Search results

The purpose of this paper is using a model-free reinforcement learning (RL) algorithm to optimize manipulability which can overcome difficulties of dilemmas of matrix inversion, complicated formula transformation and expensive calculation time.

Manipulability optimization is an effective way to solve the singularity problem arising in manipulator control. Some control schemes are proposed to optimize the manipulability during trajectory tracking, but they involve the dilemmas of matrix inversion, complicated formula transformation and expensive calculation time.

The redundant manipulator trained by RL can adjust its configuration in real-time to optimize the manipulability in an inverse-free manner while tracking the desired trajectory. Computer simulations and physics experiments demonstrate that compared with the existing methods, the average manipulability is increased by 58.9%, and the calculation time is reduced to 17.9%. Therefore, the proposed method effectively optimizes the manipulability, and the calculation time is significantly shortened.

To the best of the authors’ knowledge, this is the first method to optimize manipulability using RL during trajectory tracking. The authors compare their approach to existing singularity avoidance and manipulability maximization techniques, and prove that their method has better optimization effects and less computing time.

Most manufacturing plants choose the easy way of completely separating human operators from robots to prevent accidents, but as a result, it dramatically affects the overall quality and speed that is expected from human–robot collaboration. It is not an easy task to ensure human safety when he/she has entered a robot’s workspace, and the unstructured nature of those working environments makes it even harder. The purpose of this paper is to propose a real-time robot collision avoidance method to alleviate this problem.

In this paper, a model is trained to learn the direct control commands from the raw depth images through self-supervised reinforcement learning algorithm. To reduce the effect of sample inefficiency and safety during initial training, a virtual reality platform is used to simulate a natural working environment and generate obstacle avoidance data for training. To ensure a smooth transfer to a real robot, the automatic domain randomization technique is used to generate randomly distributed environmental parameters through the obstacle avoidance simulation of virtual robots in the virtual environment, contributing to better performance in the natural environment.

The method has been tested in both simulations with a real UR3 robot for several practical applications. The results of this paper indicate that the proposed approach can effectively make the robot safety-aware and learn how to divert its trajectory to avoid accidents with humans within the workspace.

The method has been tested in both simulations with a real UR3 robot in several practical applications. The results indicate that the proposed approach can effectively make the robot be aware of safety and learn how to change its trajectory to avoid accidents with persons within the workspace.

This paper provides a novel collision avoidance framework that allows robots to work alongside human operators in unstructured and complex environments. The method uses end-to-end policy training to directly extract the optimal path from the visual inputs for the scene.

The purpose of this paper is to present a markerless human–manipulators interface which maps the position and orientation of human end-effector (EE, the center of the palm) to those of robot EE so that the robot could copy the movement of the operator hand.

The tracking system of this human–manipulators interface comprises five Leap Motions (LMs) which not only makes up the narrow workspace drawback of one LM but also provides redundancies to improve the data precision. However, because of the native noises and tracking errors of the LMs, the measurement errors increase over time. To address this problem, two filter tools are integrated to obtain the relatively accurate estimation of the human EE, that is, Particle Filter for position estimation and Kalman Filter for orientation estimation. Because the operator has inherent perceptive limitations, the motions of the manipulator may be out of sync with the hand motions, so that it is hard to complete with the high performance manipulation. Therefore, in this paper, an over-damping method is adopted to improve reliability and accuracy.

A series of human–manipulators interaction experiments were carried out to verify the proposed system. Compared with the markerless and contactless methods(Kofman et al., 2007; Du and Zhang, 2015), the method described in this study is more accurate and efficient.

The proposed method would not hinder most natural human limb motion and allows the operator to concentrate on his/her own task, making it perform high-precision manipulations efficiently.

Climatic changes caused by greenhouse gases (GHGs) emissions are an urgent challenge for all regions around the globe while the livestock sector is an important source of GHGs emissions. The adoption of low-carbon manure treatment technology (LMTT) by farmers is emerging as an effective remedy to neutralize the carbon emissions of livestock. This paper aims to incorporate environmental literacy and social norms into the analysis framework, with the aim of exploring the impact of environmental literacy and social norms on farmers' adoption of LMTT and finally reduce GHGs emission and climate effects.

