Search results

Teaching by demonstration (TbD) is a promising way for robot learning skills in human and robot collaborative hybrid manufacturing lines. Traditionally, TbD systems have only concentrated on how to enable robots to learn movement skills from humans. This paper aims to develop an extended TbD system which can also enable learning stiffness regulation strategies from humans.

Here, the authors propose an extended dynamical motor primitives (DMP) framework to achieve this goal. In addition to the advantages of the traditional ones, the authors’ framework can enable robots to simultaneously learn stiffness and the movement from human demonstrations. Additionally, Gaussian mixture model (GMM) is used to capture the features of movement and of stiffness from multiple demonstrations of the same skill. Human limb surface electromyography (sEMG) signals are estimated to obtain the reference stiffness profiles.

The authors have experimentally demonstrated the effectiveness of the proposed framework. It shows that the authors approach could allow the robot to execute tasks in a variable impedance control mode with the learned movement trajectories and stiffness profiles.

In robot skill acquisition, DMP is widely used to encode robotic behaviors. So far, however, these DMP modes do not provide the ability to properly represent and generalize stiffness profiles. The authors argue that both movement trajectories and stiffness profiles should be considered equally in robot skill learning. The authors’ approach has great potential of applications in the future hybrid manufacturing lines.

The purpose of this paper was to propose a method based on an Artificial Neural Network and a real-time vision algorithm, to learn welding skills in industrial robotics.

By using an optic camera to measure the bead geometry (width and height), the authors propose a real-time computer vision algorithm to extract training patterns and to enable an industrial robot to acquire and learn autonomously the welding skill. To test the approach, an industrial KUKA robot and a welding gas metal arc welding machine were used in a manufacturing cell.

Several data analyses are described, showing empirically that industrial robots can acquire the skill even if the specific welding parameters are unknown.

The approach considers only stringer beads. Weave bead and bead penetration are not considered.

With the proposed approach, it is possible to learn specific welding parameters despite of the material, type of robot or welding machine. This is due to the fact that the feedback system produces automatic measurements that are labelled prior to the learning process.

The main contribution is that the complex learning process is reduced into an input-process-output system, where the process part is learnt automatically without human supervision, by registering the patterns with an automatically calibrated vision system.

A neural network controller is proposed for the motion control of robot manipulators with force/torque feedback signals. This controller is trained with reinforcement learning algorithms and a model is extracted from the synaptic weights within the neural network. This model is continuously refined by the feedback signals to ensure its validity even in a stochastic and non‐stationary environment. With this model and the real‐time force/torque feedback data, the robot can acquire a fine skill for a particular assembly task for which it is trained.

To adapt the segway RMP, a dynamically balancing robot base, to build robots capable of playing soccer autonomously.

Focuses on the electro‐mechanical mechanisms required to make the Segway RMP autonomous, sensitive, and able to control a football.

Finds that turning a Segway RMP into a soccer‐playing robot requires a combined approach to the mechanics, electronics and software control.

Although software algorithms necessary for autonomous operation and infrastructure supplying logging and debugging facilities have been developed, the scenario of humans and robots playing soccer together has yet to be addressed.

Turning the model into a soccer playing robot demonstrates the technique of combining mechanics, electronics and software control.

Shows how the model as a base platform can be developed into a fully functional, autonomous, soccer‐playing robot.

The purpose of this paper is to present an improved concept of software‐based laboratory exercises, namely a Virtual Laboratory for Engineering Sciences (VLES).

The implementation of distance learning and e‐learning in engineering sciences (such as Mechanical and Electrical Engineering) is still far behind current practice in narrative disciplines (Economics, Management, etc.). This is because education in technical disciplines requires laboratory exercises, providing skill‐acquisition and hands‐on experience. In order to overcome this problem for distance‐learning developers and practitioners, a new modular and hierarchically organized approach is needed.

The concept involves simulation models to emulate system dynamics, full virtual reality to provide visualization, advanced social‐clubbing to ensure proper communication, and an AI tutor to supervise the lab work. Its modularity and hierarchical organization offer the possibility of applying the concept to practically any engineering field: a higher level provides the general framework – it considers lab workplaces as objects regardless of the technical field they come from, and provides communication and supervision – while the lower level deals with particular workplaces. An improved student's motivation is expected.

The proposed concept aims rather high, thus making the work truly challenging. With the current level of information and communication technologies, some of the required features can only be achieved with difficulty; however, the rapid growth of the relevant technologies supports the eventual practicality of the concept. This paper is not intended to present any final results, solutions, or experience. The idea is to promote the concept, identify problems, propose guidelines, and possibly open a discussion.

