Search results

The tactile sensor with array structure normally has the defects of existing nondetection zone, complex and nonstretchable structure. It is difficult to seamlessly attach to the surface of the robot. For this reason, this paper proposes a method to prepare nonarray structure tactile sensor directly on the surface of the robot by spraying process.

Based on the principle of gradient potential distribution, the potential fields are constructed in two different directions over the conductive film in time-sharing. The potentials at touching position in the two directions are detected to determine the coordinate of the touching point. The designed tactile sensor based on this principle consists of only three layers. Its bottom layer is designed as a weak conductive film made of graphite coating and used to construct the potential field. It can be sprayed either on PET substrate or directly on robot surface.

The radial basis function neural network is used for remodeling the potential distribution, which can effectively solve the problem of nonlinear potential distribution caused by irregular sensor shape, and uneven conductivity at different points of the spraying coating. The simulation and experimental results show that the principle of the proposed tactile sensor used for touching position detection is feasible to be applied to complex surfaces of the robot.

This paper proposed a nonarray customizable tactile sensor based on the spraying process. The sensor has a simple structure, and only five lead wires are needed to realize the coordinate detection of the touch position.

This study aims to address the issue that existing methods for limb action recognition typically assume a fixed wearing orientation of inertial sensors, which is not the case in real-world human-robot interaction due to variations in how operators wear it, installation errors, and sensor movement during operation.

To address the resulting decrease in recognition accuracy, this paper introduced a data transformation algorithm that integrated the Euclidean norm with singular value decomposition. This algorithm effectively mitigates the impact of orientation errors on data collected by inertial sensors. To further enhance recognition accuracy, this paper proposed a method for extracting features that incorporate both time-domain and time-frequency domain features, markedly improving the algorithm’s robustness. This paper used five classifiers to conduct comparative experiments on action recognition. Finally, this paper built an experimental human-robot interaction platform.

The experimental results demonstrate that the proposed method achieved an average action recognition accuracy of 96.4%, conclusively proving its effectiveness. This approach allows for the recognition of data from sensors placed in any orientation, using only training samples conducted at an orientation.

This study addresses the challenge of reduced accuracy in limb action recognition caused by sensor misorientation. The human-robot interaction system developed in this paper was experimentally verified to effectively and efficiently guide the industrial robot to perform tasks based on the operator’s limb actions.

Polishing is a crucial process in mechanical manufacturing. The use of industrial robots to automate polishing is an inevitable trend in future developments. However, current robotic polishing tools are too large to reach inside deep holes or grooves in workpieces. This study aims to use a pneumatic artificial muscle (PAM) as the actuator and designs a force-controlled end-effector to reach inside the deep and narrow areas in the workpiece.

This approach first addresses the challenge of converting the tensile force generated by the PAM into pushing force through mechanism design. In addition, a dynamics model of the end-effector was established based on the three-element model of the PAM. A combined control strategy was proposed to enhance force control accuracy and adaptability during the polishing process.

Experiments were conducted on a robotic platform equipped with the proposed end-effector. The experimental results demonstrate that the end-effector can polish the inner end face of holes or grooves with diameters as small as 80 mm and depths reaching 200 mm. By implementing the combined control strategies, the target force tracking error was reduced by 48.66% compared to the use of the PID controller alone.

A new force-controlled end-effector based on the PAM is designed for robotic polishing. According to the experimental result, this end-effector can polish not only the outer surfaces of the workpiece but also the internal surfaces of workpieces with deep holes or grooves specifically. By using the combined control strategy proposed in this paper, the end-effector significantly improves force control precision and polishing quality.

This paper aims to report a flexible position-sensitive sensor that can be applied as large-area electronic skin over the stiff media.

The sensor uses a whole piezoresistive film as a touch sensing area. By alternately constructing two uniform electric fields with orthogonal directions in the piezoresistive film, the local changes in conductivity caused by touch can be projected to the boundary along the equipotential line under the constraint of electric field. Based on the change of boundary potential in the two uniform electric fields, it can be easy to determine the position of the contact area in the piezoresistive film.

Experiment results show the proposed tactile sensor is capable of detecting the contact position and classifying the contact force in real-time based on the changes of the potential differences on the boundary of the sensor.

The application example of using the sensor sample as a controller in shooting game is presented in this paper. It shows that the sensor has excellent touch sensing performance.

In this paper, a position-sensitive electronic skin is proposed. The experiment results show that the sensor has great application prospects in the field of interactive tactile sensing.

Imitation learning is a powerful tool for planning the trajectory of robotic end-effectors in Cartesian space. Present methods can adapt the trajectory to the obstacle; however, the solutions may not always satisfy users, whereas it is hard for a nonexpert user to teach the robot to avoid obstacles in time as he/she wishes through demonstrations. This paper aims to address the above problem by proposing an approach that combines human supervision with the kernelized movement primitives (KMP) model.

This approach first extracts the reference database used to train KMP from demonstrations by using Gaussian mixture model and Gaussian mixture regression. Subsequently, KMP is used to modulate the trajectory of robotic end-effectors in real time based on feedback from its interaction with humans to avoid obstacles, which benefits from a novel reference database update strategy. The user can test different obstacle avoidance trajectories in the current task until a satisfactory solution is found.

Experiments performed with the KUKA cobot for obstacle avoidance show that this approach can adapt the trajectories of the robotic end-effector to the user’s wishes in real time, including trajectories that the robot has already passed and has not yet passed. Simulation comparisons also show that it exhibits better performance than KMP with the original reference database update strategy.

