Richard M. Crowder

A Conceptual Framework for Serious Games

A considerable number of serious games have been developed over the last ten years, with varying degrees of success. Due to a lack of clear standards and guidelines for game developers, it is difficult to justify claims that a specific game meets the learner’s requirements and/or expectations. This paper defines a conceptual model for serious games that will contribute to their design and the measurement of achievement in meeting their learning outcomes.

Validation of Serious Games Attributes Using the Technology Acceptance Model

The paper introduces a conceptual model for the design of serious games and uses the Technology Acceptance Model (TAM) for its validation. A specially developed game introduced international students to public transport in Southampton. After completing the game, participants completed a short questionnaire and the data was analyzed using structural equation modeling (SEM). The results identified the attributes and combinations of attributes that led the learner to accept and to use the serious game for learning. These findings are relevant in helping game designers and educational practitioners design serious games for effective learning.

The Development of an Agent-Based Modeling Framework for Simulating Engineering Team Work

Team working is becoming increasingly important in modern organizations due to its beneficial outcomes. A teams performance levels are determined by complex interactions between the attributes of its individual members, the communication and dynamics between members, the working environment, and the teams work tasks. As organizations evolve, so too does the nature of team working. During the past two decades, product development in engineering organizations has increasingly been undertaken by multidisciplinary integrated product teams. Such increasing complexity means that the nature of research methods for studying teams must also evolve. Accordingly, this paper proposes an agent-based modeling approach for simulating team working within an engineering environment, informed by research conducted in two engineering organizations. The model includes a number of variables at an individual level (competency, motivation, availability, response rate), team level (communication, shared mental models, trust), and task level (difficulty, workflow), which jointly determine team performance (quality, time to complete the task, time spent working on the task). In addition to describing the models development, the paper also reports the results of various simulation runs that were conducted in response to realistic team working scenarios, together with its validation. Finally, the paper discusses the models practical applications as a tool for facilitating organizational decision making with respect to optimizing team working.

An Agent Based Approach to Finding Expertise

In many organisations people need to locate colleagues with knowledge and information to resolve a problem. Computer based systems that assist users with finding such expertise are increasingly important to organizations and scientific communities. In this paper we discuss the development of an agent based expertise finder (EF) suitable for use within an academic research environment. A key feature of this work is that the EF returns both recommended contacts and supporting documentation. The EF bases its results on information held within the organisation, for example publications, human resource records and not on CVs or user maintained records. The recommendations are presented to the user with due regard to the social context, and are supported by the documents used to make the recommendation. The technology used allows the development of distributed, interchangeable agents that use real time data to find expertise. It is our intention to use this approach within manufacturing and other knowledge intensive organisations.

Adaptive neurofuzzy control of a robotic gripper with on-line machine learning

Abstract Pre-programming complex robotic systems to operate in unstructured environments is extremely difficult because of the programmer’s inability to predict future operating conditions in the face of unforeseen environmental conditions, mechanical wear of parts, etc. The solution to this problem is for the robot controller to learn on-line about its own capabilities and limitations when interacting with its environment. At the present state of technology, this poses a challenge to existing machine learning methods. We study this problem using a simple two-fingered gripper which learns to grasp an object with appropriate force, without slip while minimising chances of damage to the object. Three machine learning methods are used to produce a neurofuzzy controller for the gripper. These are off-line supervised neurofuzzy learning and two on-line methods, namely unsupervised reinforcement learning and an unsupervised/supervised hybrid. With the two on-line methods, we demonstrate that the controller can learn through interaction with its environment to overcome simulated failure of its sensors. Further, the hybrid is shown to out perform reinforcement learning alone in terms of faster adaptation to the changing circumstances of sensor failure. The hybrid learning scheme allows us to make best use of such pre-labeled datasets as might exist and to remember effectively good control actions discovered by reinforcement learning.

GRASPING AND CONTROL ISSUES IN ADAPTIVE END EFFECTORS

Research into robotic grasping and manipulation has led to the development of a large number of tendon based end effectors. Many are, however, developed as a research tool, which are limited in application to the laboratory environment. The main reason being that the designs requiring a large number of actuators to be controlled. Due to the space and safety requirements, very few have been developed and commissioned for industrial applications. This paper presents design of a rigid link finger operated by a minimum number of actuators, which may be suitable for a number of adaptive end effectors. The adaptive nature built into the end effector (due to limited number of actuators) presents considerable problems in grasping and control. The paper discusses the issues associated with such designs. The research can be applicable to any adaptive end effectors that are controlled by limited number of actuators and evaluates their suitability in industrial environments.

Optimal object grasp using tactile sensors and fuzzy logic

Optimal control of fingertip force during grasping operation by multifingered robotic end effectors is an important consideration. Determination of optimal fingertip force is, however, very complicated due to the involvement of a number of contact parameters at the finger-object interface including the mass of the object and the frictional properties of the contact surfaces. Modelling of various contact parameters is computationally overloading, which may not be tenable in practical situations where objects of different mass and material are available. Also for an unknown and unstructured environment, these properties may not be known in advance. This paper presents a controller based on fuzzy logic which is capable of performing optimal grasp of objects without knowing their mass and frictional properties. The controller also accounts for stability and dynamic aspects of the grasp. The experimental results of the implementation are presented.

Integration of manufacturing information using open hypermedia

This paper discusses some of the benefits from using an open hypermedia system to deliver the diverse range of information found within the manufacturing environment. The open hypermedia approach to information management and delivery allows a single multimedia resource base to be used for a range of applications, and permits a user to have controlled access to the required information, in an easily accessible and structured manner. Our approach is illustrated by the presentation of a case study of a system delivering maintenance and process information on the factory floor, within a fully automated manufacturing plant. The development of the application is discussed, together with guide lines for the authoring and delivery of information. It is our contention that with the integration of open hypermedia, and knowledge based systems together with network technology giving access to external databases, the concept of industrial strength hypermedia can be realised.

An anthropomorphic robotic end effector

Research into the development of artificial mechanical hands for prosthetic applications has been conducted over many hundreds of years. Dexterous mechanical hands are now being applied to advanced robotic applications, including tele-operated manipulators. The successful application of dexterous mechanical hands depends on the development of suitable mechanisms, actuators and control strategies. Recently the requirement arose for a manipulator to fit and operate within a standard glove box glove.. The design and development of a fully anthropomorphic dexterous end effector for the manipulator is discussed in this paper. To arrive at the final design a study of the operation of the human hand was undertaken. The end effector consists of four mechanically adaptive fingers and a thumb. The mechanism developed for the fingers will simulate the curl of the human finger. The complete finger mechanism requires only one actuator to produce fully the required motion, leading to a compact design for the end effector. To gain y=the full operational advantage of the dexterous hand a control strategy has been developed based on global sensing and a hierarchical control strategy. The results of handelling trials are presented.

Integrating Case-Based Reasoning and Hypermedia Documentation: An Application for the Diagnosis of a Welding Robot at Odense Steel Shipyard

Reliable and effective maintenance support is a vital consideration for the management within todays manufacturing environment. This paper discusses the development a maintenance system for the world largest robot welding facility. The developed system combines a case-based reasoning approach for diagnosis with context information, as electronic on-line manuals, linked using open hypermedia technology. The work discussed in this paper delivers not only a maintenance system for the robot stations under consideration, but also a design framework for developing maintenance systems for other similar applications.