Search results

Compared with traditional methods relying on manual teaching or system modeling, data-driven learning methods, such as deep reinforcement learning and imitation learning, show more promising potential to cope with the challenges brought by increasingly complex tasks and environments, which have become the hot research topic in the field of robot skill learning. However, the contradiction between the difficulty of collecting robot–environment interaction data and the low data efficiency causes all these methods to face a serious data dilemma, which has become one of the key issues restricting their development. Therefore, this paper aims to comprehensively sort out and analyze the cause and solutions for the data dilemma in robot skill learning.

First, this review analyzes the causes of the data dilemma based on the classification and comparison of data-driven methods for robot skill learning; Then, the existing methods used to solve the data dilemma are introduced in detail. Finally, this review discusses the remaining open challenges and promising research topics for solving the data dilemma in the future.

This review shows that simulation–reality combination, state representation learning and knowledge sharing are crucial for overcoming the data dilemma of robot skill learning.

To the best of the authors’ knowledge, there are no surveys that systematically and comprehensively sort out and analyze the data dilemma in robot skill learning in the existing literature. It is hoped that this review can be helpful to better address the data dilemma in robot skill learning in the future.

Because of the advantages of high deposition efficiency and low manufacturing cost compared with other additive technologies, robotic wire arc additive manufacturing (WAAM) technology has been widely applied for fabricating medium- to large-scale metallic components. The additive manufacturing (AM) method is a relatively complex process, which involves the workpiece modeling, conversion of the model file, slicing, path planning and so on. Then the structure is formed by the accumulated weld bead. However, the poor forming accuracy of WAAM usually leads to severe dimensional deviation between the as-built and the predesigned structures. This paper aims to propose a visual sensing technology and deep learning–assisted WAAM method for fabricating metallic structure, to simplify the complex WAAM process and improve the forming accuracy.

Instead of slicing of the workpiece modeling and generating all the welding torch paths in advance of the fabricating process, this method is carried out by adding the feature point regression branch into the Yolov5 algorithm, to detect the feature point from the images of the as-built structure. The coordinates of the feature points of each deposition layer can be calculated automatically. Then the welding torch trajectory for the next deposition layer is generated based on the position of feature point.

The mean average precision score of modified YOLOv5 detector is 99.5%. Two types of overhanging structures have been fabricated by the proposed method. The center contour error between the actual and theoretical is 0.56 and 0.27 mm in width direction, and 0.43 and 0.23 mm in height direction, respectively.

The fabrication of circular overhanging structures without using the complicate slicing strategy, turning table or other extra support verified the possibility of the robotic WAAM system with deep learning technology.

Because of the key role of joint torque in industrial robots (IRs) motion performance control and energy consumption calculation and efficiency optimization, the purpose of this paper is to propose a deep learning torque prediction method based on long short-term memory (LSTM) recurrent neural networks optimized by particle swarm optimization (PSO), which can accurately predict the the joint torque.

The proposed model optimized the LSTM with PSO algorithm to accurately predict the IRs joint torque. The authors design an excitation trajectory for ABB 1600–10/145 experimental robot and collect its relative dynamic data. The LSTM model was trained with the experimental data, and PSO was used to find optimal number of LSTM nodes and learning rate, then a torque prediction model is established based on PSO-LSTM deep learning method. The novel model is used to predict the robot’s six joint torque and the root mean error squares of the predicted data together with least squares (LS) method were comparably studied.

The predicted joint torque value by PSO-LSTM deep learning approach is highly overlapped with those from real experiment robot, and the error is quite small. The average square error between the predicted joint torque data and experiment data is 2.31 N.m smaller than that with the LS method. The accuracy of the novel PSO-LSTM learning method for joint torque prediction of IR is proved.

PSO and LSTM model are deeply integrated for the first time to predict the joint torque of IR and the prediction accuracy is verified.

This theoretical paper introduces a conceptual framework for Personal Cultural Heritage Management (PCHM), derived from prior research on migrants' information practices. It elaborates on the literature background and the development of the PCHM framework, highlighting the role of personal information management (PIM) and personal collections in the creation, access and utilization of cultural heritage information.

The study describes and explains the construction of the PCHM framework as a structured and self-motivated approach to personal heritage and identity learning.

Following the theoretical background and assumptions, along with the presentation of the key building blocks, the paper describes the key components of the framework, outlines their definitions and provides examples.

Theoretically, PCHM extends the current literature by encapsulating processes and actions employed by individuals to manage personal collections for cultural identity purposes, thereby underscoring the critical role personal collections play in both preserving and communicating cultural heritage.

PCHM can guide the development of support systems and policies to enhance cultural continuity and integration, thus empowering individuals to navigate their cultural identities confidently.

The PCHM framework creates a unique intersection between PIM and cultural heritage, providing a new perspective for understanding the dynamic evolution and formation of cultural identity among migrants.

The existing literature on business incubators has rarely addressed network establishments thus far. The purpose of this study is to shed light on the process of network formation and its structure during the incubator creation process. The study focuses on establishing a network involving three key types of partners in the initial phase of setting up four agribusiness incubators. These partners come from universities, research organisations and private companies operating in a developing context.

This study uses social network theory, using a combination of qualitative and network survey approaches in Kenya, Uganda and Zambia. The qualitative data were used to investigate partnership formation, while the network survey was conducted to map the organisational network of business incubator partners. Constructs of social network theory, including relational content, relational form, centrality of actors and instrumentality, were qualitatively measured in this study.

The findings indicate that partners rely on previous informal relationships, which are formalised during the creation of business incubator partnerships. In the African context, once these relationships are formalised, they become part of what is referred to as business networks, irrespective of the nature of the relationship content. Personal networks serve as precursors to establishing organisational networks that cater to incubated firms. Incubator partners facilitate the networking process and enhance the formation of new connections in the early-stage partnership-based tripartite business incubators. They act as brokers, bridging structural holes by coordinating actors across the hole and linking disconnected nodes by activating their sub-networks. The results reveal that the partners' level of embeddedness in various organisational settings increases the diversity of contacts integrated into the incubator networks. In terms of relational content, partners tend to perceive the ties as business-oriented, even though the content of the relationship may differ. The strength of relationships depends on their formalization and the frequency of interaction.

The findings of the study contradict the reviewed social network literature, emphasising the necessity to adapt methodological approaches based on the cultural and institutional context in which they are applied. The social network questionnaire requires modification when used in different contexts and settings. Specifically, methodologies should be adjusted in situations where actors need to be discreet concerning their various relationships. It is important to note that organisational culture does influence actors' behaviours.

This study is deemed relevant to managers and practitioners of business incubators alike. It highlights that understanding the contextual factors that influence networking practices, the type and strength of networks and the resources provided to participants are crucial elements that should be considered in future policy and intervention initiatives.

This paper addresses the identified gap in examining network formation during the establishment of business incubators. The research is significant as it provides insights into networking at the incubator level of analysis within a tripartite business incubator setup. Ultimately, this paper helps increase our understanding of networking within the context of emerging countries.