This chapter explores how robots can be used to design science, technology, engineering and mathematics (STEM) learning that is inclusive and engaging for adolescents with autism spectrum disorder (ASD). The importance of purposefully designed and problematic learning experiences is explored along with an examination of the role and function of meaningful discursive situations and inclusive contexts for learning. The goal of the chapter is to provide a context for readers interested in integrating the use of robots with adolescents with ASD, but it is also of use to those more broadly interested in the use of robots as learning tools. Recommendations for successful use are provided along with a discussion of how to start. This chapter is of interest to K-12 educators and others interested in the use of robots to create opportunities for students to understand the nature of doing STEM in an inclusive environment.

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.

Using the Delphi technique, this paper aims to investigate how human resource experts perceive service robots will impact leadership and human resource management in the hospitality industry.

A three-stage Delphi study with hotel industry human resource experts was conducted to identify the key trends and major challenges that will emerge in the next ten years and how leaders should deal with the challenges brought about by service robot technologies.

The results show that while service robots are anticipated to increase efficiency and productivity of hotel activities, they may also pose challenges such as high costs, skill deficits and significant changes to the organizational structure and culture of hotels. Therefore, the anticipated applications and integration of robotic technology will require leaders of the future to carefully consider the balance between the roles of service robots and human employees in the guest experience and to nurture a work environment that embraces open-mindedness and change.

This is the first type of study to examine hospitality leadership and human resource management in the context of robotized hotels. This study has taken an important step to understand the leadership role in robotized hotels from a human resource perspective and brings clarity as to how robotic technology can influence leadership in the future workplace.

Purpose: The purpose is to introduce the fundamental economic concepts that must be wrestled with the incorporation of robots, artificial intelligence and service automation (RAISA) into the travel, tourism and hospitality industries.

Design/methodology/approach: This chapter uses cost-benefit analytical framework of the incorporation of RAISA technologies into travel, tourism and hospitality industries.

Findings: The chapter elaborates on the economic fundamentals of RAISA adoption into the travel, tourism and hospitality industries. The analysis reveals that many financial and non-financial costs and benefits need to be considered when taking a decision to use RAISA technologies. Automation of tasks leads to simultaneous substitution and enhancement of human employees. Introduction of RAISA technologies results on inevitable deskilling of some and upskilling of other tourism and hospitality jobs.

Research limitations/implications: The chapter is conceptual and conclusions are limited by the views and interpretations of the authors.

Practical implications: RAISA technologies will become increasingly omnipresent in the travel, tourism and hospitality industries. That is why an understanding of the costs and benefits and many of the practical impediments to the incursion of RAISA into the workplace should be understood to make a transition from human-performed tasks to technology-performed tasks.

Social implications: Replacement of human labour will have significant social implications for the workforce and employers.

Originality/value: This is one of the few publications that discuss the economic aspects of the incorporation of RAISA technologies into travel, tourism and hospitality industries.

A wave of technological change in the first decades of the twenty-first century is prefiguring a fundamental restructuring of society. Key among the driving forces behind such change are powerful technologies with the potential to exert major transformations on a range of human activities and, crucially, to do so without direct human intervention. The technologies collectively referred to as Artificial Intelligence, or AI represent a productive lens through which to investigate two interrelated transformations: the emergence of self-driving cars and the coming shifts in education. This is in particular because AI’s versatility has led it to be directly applied (and increasingly valued) both in new automated driving technologies, and in the development of new forms of instruction. From the educational perspective, this means that the same technologies that are transforming workforce conditions are also reshaping – directly and indirectly – the approaches, objectives, and experiences of students and educational institutions. This chapter lays out how these twin transformations are likely to play out in the case of the automotive industry and the educational pathways of two occupations closely associated with it: automotive engineers and repair technicians. Two key arguments underpin this examination. First, educational programs for these two occupations, (and beyond) should be broadened to develop versatility and adaptability through tools and perspectives that allow people to move vertically within organizations and laterally across industries in the face of rapid technological change. Second, these educational programs must explicitly tackle AI and the coming technological revolution from a variety of dimensions that connect technical skills acquisition with the context on how these technologies are incorporated in society, how they are governed, and what are the various responses to them. This will allow students and professionals to navigate a rapidly changing labor landscape better while endowing them with the vocabulary to actively participate in the debates that shape its construction.