Visual sea-floor mapping from low overlap imagery using bi-objective bundle adjustment and constrained motion

In most visual mapping applications suited to Autonomous Underwater Vehicles (AUVs), stereo visual odometry (VO) is rarely utilised as a pose estimator as imagery is typically of very low framerate due to energy conservation and data storage requirements. This adversely affects the robustness of a vision-based pose estimator and its ability to generate a smooth trajectory. This paper presents a novel VO pipeline for low-overlap imagery from an AUV that utilises constrained motion and integrates magnetometer data in a bi-objective bundle adjustment stage to achieve low-drift pose estimates over large trajectories. We analyse the performance of a standard stereo VO algorithm and compare the results to the modified vo algorithm. Results are demonstrated in a virtual environment in addition to low-overlap imagery gathered from an AUV. The modified VO algorithm shows significantly improved pose accuracy and performance over trajectories of more than 300m. In addition, dense 3D meshes generated from the visual odometry pipeline are presented as a qualitative output of the solution.

Creating fashion professionals for the 21st century : a tale of pedagogical tensions and emerging challenges

The ‘Fashion Tales’ Conference identifies three fashion discourses: that of making, that of media, and that of scholarship. We propose a fourth, which provides a foundational base for the others: the discourse of fashion pedagogy. We begin with the argument that to thrive in any of these discourses, all fashion graduates require the ability to navigate the complexities of the 21st century fashion industry. Fashion graduates emerge into a professional world which demands a range of high level capabilities above and beyond those traditionally acknowledged by the discipline. Professional education in fashion must transform itself to accommodate these imperatives. In this paper, we document a tale of fashion learning, teaching and scholarship – the tale of a highly successful future-orientated boutique university-based undergraduate fashion course in Queensland, Australia. The Discipline consistently maintains the highest student satisfaction and lowest attrition of any course in the university, achieves extremely competitive student satisfaction scores when compared with other courses nationally and internationally, and reports outstanding graduate employment outcomes. The core of the article addresses how the course effectively balances five key pedagogical tensions identified from the findings of in-depth focus groups with graduating students, and interviews with teaching staff. The pedagogical tensions are: high concept/ authenticity; high disciplinarity/ interdisciplinarity; high rigour/ play; high autonomy/ scaffolding; and high individuality/ community, where community can be further divided into high challenge and high support. We discuss each of these tensions and how they are characterised within the course, using rich descriptions given by the students. We also draw upon the wider andragogical and learning futures literatures to link the tensions with what is already known about excellence in 21st century higher and further education curriculum and pedagogic practice. We ask: as the fashion industry becomes truly globalised, virtualised, and diversified, and as initial professional training for the industry becomes increasingly massified and performatised, what are the best teaching approaches to produce autonomous, professionally capable, enterprising and responsible graduates into the future? Can the pedagogical balances described in this case study be maintained in the light of these powerful external forces, and if so, how?

Email as an arena for authoring a dialogical self among gifted young adolescents : a qualitative study

This paper describes a qualitative study that investigated young adolescents’ self-constructions within the context of online (email) communication. Drawing from dialogical perspectives of self as multiply-situated and complex phenomena, the study focused on the everyday narratives of individual young adolescents interpreted as different “I” voices. With the assumption that computer mediation offers cultural relevance and empowerment to young adolescents, techniques of personal journal writing were used in combination with email as an alternative to face-to-face methods. Twelve participants aged 10 to 14 years were recruited online and by word-of-mouth with an invitation to write freely about their lives over a six month period in a participant-led email journal project. The role of the researcher was to develop a supportive voice of listener/responder that was intended to facilitate the emergence of participants’ own ‘self’ voices within an interactive space for relatively autonomous self-expression. Data as email texts were analysed using a close listening method that synchronised with the theory by revealing multi-layered patterns and shifts of voices in order to give a nuanced understanding of participants’ self and other evaluations. The paper shows that narrative methods used online and in concert with dialogical concepts have potential to heighten self-reflection and strengthen agency as a means to access rich and nuanced data from young adolescent individuals. The study’s findings contribute to a growing interest in the use of dialogical concepts to explore the ways people engage in active meaning-making while embedded in their specific social and cultural environments.

