Darjeeling, a feature-rich VM for the resource poor

The programming and retasking of sensor nodes could benefit greatly from the use of a virtual machine (VM) since byte code is compact, can be loaded on demand, and interpreted on a heterogeneous set of devices. The challenge is to ensure good programming tools and a small footprint for the virtual machine to meet the memory constraints of typical WSN platforms. To this end we propose Darjeeling, a virtual machine modelled after the Java VM and capable of executing a substantial subset of the Java language, but designed specifically to run on 8- and 16-bit microcontrollers with 2 - 10 KB of RAM. The Darjeeling VM uses a 16- rather than a 32-bit architecture, which is more efficient on the targeted platforms. Darjeeling features a novel memory organisation with strict separation of reference from non-reference types which eliminates the need for run-time type inspection in the underlying compacting garbage collector. Darjeeling uses a linked stack model that provides light-weight threads, and supports synchronisation. The VM has been implemented on three different platforms and was evaluated with micro benchmarks and a real-world application. The latter includes a pure Java implementation of the collection tree routing protocol conveniently programmed as a set of cooperating threads, and a reimplementation of an existing environmental monitoring application. The results show that Darjeeling is a viable solution for deploying large-scale heterogeneous sensor networks. Copyright 2009 ACM.

Experience mapping : producing spatially continuous environment representations using RatSLAM

RatSLAM is a system for vision-based Simultaneous Localisation and Mapping (SLAM) inspired by models of the rodent hippocampus. The system can produce stable representations of large complex environments during robot experiments in both indoor and outdoor environments. These representations are both topological and metric in nature, and can involve multiple representations of the same place as well as discontinuities. In this paper we describe a new technique known as experience mapping that can be used online with the RatSLAM system to produce world representations known as experience maps. These maps group together multiple place representations and are spatially continuous. A number of experiments have been conducted in simulation and a real world office environment. These experiments demonstrate the high degree to which experience maps are representative of the spatial arrangement of the environment.

RatSLAM on the edge : revealing a coherent representation from an overloaded rat brain

The RatSLAM system can perform vision based SLAM using a computational model of the rodent hippocampus. When the number of pose cells used to represent space in RatSLAM is reduced, artifacts are introduced that hinder its use for goal directed navigation. This paper describes a new component for the RatSLAM system called an experience map, which provides a coherent representation for goal directed navigation. Results are presented for two sets of real world experiments, including comparison with the original goal memory system's performance in the same environment. Preliminary results are also presented demonstrating the ability of the experience map to adapt to simple short term changes in the environment.

Efficient goal directed navigation using RatSLAM

RatSLAM is a system for vision based Simultaneous Localization and Mapping (SLAM) that has been shown to be capable of building stable representations of real world environments. In this paper we describe a method for using RatSLAM representations as the basis for navigation to designated goal locations. The method uses a new component, goal memory, to learn the temporal gradient between places. Paths are recalled or inferred from the goal memory by following the temporal gradient from the robot’s current position to the goal location. Experimental results have been gathered in a combined office and laboratory environment using a Pioneer robot. The experiments show that the robot can perform vision based SLAM on-line and in real time, and then use those representations immediately to navigate directly to designated goal locations.

Airborne systems laboratory for automation research

This paper presents an Airborne Systems Laboratory for Automation Research. The Airborne Systems Laboratory (ASL) is a Cessna 172 aircraft that has been specially modified and equipped by ARCAA specifically for research in future aircraft automation technologies, including Unmanned Airborne Systems (UAS). This capability has been developed over a long period of time, initially through the hire of aircraft, and finally through the purchase and modification of a dedicated flight-testing capability. The ASL has been equipped with a payload system that includes the provision of secure mounting, power, aircraft state data, flight management system and real-time subsystem. Finally, this system has been deployed in a cost effective platform allowing real-world flight-testing on a range of projects.