An interactive learning approach based on KMP is proposed and verified, which not only enables users to plan the trajectory of robotic end-effectors for obstacle avoidance more conveniently and efficiently but also provides an effective idea for accomplishing interactive learning tasks under constraints.

The aim of the research is to achieve a robot skin which is easy to use, and can detect both position and force interacted between robot and environments.

The new type of robot skin proposed in this paper includes two functional modules – contact position sensor and contact force sensor. The contact position sensor module is based on the resistor divider principle, which consists of two perpendicular conductive fiber layers and insulated dot spacer between them. The contact force sensor module is based on capacitance change theory, which consists of two soft conductive plates and a viscoelastic layer between them. By combining the two modules, the soft robot skin was designed.

Simulation and experiment results demonstrate that the proposed robot skin design is feasible and effective enough to sense contact position and contact force simultaneously.

This robot skin is low-cost and easy to make and use, which provides safety solutions for most of the robot.

For the first time, an integrated robot skin which can get contact position and force information simultaneously is designed. Unlike general tactile sensor matrices, this robot skin has only six leads. Furthermore, the number of leads does not increase with the enlarging of sensor area. Soft and simple structure of the robot skin makes it possible to cover any region of the robot body.

The purpose of this study is to explore a new assembly process planning and execution mode to realize rapid response, reduce the labor intensity of assembly workers and improve the assembly efficiency and quality.

Based on the related concepts of digital twin, this paper studies the product assembly planning in digital space, the process execution in physical space and the interaction between digital space and physical space. The assembly process planning is simulated and verified in the digital space to generate three-dimensional visual assembly process specification documents, the implementation of the assembly process specification documents in the physical space is monitored and feed back to revise the assembly process and improve the assembly quality.

Digital twin technology enhances the quality and efficiency of assembly process planning and execution system.

It provides a new perspective for assembly process planning and execution, the architecture, connections and data acquisition approaches of the digital twin-driven framework are proposed in this paper, which is of important theoretical values. What is more, a smart assembly workbench is developed, the specific image classification algorithms are presented in detail too, which is of some industrial application values.

The purpose of this paper is to propose a new approach for aerodynamic parameter identification of hypersonic vehicles, which is based on Pigeon-inspired optimization (PIO) algorithm, with the objective of overcoming the disadvantages of traditional methods based on gradient such as New Raphson method, especially in noisy environment.

The model of hypersonic vehicles and PIO algorithm is established for aerodynamic parameter identification. Using the idea, identification problem will be converted into the optimization problem.

A new swarm optimization method, PIO algorithm is applied in this identification process. Experimental results demonstrated the robustness and effectiveness of the proposed method: it can guarantee accurate identification results in noisy environment without fussy calculation of sensitivity.

The new method developed in this paper can be easily applied to solve complex optimization problems when some traditional method is failed, and can afford the accurate hypersonic parameter for control rate design of hypersonic vehicles.

In this paper, the authors converted this identification problem into the optimization problem using the new swarm optimization method – PIO. This new approach is proved to be reasonable through simulation.

The purpose of this paper is to present and implement a task allocation method based on game theory for reconnaissance mission planning of UAVs and USVs system.

In this paper, the decision-making framework via game theory of mission planning is constructed. The mission planning of UAVs–USVs is transformed into a potential game optimization problem by introducing a minimum weight vertex cover model. The modified population-based game-theoretic optimizer (MPGTO) is used to improve the efficiency of solving this complex multi-constraint assignment problem.

Several simulations are carried out to exhibit that the proposed algorithm obtains the superiority on quality and efficiency of mission planning solutions to some existing approaches.

Several simulations are carried out to exhibit that the proposed algorithm obtains the superiority on quality and efficiency of mission planning solutions to some existing approaches.

The proposed framework and algorithm are expected to be applied to complex real scenarios with uncertain targets and heterogeneity.

The decision framework via game theory is proposed for the mission planning problem of UAVs–USVs and a MPGTO with swarm evolution, and the adaptive iteration mechanism is presented for ensuring the efficiency and quality of the solution.

The purpose of this study is to propose a new consumer value segmentation method for low-dimensional dense market datasets to quickly detect and cluster the most profitable customers for the enterprises.

In this study, the comprehensive segmentation bases (CSB) with richer meanings were obtained by introducing the weighted recency-frequency-monetary (RFM) model into the common segmentation bases (SB). Further, a new market segmentation method, the CSB-MBK algorithm was proposed by integrating the CSB model and the mini-batch k-means (MBK) clustering algorithm.

The results show that our proposed CSB model can reflect consumers' contributions to a market, as well as improve the clustering performance. Moreover, the proposed CSB-MBK algorithm is demonstrably superior to the SB-MBK, CSB-KMA and CSB-Chameleon algorithms with respect to the Silhouette Coefficient (SC), the Calinski-Harabasz (CH) Index , the average running time and superior to the SB-MBK, RFM-MBK and WRFM-MBK algorithms in terms of the inter-market value and characteristic differentiation.

This paper provides a tool for decision-makers and marketers to segment a market quickly, which can help them grasp consumers' activity, loyalty, purchasing power and other characteristics in a target market timely and achieve the precision marketing.

This study is the first to introduce the CSB-MBK algorithm for identifying valuable customers through the comprehensive consideration of the clustering quality, consumer value and segmentation speed. Moreover, the CSB-MBK algorithm can be considered for applications in other markets.