hampers the application of parallel robots in high-precision processing and manufacturing fields. To enhance the performance of parallel robots and address the complexities in establishing their error models, a deep learning-based predicting and compensating method is investigated, which can accurately predict their pose deviations. This method ingeniously integrates the spatial feature extraction capabilities of convolutional neural networks, the bidirectional dependency capturing prowess of bilateral long short-term memory networks, and the feature significance discernment offered by squeeze-and-excitation networks. Subsequently, the pose deviations are definitely predicted by this method and are pre-compensated into nominal pose so as to improve the performance. A pose-deviation pairs dataset is established to accomplish the comparison of the investigated method with the two commonly used artificial neural network and long short-term memory on the 6-UPS parallel robot. Experiment on the 6-UPS parallel robot against traditional kinematic calibration methods demonstrate the investigated method achieves satisfactory pose accuracies, with the ability to reduce pose deviations by 88.60 %. Meanwhile, the effectiveness and general applicability of this method have also been validated by successful implementation on a 6-UCU parallel robot.

A multi-directional magnetic-driven multifunctional soft crawling robot

Multifunctional and multi-freedom integrated magnetic-driven soft robots have received widespread attention in the past decade. However, the current magnetic-driven soft crawling robots with multiple functional modules focus on the development of new materials or innovation of driving component. Herein, we propose a soft crawling robot that materializes multi-directional motion driven only through a unidirectional magnetic field (MF) while possessing the ability to communication, loading, and positioning. The locomotion of robot relies on ingenious leg design to generate differences in friction between each leg and the ground by controlling the MF intensity. The integrated wireless communication modules on the robot's legs serve as a medium for interacting with the external world, enabling the robot to effectively perceive the environment via electromagnetic coupling. In addition, the magnetic-driven soft crawling robot carries loads (3.37 g) larger than twice its own weight for motion. Overall, this work showcases a new paradigm for robot applications, providing a practicable idea for developing miniaturization, multi-directional soft crawling robots.

A Compact Aerial Manipulator: Design and Control for Dexterous Operations

The lack of aerial physical interaction capability is one of the choke points limiting the extension of aerial robot applications, such as rescue missions and aerial maintenance. We present a new aerial robotic manipulator (AEROM) for aerial dexterous operations in this work. It contains a robotic manipulator with 6-degree-of-freedom and a compact flight platform. Firstly, we propose a quantitative capability index to evaluate and guide the mechanical design of the AEROM. Based on the proposed quantitative index, we construct a lightweight bird-inspired manipulator to imitate a raptor hindlimb. An additional telescopic joint and an end-effector consisting of three soft fingers allow the AEROM to execute aerial interaction tasks. In addition, the wrist joints enable independent control of the end-effector attitude regardless of the flight platform. After explicitly analyzing the multi-source disturbances during the aerial operation tasks, we develop a refined anti-disturbance controller to compensate for the disturbances with different characteristics. The proposed controller further improves the position accuracy of end-effector to enable dexterous operations during aerial interaction tasks. Finally, the physical experiments verify the effectiveness of the proposed AEROM system.

Investigation on position and attitude estimation and control of manipulator based on machine vision

With the development of science and technology, people have higher and higher requirements for robots. The application of robots in industrial production is also increasing, and there are more applications in people’s lives. Therefore, robots must have a better ability to receive and process the external environment. Therefore, visual servo system appears. Pose estimation is a major problem in the current vision system. It has great application value in positioning and navigation, target tracking and recognition, virtual reality and motion estimation. Therefore, this paper put forward the research of robot arm pose estimation and control based on machine vision. This paper first analyzed the technology of machine vision, and then carried out experiments. The accuracy and stability of the two methods for robot arm pose estimation were compared. The experimental results showed that when the noise of Kalman’s centralized data fusion method was 1 pixel, the maximum error of the X-axis angle was only 0.55, and the average error was 0.02. In Kalman’s distributed data fusion method, the average error of X-axis displacement was 0.06, and the maximum value was 17.66. In terms of accuracy, Kalman’s centralized data fusion method was better. In terms of stability, Kalman’s centralized data fusion method was also better. However, in general, these two methods had very good results, and could accurately control the position and posture of the manipulator.