Towards persistent indoor appearance-based localization, mapping and navigation using CAT-Graph

The challenge of persistent appearance-based navigation and mapping is to develop an autonomous robotic vision system that can simultaneously localize, map and navigate over the lifetime of the robot. However, the computation time and memory requirements of current appearance-based methods typically scale not only with the size of the environment but also with the operation time of the platform; also, repeated revisits to locations will develop multiple competing representations which reduce recall performance. In this paper we present a solution to the persistent localization, mapping and global path planning problem in the context of a delivery robot in an office environment over a one-week period. Using a graphical appearance-based SLAM algorithm, CAT-Graph, we demonstrate constant time and memory loop closure detection with minimal degradation during repeated revisits to locations, along with topological path planning that improves over time without using a global metric representation. We compare the localization performance of CAT-Graph to openFABMAP, an appearance-only SLAM algorithm, and the path planning performance to occupancy-grid based metric SLAM. We discuss the limitations of the algorithm with regard to environment change over time and illustrate how the topological graph representation can be coupled with local movement behaviors for persistent autonomous robot navigation.

OpenRatSLAM : an open source brain-based SLAM system

RatSLAM is a navigation system based on the neural processes underlying navigation in the rodent brain, capable of operating with low resolution monocular image data. Seminal experiments using RatSLAM include mapping an entire suburb with a web camera and a long term robot delivery trial. This paper describes OpenRatSLAM, an open-source version of RatSLAM with bindings to the Robot Operating System framework to leverage advantages such as robot and sensor abstraction, networking, data playback, and visualization. OpenRatSLAM comprises connected ROS nodes to represent RatSLAM’s pose cells, experience map, and local view cells, as well as a fourth node that provides visual odometry estimates. The nodes are described with reference to the RatSLAM model and salient details of the ROS implementation such as topics, messages, parameters, class diagrams, sequence diagrams, and parameter tuning strategies. The performance of the system is demonstrated on three publicly available open-source datasets.

Sensing and control for a small-size helicopter

This paper details the progress to date, toward developing a small autonomous helicopter. We describe system architecture, avionics, visual state estimation, custom IMU design, aircraft modelling, as well as various linear and neuro/fuzzy control algorithms. Experimental results are presented for state estimation using fused stereo vision and IMU data, heading control, and attitude control. FAM attitude and velocity controllers have been shown to be effective in simulation.

Visualizing the evolution of knowledge management capability in construction firms

A firm, as a dynamic, evolving, and quasi-autonomous system of knowledge production and application, develops knowledge management capability (KMC) through strategic learning in order to sustain competitive advantages in a dynamic environment. Knowledge governance mechanisms and knowledge processes connect and interact with each other forming learning mechanisms, which carry out double loop learning that drives genesis and evolution of KMC to modify operating routines that effect desired performance. This paper reports a study that was carried out within a context of construction contractors, a type of project-based firms, operating within the dynamic Hong Kong construction market. A multiple-case design was used to incorporate evidence from the literature and interviews, with the help of system dynamics modeling, to visualize the evolution of KMC. The study demonstrates the feasibility to visualize how a firm's KMC matches its operating environment over time. The findings imply that knowledge management (KM) applications can be better planned and controlled through evaluation of KM performance over time from a capability perspective.

Context-aware device self-configuration using self-organizing maps

Modern mobile computing devices are versatile, but bring the burden of constant settings adjustment according to the current conditions of the environment. While until today, this task has to be accomplished by the human user, the variety of sensors usually deployed in such a handset provides enough data for autonomous self-configuration by a learning, adaptive system. However, this data is not fully available at certain points in time, or can contain false values. Handling potentially incomplete sensor data to detect context changes without a semantic layer represents a scientific challenge which we address with our approach. A novel machine learning technique is presented - the Missing-Values-SOM - which solves this problem by predicting setting adjustments based on context information. Our method is centered around a self-organizing map, extending it to provide a means of handling missing values. We demonstrate the performance of our approach on mobile context snapshots, as well as on classical machine learning datasets.

