Yu Du, Jipan Jian, Zhiming Zhu, Dehua Pan, Dong Liu and Xiaojing Tian
Aiming at the problems of weak generalization of robot imitation learning methods and higher accuracy requirements of low-level detectors, this study aims to propose an imitation…
Abstract
Purpose
Aiming at the problems of weak generalization of robot imitation learning methods and higher accuracy requirements of low-level detectors, this study aims to propose an imitation learning method based on structural grammar.
Design/methodology/approach
The paper proposes a hybrid training model based on artificial immune algorithm and the Baum–Welch algorithm to extract the action information of the demonstration activity to form the {action-object} sequence and extract the symbol description of the scene to form the symbol primitives sequence. Then, probabilistic context-free grammar is used to characterize and manipulate these sequences to form a grammar space. Minimum description length criteria are used to evaluate the quality of the grammar in the grammar space, and the improved beam search algorithm is used to find the optimal grammar.
Findings
It is found that the obtained general structure can parse the symbol primitive sequence containing noise and obtain the correct sequence, thereby guiding the robot to perform more complex and higher-order demonstration tasks.
Practical implications
Using this strategy, the robot completes the fourth-order Hanoi tower task has been verified.
Originality/value
An imitation learning method for robots based on structural grammar is first proposed. The experimental results show that the method has strong generalization ability and good anti-interference performance.
Details
Keywords
Zhenghai Liu, Hui Tang, Dong Liu, Jingji Zhao, Xinyue Zhu, Yu Du, Xiaojing Tian and Ming Cong
In response to the complex external structure of high-precision aviation plugs, which makes it difficult to search outside the hole and adjust inside the hole during automated…
Abstract
Purpose
In response to the complex external structure of high-precision aviation plugs, which makes it difficult to search outside the hole and adjust inside the hole during automated assembly. This paper aims to propose an assembly framework that combines multi-agent search and variable parameter compliant control to solve this problem.
Design/methodology/approach
First, a multi-agent search strategy (MAS) based on Gaussian Mixture Model and Deep Q-Network was proposed to optimize displacement direction and actions, thereby improving search speed and success rate. Then, a variable parameter admittance control method (RL-VPA) based on dual delay depth deterministic policy gradient (TD3) was proposed, which dynamically optimized the internal parameters of the admittance controller and adopted state space discretization to improve convergence speed and assembly efficiency.
Findings
Compared to spiral search and single-agent search, the average search success rate has improved by approximately 10% and 6.6%. Compared to fixed admittance control and other RL-based methods, the average assembly success rate has increased by approximately 38.6%, 22% and 8.6%. Compared with the training results of the model without state discretization, it was found that state discretization helps the model converge quickly. To verify the generalization ability of the assembly framework, experiments were conducted on three different pin counts of aviation plugs, the assembly success rate reached 86.7%, all of which showed good assembly results. Finally, combining state space discretization to reduce the impact of environmental noise, improve training effectiveness and convergence speed.
Originality/value
MAS has been proposed to optimize displacement direction and action, improving search speed and success rate. RL-VPA is designed to dynamically optimize the internal parameters of the admittance controller, enhancing the robustness and generalization ability of the model. Additionally, state space discretization is combined to improve training effectiveness and convergence speed.
Details
Keywords
Minghao Wang, Ming Cong, Yu Du, Dong Liu and Xiaojing Tian
The purpose of this study is to solve the problem of an unknown initial position in a multi-robot raster map fusion. The method includes two-dimensional (2D) raster maps and…
Abstract
Purpose
The purpose of this study is to solve the problem of an unknown initial position in a multi-robot raster map fusion. The method includes two-dimensional (2D) raster maps and three-dimensional (3D) point cloud maps.
Design/methodology/approach
A fusion method using multiple algorithms was proposed. For 2D raster maps, this method uses accelerated robust feature detection to extract feature points of multi-raster maps, and then feature points are matched using a two-step algorithm of minimum Euclidean distance and adjacent feature relation. Finally, the random sample consensus algorithm was used for redundant feature fusion. On the basis of 2D raster map fusion, the method of coordinate alignment is used for 3D point cloud map fusion.
