Quoc Do

Requirements for a Metamodel to Facilitate Knowledge Sharing between Project Stakeholders

The successful realization of the goal of Model-Based Systems Engineering (MBSE) practice, to contain all project information in models, is predicated on the ability of the system model to represent the information needs of a broad range of stakeholders such as the owners, acquirers, suppliers, maintainers, and users. The paper opens by discussing the interface between the acquirer and supplier within the pre-contract competitive Australian defence context. From this and earlier work, the need for the model of the system of interest to be built upon a comprehensive knowledge representation that can support the creation and integration of multiple stakeholder specific models is derived. Elicitation of further requirements from both stakeholder workshops and from functional analysis follows.

A fast visual search and recognition mechanism for real-time robotics applications

Robot navigation relies on a robust and real-time visual perception system to understand the surrounding environment This paper describes a fast visual landmark search and recognition mechanism for real-time robotics applications The mechanism models two stages of visual perception named preattentive and attentive stages The pre-attentive stage provides a global guided search by identifying regions of interest, which is followed by the attentive stage for landmark recognition The results show the mechanism validity and applicability to autonomous robot applications.

An Investigation of MBSE Practices across the Contractual Boundary

Abstract One of the key impediments to the expansion of Model-Based Systems Engineering (MBSE) practice across the lifecycle, particularly in competitive tendering environments, is the continued reliance on documents to define the contractual interface between the acquirer and the supplier. This paper describes the collaborative research project between the University of South Australia (UniSA), the Defence Systems Innovation Centre (DSIC), and the Defence Science Technology Organisation (DSTO) that is investigating the capability of the DSTO Whole-of- System Analytical Framework (WSAF) to supplant contractual documents within the tender process and the degree to which the model passed from acquirer through the contractual interface can be used by the supplier as the basis of their tender response and subsequent systems development. The paper opens with background material and then describes the “learning-by-doing” approach that is being employed. This is followed by a description of methods and tools used to support the design of the tender response and the capture of the design rationale in the same MBSE environment used to capture the project definition. The paper concludes with a discussion section that surfaces the key issues and challenges inherent in utilising this MBSE approach across the contractual boundary and ways that the selected approach could address these.

Application of neural processing paradigm in visual landmark recognition and autonomous robot navigation

This article addresses the issue of visual landmark recognition in autonomous robot navigation along known routes, by intuitively exploiting the functions of the human visual system and its navigational ability. A feedforward–feedbackward architecture has been developed for recognising visual landmarks in real time. It integrates the theoretical concepts from the pre-attentive and attentive stages in the human visual system, the selective attention adaptive resonance theory neural network and its derivatives, and computational approaches towards object recognition in computer vision. The architecture mimics the pre-attentive and attentive stages in the context of object recognition, embedding neural network processing paradigm into a computational template-matching approach in computer vision. The real-time landmark recognition capability is achieved by mimicking the pre-attentive stage, where it models a selective attention mechanism for optimal computational resource allocation, focusing only on the regions of interest to address the computational restrictive nature of current computer processing power. Similarly, the recognition of visual landmarks in both clean and cluttered backgrounds is implemented in the attentive stage by developing a memory feedback modulation (MFM) mechanism that enables knowledge from the memory to interact and enhance the efficiency of earlier stages in the architecture. Furthermore, it also incorporates both top-down and bottom-up facilitatory and inhibition pathways between the memory and the earlier stages to enable the architecture to recognise a 2D landmark, which is partially occluded by adjacent features in the surroundings. The results show that the architecture is able to recognise objects in cluttered backgrounds using real-images in both indoor and outdoor scenes. Furthermore, the architecture application in autonomous robot navigation has been demonstrated through a number of real-time trials in both indoor and outdoor environments.

A Visual Landmark Recognition System for Autonomous Robot Navigation

This paper presents a vision system for autonomously guiding a robot along a known route using a single CCD camera. The prominent feature of the system is the real-time recognition of shape-based visual landmarks in cluttered backgrounds, using a memory feedback modulation (MFM) mechanism, which provides a means for the knowledge from the memory to interact and enhance the earlier stages in the system. Its feasibility in autonomous robot navigation is demonstrated in both indoor and outdoor experiments using a vision-based navigating vehicle.

A vision system for partially occluded landmark recognition

This paper describes a vision system for extracting and recognising partially occluded 2D visual landmarks. The system is developed based on the traditional template matching approach and a memory feedback modulation (MFM) mechanism. It identifies the obscured portions and selectively enhances non-occluded areas of the landmark, while simultaneously suppressing background clutters of the bottom-up edge processed input images. The architecture has been tested with a large number of real images with varying levels of landmark concealment and further evaluated using a vision-based navigating robot in the laboratory environment.

Selective Attention Adaptive Resonance Theory and Object Recognition

The concept of selective attention as a useful mechanism in Artificial Neural Network models of visual pattern recognition has received a lot of attention recently, particularly since it was found that such a mechanism influences the receptive field profiles of cells in the primate visual pathway by filtering out non-relevant stimuli [28, 29]. It is believed that the massive feedback pathways in the brain play a role in attentional mechanisms by biasing the competition amongst the neural populations that are activated by different parts of a scene [8, 14, 15].

A Sandpit for Systems Engineering and Systems Integration education and research

This paper describes the Microcosm programme established by the Defence Science and Technology Organisation and University of South Australia that seeks to provide a facility to explore systems integration issues, accelerate the formation of systems engineering competencies, and conduct research into model-based systems engineering. Firstly, the paper outlines the design drivers and long term goals of the programme. This is followed by a description of the Stage One implementation that covers the high-level architecture, system design, and implementation. The utility of the Microcosm Sandpit has been successfully demonstrated through a real-time intruder detection and engagement scenario using real and simulated autonomous robot vehicles.

Special issue recent advances in soft computing: Theories and applications

Soft Computing is an interdisciplinary area that encompasses a variety of computing paradigms. Examples of some popular soft computing paradigms include fuzzy computing, neural computing, evolutionary computing, and probabilistic computing. Soft computing paradigms, in general, aim to produce computing systems/machines that exhibit some useful properties, e.g. making inference with vague and/or ambiguous information, learning from noisy and/or incomplete data, adapting to changing environments, and reasoning with uncertainties. These properties are important for the systems/machines to be useful in assisting humans in our daily activities. Indeed, soft computing paradigms have been demonstrated to be capable of tackling a wide range of problems, e.g. optimization, decision making, information processing, pattern recognition, and intelligent data analysis. A number of papers pertaining to some recent advances in theoretical development and practical application of different soft computing paradigms are highlighted in this special issue.

A Biological Inspired Visual Landmark Recognition Architecture

An architecture that is inspired by a human’s capability to autonomously navigate an environment based on visual landmark recognition is presented. It consists of pre-attentive and attentive stages that allow visual landmarks to be recognized reliably under both clean and cluttered backgrounds. The pre-attentive stage provides an efficient means for real-time image processing by selectively focusing on regions of interest within input images. The attentive stage has a memory feedback modulation mechanism that allows visual knowledge of landmarks in the memory to interact and guide different stages in the architecture for efficient feature extraction and landmark recognition. The results show that the architecture is able to reliably recognise both occluded and non-occluded visual landmarks in complex backgrounds.