Long summer days : grounded learning of words for the uneven cycles of real world events

Time and space are fundamental to human language and embodied cognition. In our early work we investigated how Lingodroids, robots with the ability to build their own maps, could evolve their own geopersonal spatial language. In subsequent studies we extended the framework developed for learning spatial concepts and words to learning temporal intervals. This paper considers a new aspect of time, the naming of concepts like morning, afternoon, dawn, and dusk, which are events that are part of day-night cycles, but are not defined by specific time points on a clock. Grounding of such terms refers to events and features of the diurnal cycle, such as light levels. We studied event-based time in which robots experienced day-night cycles that varied with the seasons throughout a year. Then we used meet-at tasks to demonstrate that the words learned were grounded, where the times to meet were morning and afternoon, rather than specific clock times. The studies show how words and concepts for a novel aspect of cyclic time can be grounded through experience with events rather than by times as measured by clocks or calendars

Primary classroom teachers' use of social and emotional wellbeing programs and the factors influencing program use

There has been a rapid escalation in the development and evaluation of social and emotional well-being (SEW) programs in primary schools over the last few decades. Despite the plethora of programs available, primary teachers’ use of SEW programs is not well documented in Australian schools, with even less consideration of the factors influencing program use. A cross-sectional survey was undertaken with primary classroom teachers across twelve schools in the Brisbane and Sunshine Coast Education Districts in Queensland, Australia, during 2005. A checklist of SEW programs and an audit of SEW practices in schools were employed to investigate the number, range and types of SEW programs used by primary classroom teachers and the contextual factors influencing program use. Whilst the majority of implementation studies have been conducted under intervention conditions, this study was designed to capture primary classroom teachers’ day-to-day use of SEW programs and the factors influencing program use under real-world conditions. The findings of this research indicate that almost three quarters of the primary classroom teachers involved in the study reported using at least one SEW program during 2005. Wide variation in the number and range of programs used was evident, suggesting that teachers are autonomous in their use of SEW programs. Evidence-based SEW programs were used by a similar proportion of teachers to non-evidence-based programs. However, irrespective of the type of program used, primary teachers overwhelmingly reported using part of a SEW program rather than the whole program. This raises some issues about the quality of teachers’ program implementation in real-world practice, especially with respect to programs that are evidence-based. A content analysis revealed that a wide range of factors have been examined as potential influences on teachers’ implementation of health promotion programs in schools, including SEW programs, despite the limited number of studies undertaken to date. However, variation in the factors examined and study designs employed both within and across health promotion fields limited the extent to which studies could be compared. A methodological and statistical review also revealed substantial variation in the quality of reporting of studies. A variety of factors were examined as potential influences on primary classroom teachers’ use of SEW programs across multiple social-ecological levels of influence (ranging from community to school and individual levels). In this study, parent or caregiver involvement in class activities and the availability of wellbeing-related policies in primary schools were found to be influential in primary classroom teachers’ use of SEW programs. Teachers who often or always involve parents or caregivers in class activities were at a higher odds of program use relative to teachers who never or rarely involved parents or caregivers in class activities. However, teachers employed in schools with the highest number of wellbeing-related policies available were at a lower odds of program use relative to teachers employed in schools with fewer wellbeing-related policies available. Future research should investigate primary classroom teachers’ autonomy and motivations for using SEW programs and the reasons behind the selection and use of particular types of programs. A larger emphasis should also be placed upon teachers not using SEW programs to identify valid reasons for non-use. This would provide another step towards bridging the gap between the expectations of program developers and the needs of teachers who implement programs in practice. Additionally, the availability of wellbeing-related school policies and the types of activities that parents and caregivers are involved with in the classroom warrant more in-depth investigation. This will help to ascertain how and why these factors influence primary classroom teachers’ use of SEW programs on a day-to-day basis in schools.

