Multi-scale bio-inspired place recognition

This paper presents a novel place recognition algorithm inspired by the recent discovery of overlapping and multi-scale spatial maps in the rodent brain. We mimic this hierarchical framework by training arrays of Support Vector Machines to recognize places at multiple spatial scales. Place match hypotheses are then cross-validated across all spatial scales, a process which combines the spatial specificity of the finest spatial map with the consensus provided by broader mapping scales. Experiments on three real-world datasets including a large robotics benchmark demonstrate that mapping over multiple scales uniformly improves place recognition performance over a single scale approach without sacrificing localization accuracy. We present analysis that illustrates how matching over multiple scales leads to better place recognition performance and discuss several promising areas for future investigation.

Vision based guidance for robot navigation in agriculture

This paper describes a novel vision based texture tracking method to guide autonomous vehicles in agricultural fields where the crop rows are challenging to detect. Existing methods require sufficient visual difference between the crop and soil for segmentation, or explicit knowledge of the structure of the crop rows. This method works by extracting and tracking the direction and lateral offset of the dominant parallel texture in a simulated overhead view of the scene and hence abstracts away crop-specific details such as colour, spacing and periodicity. The results demonstrate that the method is able to track crop rows across fields with extremely varied appearance during day and night. We demonstrate this method can autonomously guide a robot along the crop rows.

Long-term exploration and tours for energy constrained robots with online proprioceptive traversability estimation

This paper is concerned with how a localised and energy-constrained robot can maximise its time in the field by taking paths and tours that minimise its energy expenditure. A significant component of a robot's energy is expended on mobility and is a function of terrain traversability. We estimate traversability online from data sensed by the robot as it moves, and use this to generate maps, explore and ultimately converge on minimum energy tours of the environment. We provide results of detailed simulations and parameter studies that show the efficacy of this approach for a robot moving over terrain with unknown traversability as well as a number of a priori unknown hard obstacles.

Empirical modelling of rolling shutter effect

We propose and evaluate a novel methodology to identify the rolling shutter parameters of a real camera. We also present a model for the geometric distortion introduced when a moving camera with a rolling shutter views a scene. Unlike previous work this model allows for arbitrary camera motion, including accelerations, is exact rather than a linearization and allows for arbitrary camera projection models, for example fisheye or panoramic. We show the significance of the errors introduced by a rolling shutter for typical robot vision problems such as structure from motion, visual odometry and pose estimation.

Lighting invariant urban street classification

In this paper we propose the hybrid use of illuminant invariant and RGB images to perform image classification of urban scenes despite challenging variation in lighting conditions. Coping with lighting change (and the shadows thereby invoked) is a non-negotiable requirement for long term autonomy using vision. One aspect of this is the ability to reliably classify scene components in the presence of marked and often sudden changes in lighting. This is the focus of this paper. Posed with the task of classifying all parts in a scene from a full colour image, we propose that lighting invariant transforms can reduce the variability of the scene, resulting in a more reliable classification. We leverage the ideas of “data transfer” for classification, beginning with full colour images for obtaining candidate scene-level matches using global image descriptors. This is commonly followed by superpixellevel matching with local features. However, we show that if the RGB images are subjected to an illuminant invariant transform before computing the superpixel-level features, classification is significantly more robust to scene illumination effects. The approach is evaluated using three datasets. The first being our own dataset and the second being the KITTI dataset using manually generated ground truth for quantitative analysis. We qualitatively evaluate the method on a third custom dataset over a 750m trajectory.