Crack-insensitive fracture of elastomer-based soft network materials under monotonic and cyclic loads

In various applications of stretchable electronics and soft robots, soft materials are subjected to long-term load-bearing conditions, requiring them to possess good extreme mechanical properties such as highly stretchable, strong, fracture-resistant and anti-fatigue. Conventional soft materials with a single polymer network typically exhibit relatively low fracture resistance, while commonly employed toughening method involves introducing mechanical dissipation into original polymer networks often require complicated chemical synthesis and result in significant hysteresis under cyclic loads. Designing soft solid materials into soft network materials with periodic lattice structure paving another effective route to improve the fracture-resistant performance of soft materials, which has not been reported in the literature. This work provides a combined experimental and computational study on the mechanical properties and fracture behaviors of elastomer-based soft network materials with/without a precut crack under monotonic and cyclic loads, aiming to present a structural design strategy for fracture-resistant soft materials. The elastomer-based soft network materials are proven to be crack-insensitive, low-hysteresis and anti-fatigue. The nonlinear finite element analysis (FEA) is employed to reveal the underlying mechanism of crack-insensitivity in elastomer-based soft network materials. Both the mechanical properties and deformed configurations of soft network materials with/without a precut crack are accurately predicted by the FEA method. The effect of microstructure geometry and network topology on the mechanical properties of soft network materials is systematically studied. Under various amplitudes of cyclic applied strain, the elastomer-based soft network materials can survive even after individual microstructures ruptured, and the fatigue fracture process slows down as the applied strain amplitude decreases. In contrast to the behavior observed in monotonic loads where fracture initiates at the microstructure located ahead of the crack tip, fatigue fracture initiation in soft network materials with a precut crack exhibits a random distribution.

Real-time adaptive super twisting algorithm based on PSO algorithm: application for an exoskeleton robot

Abstract In this paper, an online adaptive super twisting sliding mode controller is proposed for a non-linear system. The adaptive controller has been designed in order to deal with the unknown dynamic uncertainties and give the best trajectory tracking. The adaptation is based on an optimal Particle Swarm Optimization (PSO) algorithm whose goal is online tuning the parameters through focusing on decreasing the objective function. The novelty of this study is online handling parameters setting in the conventional super twisting algorithm, bypass heavy offline calculation, and also avoid the instability and abrupt changing of the controller’s parameters for better actuators lifetime. This novel approach has been applied on an upper limb exoskeleton robot for arm rehabilitation. Despite the changes of the dynamic model of the system which defers from one patient to another due to the direct interactions between the wearer and the exoskeleton, this control technique preserves its robustness with respect to bounded external disturbances. The effectiveness of the proposed adaptive controller has been proved in simulation and then in real-time experiment with two human subjects. A comparison between the proposed approach and classic super twisting algorithm has been conducted. The obtained results show the performance and efficiency of the proposed controller.

A Soft Collaborative Robot for Contact-based Intuitive Human Drag Teaching.

Soft material-based robots, known for their safety and compliance, are expected to play an irreplaceable role in human-robot collaboration. However, this expectation is far from real industrial applications due to their complex programmability and poor motion precision, brought by the super elasticity and large hysteresis of soft materials. Here, a soft collaborative robot (Soft Co-bot) with intuitive and easy programming by contact-based drag teaching, and also with exceptional motion repeatability (< 0.30% of body length) and ultra-low hysteresis (< 2.0%) is reported. Such an unprecedented capability is achieved by a biomimetic antagonistic design within a pneumatic soft robot, in which cables are threaded to servo motors through tension sensors to form a self-sensing system, thus providing both precise actuation and dragging-aware collaboration. Hence, the Soft Co-bots can be first taught by human drag and then precisely repeat various tasks on their own, such as electronics assembling, machine tool installation, etc. The proposed Soft Co-bots exhibit a high potential for safe and intuitive human-robot collaboration in unstructured environments, promoting the immediate practical application of soft robots.

Efficient real-time positioning using Bayesian analysis and magnetic anomaly field

Despite the prevalence of well-established and explored navigation systems, alternative localization methods are currently the focus of intensive research. This interest is driven by geopolitical challenges and increasingly sophisticated applications of mobile robots and uncrewed aerial vehicles. This study investigates the problem of real-time positioning in GPS-denied environments. Based on the mapped magnetic anomaly field and using Bayesian formalism for data fusion, the localization obtained from embedded sensors is corrected to reduce cumulative errors. The proposed method has minimal computational cost and a minimal number of tunable parameters. The paper introduces it and demonstrates its effectiveness in a laboratory study. Experimental tests, using a system equipped with an Inertial Measurement Unit, demonstrated a significant reduction in localization uncertainty. The improvement was especially notable in areas with large, smooth variations in the magnetic field. Finally, the accuracy of the method is analyzed, and its performance is compared to a particle filter.