Findings
To verify the effectiveness of the algorithm, the segmentation mapping method (2D raster map) and the actual robot mapping method (2D raster map and 3D point cloud map) were used for experimental verification. The experiments demonstrated the stability and reliability of the proposed algorithm.
Originality/value
This algorithm uses a new visual method with coordinate alignment to process the raster map, which can effectively solve the problem of the demand for the initial relative position of robots in traditional methods and be more adaptable to the fusion of 3D maps. In addition, the original data of the map can come from different types of robots, which greatly improves the universality of the algorithm.
Details
Keywords
Minghao Wang, Ming Cong, Dong Liu, Yu Du, Xiaojing Tian and Bing Li
The purpose of this study is to designed a robot odometry based on three dimensional (3D) laser point cloud data, inertial measurement unit (IMU) data and real-time kinematic…
Abstract
Purpose
The purpose of this study is to designed a robot odometry based on three dimensional (3D) laser point cloud data, inertial measurement unit (IMU) data and real-time kinematic (RTK) data in underground spatial features and gravity fluctuations environment. This method improves the mapping accuracy in two types of underground space: multi-layer space and large-scale scenarios.
Design/methodology/approach
An IMU–Laser–RTK fusion mapping algorithm based on Iterative Kalman Filter was proposed, and the observation equation and Jacobian matrix were derived. Aiming at the problem of inaccurate gravity estimation, the optimization of gravity is transformed into the optimization of SO(3), which avoids the problem of gravity over-parameterization.
Findings
Compared with the optimization method, the computational cost is reduced. Without relying on the wheel speed odometer, the robot synchronization localization and 3D environment modeling for multi-layer space are realized. The performance of the proposed algorithm is tested and compared in two types of underground space, and the robustness and accuracy in multi-layer space and large-scale scenarios are verified. The results show that the root mean square error of the proposed algorithm is 0.061 m, which achieves higher accuracy than other algorithms.
Originality/value
Based on the problem of large loop and low feature scale, this algorithm can better complete the map loop and self-positioning, and its root mean square error is more than double compared with other methods. The method proposed in this paper can better complete the autonomous positioning of the robot in the underground space with hierarchical feature degradation, and at the same time, an accurate 3D map can be constructed for subsequent research.
Details
Keywords
Based on the theoretical definition of the quality of economic growth as well as the availability and reliability of the given data, the purpose of this paper is to build an…
Abstract
Purpose
Based on the theoretical definition of the quality of economic growth as well as the availability and reliability of the given data, the purpose of this paper is to build an evaluation system of a regional economic growth quality on three levels: conditions, processes and results.
Design/methodology/approach
From the perspective of economic quality, this paper offers a theoretical interpretation on how the urban–rural income gap affects the quality of economic growth and takes an empirical test on the sample panel data from 30 provinces and regions through difference GMM and system GMM models.
Findings
The results show that the excessively large income gap will influence economic growth in terms of the foundation, operation and the outcome, thereby, restricting the quality of economic growth. In addition, investments in human and physical capital and improvements in terms of transport infrastructure, industrial structure and economic openness play an active role in economic growth quality, whereas government expenditure scale, financial development and the deviation of industrial structure have a negative effect.
Originality/value
There has been a substantial amount of experience and evidence on the research about the issue of China’s income distribution and the quantity of economic growth, whereas there are relatively fewer discussions about the income distribution and the quality of economic growth. This paper, based on what has been mentioned above, tries to give a theoretical interpretation and an empirical test to describe the relationship between urban–rural income gap and the quality of economic growth from the quality point of view.