Simultaneous underwater visibility assessment, enhancement and improved stereo

Vision-based underwater navigation and obstacle avoidance demands robust computer vision algorithms, particularly for operation in turbid water with reduced visibility. This paper describes a novel method for the simultaneous underwater image quality assessment, visibility enhancement and disparity computation to increase stereo range resolution under dynamic, natural lighting and turbid conditions. The technique estimates the visibility properties from a sparse 3D map of the original degraded image using a physical underwater light attenuation model. Firstly, an iterated distance-adaptive image contrast enhancement enables a dense disparity computation and visibility estimation. Secondly, using a light attenuation model for ocean water, a color corrected stereo underwater image is obtained along with a visibility distance estimate. Experimental results in shallow, naturally lit, high-turbidity coastal environments show the proposed technique improves range estimation over the original images as well as image quality and color for habitat classification. Furthermore, the recursiveness and robustness of the technique allows implementation onboard an Autonomous Underwater Vehicle for improving navigation and obstacle avoidance performance.

Analyzing the impact of learning inputs on near-to-far terrain traversability estimation

With the increasing need to adapt to new environments, data-driven approaches have been developed to estimate terrain traversability by learning the rover’s response on the terrain based on experience. Multiple learning inputs are often used to adequately describe the various aspects of terrain traversability. In a complex learning framework, it can be difficult to identify the relevance of each learning input to the resulting estimate. This paper addresses the suitability of each learning input by systematically analyzing the impact of each input on the estimate. Sensitivity Analysis (SA) methods provide a means to measure the contribution of each learning input to the estimate variability. Using a variance-based SA method, we characterize how the prediction changes as one or more of the input changes, and also quantify the prediction uncertainty as attributed from each of the inputs in the framework of dependent inputs. We propose an approach built on Analysis of Variance (ANOVA) decomposition to examine the prediction made in a near-to-far learning framework based on multi-task GP regression. We demonstrate the approach by analyzing the impact of driving speed and terrain geometry on the prediction of the rover’s attitude and chassis configuration in a Marsanalogue terrain using our prototype rover Mawson.

Advancing practice in critical care : A model of knowledge integration: A Singaporean context

It could be argued that advancing practice in critical care has been superseded by the advanced practice agenda. Some would suggest that advancing practice is focused on the core attributes of an individuals practice progressing onto advanced practice status. However, advancing practice is more of a process than identifiable skills and as such is often negated when viewing the development of practitioners to the advanced practice level. For example practice development initiatives can be seen as advancing practice for the masses which ensures that practitioners are following the same level of practice. The question here is; are they developing individually. To discuss the potential development of a conceptual model of knowledge integration pertinent to critical care nursing practice. In an attempt to explore the development of leading edge critical care thinking and practice, a new model for advancing practice in critical care is proposed. This paper suggests that reflection may not be the best model for advancing practice unless the individual practitioner has a sound knowledge base both theoretically and experientially. Drawing on the contemporary literature and recent doctoral research, the knowledge integration model presented here uses multiple learning strategies that are focused in practise to develop practice, for example the use of work-based learning and clinical supervision. Ongoing knowledge acquisition and its relationship with previously held theory and experience will enable individual practitioners to advance their own practice as well as being a resource for others.

Open educational resources: Enhancing education provision and practice

Open educational resources (OERs), a disruptive technology, made their appearance in early 2002 as a promising tool for enhancing the quality of and access to education generally and higher education in particular. OERs were also perceived to have the potential to reduce costs by reusing learning materials. This brief draws on a study that reviewed the uptake of OERs and related activities in six institutions in Hong Kong, China; India; Malaysia; Pakistan; and Thailand.

Keeping up with the neighbours : China's soft power ambitions

Over the past century numerous waves of transnational media have washed across East Asia with cycles emanating from various centers of cultural production, such as Tokyo, Hong Kong, and Seoul. Most recently the People’s Republic of China (PRC) has begun to exert growing influence over the production and flow of screen media, a phenomenon tied to the increasing size and power of its overall economy. The country’s rising status achieved truly global recognition during the 2008 Beijing Olympics. In the seven years leading up to the event, the Chinese economy tripled in size, expanding from $1.3 trillion to almost $4 trillion, a figure that made it the world’s third largest economy, slightly behind Japan, but decisively ahead of its European counterparts, Germany, France, and the United Kingdom. The scale and speed of this transformation are stunning. Just as momentous are the changes in its film, television, and digital media markets, which now figure prominently in the calculations of producers throughout East Asia.