Bayesian hybrid algorithms and models : implementation and associated issues

This thesis addresses computational challenges arising from Bayesian analysis of complex real-world problems. Many of the models and algorithms designed for such analysis are ‘hybrid’ in nature, in that they are a composition of components for which their individual properties may be easily described but the performance of the model or algorithm as a whole is less well understood. The aim of this research project is to after a better understanding of the performance of hybrid models and algorithms. The goal of this thesis is to analyse the computational aspects of hybrid models and hybrid algorithms in the Bayesian context. The first objective of the research focuses on computational aspects of hybrid models, notably a continuous finite mixture of t-distributions. In the mixture model, an inference of interest is the number of components, as this may relate to both the quality of model fit to data and the computational workload. The analysis of t-mixtures using Markov chain Monte Carlo (MCMC) is described and the model is compared to the Normal case based on the goodness of fit. Through simulation studies, it is demonstrated that the t-mixture model can be more flexible and more parsimonious in terms of number of components, particularly for skewed and heavytailed data. The study also reveals important computational issues associated with the use of t-mixtures, which have not been adequately considered in the literature. The second objective of the research focuses on computational aspects of hybrid algorithms for Bayesian analysis. Two approaches will be considered: a formal comparison of the performance of a range of hybrid algorithms and a theoretical investigation of the performance of one of these algorithms in high dimensions. For the first approach, the delayed rejection algorithm, the pinball sampler, the Metropolis adjusted Langevin algorithm, and the hybrid version of the population Monte Carlo (PMC) algorithm are selected as a set of examples of hybrid algorithms. Statistical literature shows how statistical efficiency is often the only criteria for an efficient algorithm. In this thesis the algorithms are also considered and compared from a more practical perspective. This extends to the study of how individual algorithms contribute to the overall efficiency of hybrid algorithms, and highlights weaknesses that may be introduced by the combination process of these components in a single algorithm. The second approach to considering computational aspects of hybrid algorithms involves an investigation of the performance of the PMC in high dimensions. It is well known that as a model becomes more complex, computation may become increasingly difficult in real time. In particular the importance sampling based algorithms, including the PMC, are known to be unstable in high dimensions. This thesis examines the PMC algorithm in a simplified setting, a single step of the general sampling, and explores a fundamental problem that occurs in applying importance sampling to a high-dimensional problem. The precision of the computed estimate from the simplified setting is measured by the asymptotic variance of the estimate under conditions on the importance function. Additionally, the exponential growth of the asymptotic variance with the dimension is demonstrated and we illustrates that the optimal covariance matrix for the importance function can be estimated in a special case.

Audio visual automatic speech recognition in vehicles

Acoustically, car cabins are extremely noisy and as a consequence, existing audio-only speech recognition systems, for voice-based control of vehicle functions such as the GPS based navigator, perform poorly. Audio-only speech recognition systems fail to make use of the visual modality of speech (eg: lip movements). As the visual modality is immune to acoustic noise, utilising this visual information in conjunction with an audio only speech recognition system has the potential to improve the accuracy of the system. The field of recognising speech using both auditory and visual inputs is known as Audio Visual Speech Recognition (AVSR). Continuous research in AVASR field has been ongoing for the past twenty-five years with notable progress being made. However, the practical deployment of AVASR systems for use in a variety of real-world applications has not yet emerged. The main reason is due to most research to date neglecting to address variabilities in the visual domain such as illumination and viewpoint in the design of the visual front-end of the AVSR system. In this paper we present an AVASR system in a real-world car environment using the AVICAR database [1], which is publicly available in-car database and we show that the use of visual speech conjunction with the audio modality is a better approach to improve the robustness and effectiveness of voice-only recognition systems in car cabin environments.

An empirical study of data collection protocols for wireless sensor networks

In the past few years, numerous data collection protocols have been developed for wireless sensor networks (WSNs). However, there has been no comparison of their relative performance in realistic environments. Here we report the results of an empirical study using a Fleck3 sensor network testbed for four different data collection protocols: One phase pull Directed Diffusion (DD), Expected Number of Transmissions (ETX), ETX with explicit acknowledgment (ETX-eAck), and ETX with implicit acknowledgment (ETX-iAck). Our empirical study provides useful insights for future sensor network deployments. When the required application end-to-end reliability is not strict (e.g., 70%) and link quality is good, DD and ETX are the best options because of their simplicity and low routing overhead. Both ETX-eAck and ETX-iAck achieve more than 90% end-to-end reliability when the link quality is reasonable (less than 25% packet loss). When the link quality is good, ETX-iAck introduces significantly less routing overhead (up to 50%) than ETX-eAck. However, if the radio transceiver supports variable packet length, ETX-eAck can outperform ETX-iAck when the link quality is poor. The important message from this paper is that choice of data collection protocol should come after the operating environment is understood. This understanding must include the characteristics of the radio transceiver, and link loss statistics from a long-term (across seasons and weather variation) radio survey of the site.