Details
Keywords
Xiaojing Ma, Jie Li, Jun Zhao and Jiliang Chen
Aerodynamics plays a crucial role in enhancing the performance of race cars. Due to the low ride height, the aerodynamic components of race cars are affected by ground effects…
Abstract
Purpose
Aerodynamics plays a crucial role in enhancing the performance of race cars. Due to the low ride height, the aerodynamic components of race cars are affected by ground effects. The changes in pitch and roll attitudes during the car’s movement impact its ride height. This study aims to analyze the aerodynamic characteristics of race cars under specific pitch and roll attitudes to understand the underlying aerodynamic mechanisms. This paper focuses on the aerodynamic characteristics of racing cars under variations in body posture associated with different vehicle ride heights. It examines not only the force and pressure distribution resulting from changes in the overall vehicle posture but also the flow field behavior of both surface flow and off‑body flow. Analyzing individual components reveals the impact of the front wing on the overall aerodynamic performance and aerodynamic balance of the racing car under these posture variations.
Design/methodology/approach
The grid strategy for the computational fluid dynamics (CFD) method was established under baseline conditions and compared with the results from wind tunnel experiments. The CFD approach was further employed to investigate the aerodynamic characteristics of the racing car under varying body postures associated with different vehicle ride heights. Emphasis is placed on the overall aerodynamic performance of the vehicle and the various components’ influence on the changing trends of aerodynamic forces. By considering the surface pressure distribution of the car, the primary reasons behind the changes in aerodynamic forces for each component are investigated. In addition, the surface flow and detached flow (wake and vortex distributions) of the car were observed to gain insights into the overall flow field behavior under different attitudes.
Findings
The findings indicate that both pitch and roll attitudes result in a considerable loss of downforce on the front wing compared with other components, thereby affecting the overall downforce and aerodynamic balance of the vehicle.
Originality/value
This paper focuses on the aerodynamic characteristics of racing cars under variations in body posture associated with different vehicle ride heights. It examines not only the force and pressure distribution resulting from changes in the overall vehicle posture but also the flow field behavior of both surface flow and off-body flow. Analyzing individual components reveals the impact of the front wing on the overall aerodynamic performance and aerodynamic balance of the racing car under these posture variations.
Details
Keywords
Lu Xing, Xiaojing Yi and Ying Zhang
A series of environmental pollution issues and economic improvement go hand in hand. Since financial listed companies contribute significantly to the national economic…
Abstract
Purpose
A series of environmental pollution issues and economic improvement go hand in hand. Since financial listed companies contribute significantly to the national economic development, China has been paying increasing attention to the development of the financial industry. The purpose of this paper is to explore the relationship among the development level of the financial industry, over-investment of the listed companies and environmental pollution through a macro-level and micro-level mechanism.
Design/methodology/approach
In this study, we adopt the 2011–2017 panel data of listed companies in the manufacturing industry to study the impacts of the financial industry on environmental pollution. Meanwhile, the paper uses a mediator model, and over-investment is introduced to the econometric model as a mediator to explore whether the development of the financial industry can affect the environmental pollution through over-investment.
Findings
A U-shaped relationship between financial industry development and environmental pollution was observed through a macro-perspective; additionally, over-investment of the listed companies significantly increased environmental pollution, along with a significant mediator effect of over-investment. A significant positive correlation was observed between financial industry development and environmental pollution in the East region of China, while the correlation was negative in the Central and West regions. The mitigation effect of financial industry development on environmental pollution was more significant in the low-end manufacturing industry, compared with basic and high-end manufacturing industries.
Originality/value
Strengthening the incentives and supervision toward company managers, reducing over-investment behaviors, encouraging suitable financial industry development to reduce financial risks, improving environmental conservation laws and regulations, and implementing stringent penalty mechanisms for environmental conservation are necessary.
Details
Keywords
The aim of this paper is to argue for the values of familial caring and relationships in addition to the provision of social media technology during the COVID-19 pandemic in Hong…
Abstract
Purpose
The aim of this paper is to argue for the values of familial caring and relationships in addition to the provision of social media technology during the COVID-19 pandemic in Hong Kong.
Design/methodology/approach
The discussion of this paper has adopted an inter-disciplinary approach by integrating health care system and psychological analysis, based on cultural philosophical argument through the hermeneutic approach of classical texts and critical analysis.