This research survey is conducted in Hebei, Henan and Hubei provinces of China. First, this research measures environmental literacy from environmental cognition, skill and responsibility and describes social norms from descriptive and imperative social norms. Second, this paper explores the influence of environmental literacy and social norms on the adoption of LMTT by farmers using the logit model. Third, Logit model's instrumental approach, i.e. IV-Logit, is applied to address the simultaneous biases between environmental skill and farmers’ LMTT adoption. Finally, the research used a moderating model to analyze feasible paths of environmental literacy and social norms that impact the adoption of LMTT by farmers.

The results showed that environmental literacy and social norms significantly and positively affect the adoption of LMTT by farmers. In particular, the effects of environmental literacy on the adoption of LMTT by farmers are mainly contributed by environmental skill and responsibility. The enhancement of social norms on the adoption of LMTT by farmers is mainly due to the leading role of imperative social norms. Meanwhile, if the endogeneity caused by the reverse effect between environmental skill and farmers’ LMTT adoption is dealt with, the role of environmental skill will be weakened. Additionally, LMTT technologies consist of energy and resource technologies. Compared to energy technology, social norms have a more substantial moderating effect on environmental literacy, affecting the adoption of farmer resource technology.

To the best of the authors’ knowledge, a novel attempt is made to examine the effects of environmental literacy and social norms on the adoption of LMTT by farmers, with the objective of identifying more effective factors to increase the intensity of LMTT adoption by farmers.

For fast calculation of complex structure in engineering, correlations among input variables are often ignored in uncertainty propagation, even though the effect of ignoring these correlations on the output uncertainty is unclear. This paper aims to quantify the inputs uncertainty and estimate the correlations among them acorrding to the collected observed data instead of questionable assumptions. Moreover, the small size of the experimental data should also be considered, as it is such a common engineering problem.

In this paper, a novel method of combining p-box with copula function for both uncertainty quantification and correlation estimation is explored. Copula function is utilized to estimate correlations among uncertain inputs based upon the observed data. The p-box method is employed to quantify the input uncertainty as well as the epistemic uncertainty associated with the limited amount of the observed data. Nested Monte Carlo sampling technique is adopted herein to ensure that the propagation is always feasible. In addition, a Kriging model is built up to reduce the computational cost of uncertainty propagation.

To illustrate the application of this method, an engineering example of structural reliability assessment is performed. The results indicate that it may significantly affect output uncertainty whether to quantify the correlation among input variables. Furthermore, an additional advantage for risk management is obtained in this approach due to the separation of aleatory and epistemic uncertainties.

The proposed method takes advantage of p-box and copula function to deal with the correlations and limited amount of the observed data, which are two important issues of uncertainty quantification in engineering. Thus, it is practical and has the ability to predict accurate response uncertainty or system state.

Applying the theory of work adjustment (TWA), the purpose of this paper is to investigate whether the effect of hierarchical plateau on the turnover intention of employees at the career establishment stage is mediated by job satisfaction and moderated by person-job fit.

A survey method was used and data were collected from 248 Chinese employees at the career establishment stage. Hierarchical regression analysis and moderated mediation analysis were used to test the hypotheses.

The results demonstrated that hierarchical plateau was positively related to the turnover intention of employees at the career establishment stage and that job satisfaction played a mediating role in the relationship. Person-job fit moderated the relationship between hierarchical plateau and job satisfaction, and the indirect effect of hierarchical plateau on turnover intention via job satisfaction.

This research offers new insights into the links between hierarchical plateau and employees’ work attitudes and withdrawal behaviour within the TWA. The results suggest that managers can lessen the negative effects of hierarchical plateau on employees’ attitudes and withdrawal behaviour by improving employees’ overall person-job fit.