A Flight control scheme to improve position tracking performance of rotary-wing UASs

This paper outlines an innovative and feasible flight control scheme for a rotary-wing unmanned aerial system (RUAS) with guaranteed safety and reliable flight quality in a gusty environment. The proposed control methodology aims to increase gust-attenuation capability of a RUAS to ensure improved flight performance when strong gusts occur. Based on the design of an effective estimator, an altitude controller is firstly constructed to synchronously compensate for fluctuations of the main rotor thrust which might lead to crashes in a gusty environment. Afterwards, a nonlinear state feedback controller is proposed to stabilize horizontal positions of the RUAS with gust-attenuation property. Performance of the proposed control framework is evaluated using parameters of a Vario XLC helicopter and high-fidelity simulations show that the proposed controllers can effectively reduce side-effect of gusts and demonstrate performance improvement when compared with the proportional-integral-derivative (PID) controllers.

Implementing the self-management threshold learning outcome in Australian legal curricula : insights from self-determination theory

In 2010, six Threshold Learning Outcomes (TLOs) for law were developed by the Australian Learning and Teaching Council's Discipline Scholars: Law. The final of these outcomes, TLO 6, concerns self-management. This thesis examines strategies for implementing self-management in Australian legal education by first contextualising the development of TLO 6 in light of other relevant national and international developments in higher education, and secondly, analysing this learning outcome through the lens of Self-Determination Theory (SDT), an influential branch of educational psychology. It is argued that the central concept of autonomous self-regulation in SDT provides insights into factors that are relevant to law students’ capacities for long-term self-management, which is reinforced by analysis of the literature on law students’ distress. Accordingly, curriculum design that supports students’ autonomy may simultaneously promote students’ self-management capacities. The discussion of theoretical and practical perspectives on autonomy supportive curriculum design in this thesis thus illuminates potential pedagogical approaches for the implementation of TLO 6 in Australian legal curricula.

A neural-network based flight controller for UASs

This paper presents a nonlinear gust-attenuation controller based on constrained neural-network (NN) theory. The controller aims to achieve sufficient stability and handling quality for a fixed-wing unmanned aerial system (UAS) in a gusty environment when control inputs are subjected to constraints. Constraints in inputs emulate situations where aircraft actuators fail requiring the aircraft to be operated with fail-safe capability. The proposed controller enables gust-attenuation property and stabilizes the aircraft dynamics in a gusty environment. The proposed flight controller is obtained by solving the Hamilton-Jacobi-Isaacs (HJI) equations based on an policy iteration (PI) approach. Performance of the controller is evaluated using a high-fidelity six degree-of-freedom Shadow UAS model. Simulations show that our controller demonstrates great performance improvement in a gusty environment, especially in angle-of-attack (AOA), pitch and pitch rate. Comparative studies are conducted with the proportional-integral-derivative (PID) controllers, justifying the efficiency of our controller and verifying its suitability for integration into the design of flight control systems for forced landing of UASs.

Nonparametric semantic segmentation for 3D street scenes

In this paper we propose a method to generate a large scale and accurate dense 3D semantic map of street scenes. A dense 3D semantic model of the environment can significantly improve a number of robotic applications such as autonomous driving, navigation or localisation. Instead of using offline trained classifiers for semantic segmentation, our approach employs a data-driven, nonparametric method to parse scenes which easily scale to a large environment and generalise to different scenes. We use stereo image pairs collected from cameras mounted on a moving car to produce dense depth maps which are combined into a global 3D reconstruction using camera poses from stereo visual odometry. Simultaneously, 2D automatic semantic segmentation using a nonparametric scene parsing method is fused into the 3D model. Furthermore, the resultant 3D semantic model is improved with the consideration of moving objects in the scene. We demonstrate our method on the publicly available KITTI dataset and evaluate the performance against manually generated ground truth.

Aircraft collision avoidance using spherical visual predictive control and single point features

This paper presents practical vision-based collision avoidance for objects approximating a single point feature. Using a spherical camera model, a visual predictive control scheme guides the aircraft around the object along a conical spiral trajectory. Visibility, state and control constraints are considered explicitly in the controller design by combining image and vehicle dynamics in the process model, and solving the nonlinear optimization problem over the resulting state space. Importantly, range is not required. Instead, the principles of conical spiral motion are used to design an objective function that simultaneously guides the aircraft along the avoidance trajectory, whilst providing an indication of the appropriate point to stop the spiral behaviour. Our approach is aimed at providing a potential solution to the See and Avoid problem for unmanned aircraft and is demonstrated through a series.