Findings
The COVID-19 pandemic has exposed the dilemma between the public health measures for COVID-19 and sustaining elderly social psychological health through familial connection. From a Confucian perspective, the practice of filial piety (xiao, 孝), which demands taking care of parents, is essential for one’s moral formation, and for one’s becoming a virtuous (ren, 仁) person. The necessity of taking care of elderly parents by adult children is not something that can be explained in terms of consequentialism. Indeed, the rising trend of instrumental rationality seems to weaken rather than strengthen the sense of filial obligation. In the face of the COVID-19 pandemic which tends to separate connections between family members, the author argues that we should emphasize the values of familial caring and relationship because it enhances the elderly’s characteristic of resilience.
Originality/value
This paper shows that while social media technology has mitigated the negative effect of social distancing, such online relationships should never replace the bodily connections between the elderly and their family members from a Confucian perspective.
Details
Keywords
This study aims to explore the influencing factors on college students’ behaviours of spreading Internet public opinion on emergencies in colleges and universities. This study…
Abstract
Purpose
This study aims to explore the influencing factors on college students’ behaviours of spreading Internet public opinion on emergencies in colleges and universities. This study provides a reference for these institutions to cope with and reduce the influence of Internet public opinion on emergencies and maintain their normal teaching order.
Design/methodology/approach
In this study, a research model by using motivation theory and design a questionnaire on the basis of relevant literature are constructed. This paper surveys college students and collects a total of 317 valid questionnaires. On the basis of the reliability and validity of the questionnaire, this study verifies the proposed model by using Smart PLS.
Findings
The results show that social motivation and information source preference have significant positive influences on college students’ willingness to spread Internet public opinion on emergencies in colleges and universities. Moreover, information source preference has a significant moderating effect on the relationship between social motivation and dissemination willingness. If college students’ information source preference is high, then the moderating effect is significant. The extent of college students’ interaction and involvement has a significantly positive influence on their trust in the dissemination platform for Internet public opinion on emergencies in colleges and universities. Egoism has a significantly positive influence on the social motivation of college students to spread Internet public opinion on emergencies in colleges and universities. Involvement degree has a significant moderating effect on the relationship between social motivation and trust. If college students’ involvement degree is low, then the moderating effect is significant. Thus, when the involvement of college students in Internet public opinion on emergencies in colleges and universities is low, the influence of social motivation on trust is great.
Originality/value
This study increases the influencing factors in the literature on Internet public opinion, enriches the research theory of Internet public opinion on emergencies in colleges and universities and expands the application scope of the theory of social motivation. The conclusion provides guidance for colleges and students to govern Internet public opinion on emergencies and improve the ability of these institutions in dealing with Internet public opinion on emergencies.
Details
Keywords
This paper aims to explore the impact of domestic market fragmentation on the innovation performance of enterprises and its mechanism from the perspective of market segmentation…
Abstract
Purpose
This paper aims to explore the impact of domestic market fragmentation on the innovation performance of enterprises and its mechanism from the perspective of market segmentation, a government behavior with Chinese characteristics.
Design/methodology/approach
In order to verify the theoretical hypothesis proposed in the previous article, that is, whether domestic market fragmentation can effectively improve the innovation performance of enterprises, this paper bases on the data of listed companies from 2010 to 2016, empirically testing the theoretical hypothesis by constructing a measurement model.
Findings
Domestic market fragmentation has a significant inhibitory effect on enterprise innovation performance. Domestic market fragmentation has heterogeneous effects on innovation performance of enterprises and regions. It is undeniable that domestic market fragmentation does have a certain support effect on state-owned enterprises but the support effect is achieved by distorting regional resource allocation and creating an unfair market environment.
Originality/value
Firstly, this paper explores the impact mechanism of domestic market fragmentation on corporate innovation performance from the perspective of market segmentation, a government behavior with Chinese characteristics, so as to expand and enrich the relevant research on enterprise innovation. Secondly, from the perspective of corporate innovation performance, this paper provides new evidence for the “curse effect” of domestic market fragmentation. Thirdly, this paper tries to shake the domestic market fragmentation support theory from the perspective of distortion effect brought by the “hand of support” of domestic market fragmentation.