Preparing general technology teachers in China for new roles and responsibilities

This paper discusses the conceptualization, implementation and initial findings of a professional learning program (PLP) which used LEGO® robotics as one of the tools for teaching general technology (GT)in China’s secondary schools. The program encouraged teachers to design learning environments that can be realistic, authentic, engaging and fun. 100 general technology teachers from high schools in 30 provinces of China participated. The program aimed to transform teacher classroom practice, change their beliefs and attitudes, allow teachers to reflect deeply on what they do and in turn to provide their students with meaningful learning. Preliminary findings indicate that these teachers had a huge capacity for change. They were open-minded and absorbed new ways of learning and teaching. They became designers who developed innovative models of learning which incorporated learning processes that effectively used LEGO® robotics as one of the more creative tools for teaching GT.

An expert system for the strategic planning of construction projects

This paper describes the instigation and development of an expert system to aid in the strategic planning of construction projects. The paper consists of four parts - the origin of the project, the development of the concepts needed for the proposed system, the building of the system itself, and assessment of its performance. The origin of the project is outlined starting with the Japanese commitment to 5th generation computing together with the increasing local reaction to theory based prescriptive research in the field. The subsequent development of activities via the Alvey Commission and the RICS in conjunction with Salford University are traced culminating in the proposal and execution of the first major expert system to be built for the UK construction industry, subsequently recognised as one of the most successful of the expert system projects commissioned under the Alvey programme

Introduction: Mapping the Contours of East Asian Commercial Law for the Asian Century

The centre of economic gravity in the new century is shifting to the East. Since 200 1, according to the International Monetary Fund (IMF), Asia's contribution to world economic growth has matched that of the United States and Europe combined, and, since 2006, has even exceeded it (IMF, 20 I I; Neumann and Arora, 20 II ). This surge is easy to explain: China has emerged as a global super-power; Japan remains the third-largest world economy, despite only recently emerging from over twenty years of economic stagnation (The Age, 2013); South Korea and the ' tiger ' economies of Taiwan, Hong Kong and Singapore have achieved high-level economic development through capital investment and technological innovation; and Indonesia, Thailand, the Philippines and Malaysia have supplied riches in labour and resources to the regional economy (Macintyre and Naughton, 2005, p. 78). A growing middle class is lifting consumption. ‘Billions of Asians,' writes Mahbubani (2008, p. 3), 'are marching to modernity.’ This book examines scholarly interpretations for the role commercial law has played in East Asia's economic rise. At first blush, this might seem a daunting task. After all, as some theorists have argued, the East Asian experience is largely neglected in writings on Jaw generally and commercial law more broadly (Wolff, 20 12). This is because law, as a discipline, was largely forged in the prior European and American centuries; these 'Anglo-American moorings' ill-serve legal analysis in the new Asian Century (Cossman, 1997, p. 539).

Creative Industries come to China (MATE)

This paper introduces the special issue “China: Internationalizing the Creative Industries”, describing the Australian Research Council funded “MATE” project which provides the conceptual background for the questions the issue explores. The MATE project began with the expectation that as China evolves from its status as a developing country with an emphasis on primary industries and manufacturing, to a mature, market-driven economy benefiting from high levels of international investment, it will become more actively engaged with the global “knowledge economy” and “information society”. In this context, developments in the “creative industries”, which are playing such an important role in developed economies, might reasonably be expected in China. Although China continues to be characterised by strong central-policy settings, as the domestic consumer market matures there is greater scope for consumer-led creative business development. The “MATE” project aimed to capture some of these changes as they began to gain momentum across a range of services: Media, Advertising, Tourism and Education. This special issue continues this theme with papers that explore the theoretical challenges, economic questions and implications, and practical instantiations of creative industries growth in China. All papers contained in this special issue have been peer-reviewed.