Field and Service Robotics Results of the 5th International Conference

The 5th International Conference on Field and Service Robotics (FSR05) was held in Port Douglas, Australia, on 29th - 31st July 2005, and brought together the worlds' leading experts in field and service automation. The goal of the conference was to report and encourage the latest research and practical results towards the use of field and service robotics in the community with particular focus on proven technology. The conference provided a forum for researchers, professionals and robot manufacturers to exchange up-to-date technical knowledge and experience. Field robots are robots which operate in outdoor, complex, and dynamic environments. Service robots are those that work closely with humans, with particular applications involving indoor and structured environments. There are a wide range of topics presented in this issue on field and service robots including: Agricultural and Forestry Robotics, Mining and Exploration Robots, Robots for Construction, Security & Defence Robots, Cleaning Robots, Autonomous Underwater Vehicles and Autonomous Flying Robots. This meeting was the fifth in the series and brings FSR back to Australia where it was first held. FSR has been held every 2 years, starting with Canberra 1997, followed by Pittsburgh 1999, Helsinki 2001 and Lake Yamanaka 2003.

Vision-based navigational competencies for a car-like vehicle

If mobile robots are to perform useful tasks in the real-world they will require a catalog of fundamental navigation competencies and a means to select between them. In this paper we describe our work on strongly vision-based competencies: road-following, person or vehicle following, pose and position stabilization. Results from experiments on an outdoor autonomous tractor, a car-like vehicle, are presented.

Tracking road edges in the panospheric image plane

This paper presents a technique for tracking road edges in a panoramic image sequence. The major contribution is that instead of unwarping the image to find parallel lines representing the road edges, we choose to warp the parallel groundplane lines into the image plane of the equiangular panospheric camera. Updating the parameters of the line thus involves searching a very small number of pixels in the panoramic image, requiring considerably less computation than unwarping. Results using real-world images, including shadows, intersections and curves, are presented.

Personal epistemology in pre-service teachers : belief changes throughout a teacher education course

Classrooms of the 21st century are complex systems. They support diverse learners from varied contexts and function in a “messy” bricolage of policy contexts. This complexity is also evident in the nature of teaching and learning deployed in these classrooms. There is also, in current contexts, a general expectation that teachers will support students to construct, rather than simply receive knowledge. This process of constructing knowledge requires a focus on critical thinking in complex social and real world contexts (see also Elen & Clarebout, 2001; Yang, Chang & Hsu 2008). Critical thinking, which involves the identification and evaluation of multiple perspectives when making decisions, is a process of knowing – a tool of wisdom (Kuhn & Udell, 2001). Schommer-Aikens, Bird and Bakken (2010) refer to classrooms that encourage critical thinking as “epistemologically based” in which “the teacher encourages his/her students to look for connections among concepts within the text, with their prior knowledge, and with concepts found in the world beyond themselves” (p. 48).

An exploratory study of online social networking within a Doctorate of Education program

The professional doctorate is a degree that is specifically designed for professionals investigating real-world problems and relevant issues for a profession, industry and/or the community. The exploratory study on which this paper is based sought to track the scholarly skill development of a cohort of professional doctoral students who commenced their course in January 2008 at an Australian university. Via an initial survey and two focus groups held six months apart, the study aimed to determine if there had been any qualitative shifts in students’ understandings, expectations and perceptions regarding their developing knowledge and skills. Three key findings that emerged from this study were: (i) the appropriateness of using a blended learning approach in this professional doctoral program; (ii) the challenges of using wikis as an online technology for creating communities of practice; and (iii) the transition from professional to scholar is a process that requires the guided support inherent in the design of this particular doctorate of education program.

Web-based and traditional public participation in comprehensive planning : a comparative study

The present paper examines whether the potential advantages of the expanding practice of web-based public participation only complement the benefits of the traditional techniques, or are empowering enough to replace them. The question is examined in a real-world case of neighbourhood revitalization, in which both techniques were practiced simultaneously. Comparisons are made at four major planning junctions, in order to study the contributions of each technique to the qualities of involvement, trust, and empowerment. The results show that web-based participants not only differ from the participants of traditional practices, but they also differ from each other on the basis of their type of web participation. The results indicate that web-based participation is an effective and affective complementary means of public participation, but it cannot replace the traditional unmediated techniques.

Speech recognition using ad-hoc microphone arrays

While close talking microphones give the best signal quality and produce the highest accuracy from current Automatic Speech Recognition (ASR) systems, the speech signal enhanced by microphone array has been shown to be an effective alternative in a noisy environment. The use of microphone arrays in contrast to close talking microphones alleviates the feeling of discomfort and distraction to the user. For this reason, microphone arrays are popular and have been used in a wide range of applications such as teleconferencing, hearing aids, speaker tracking, and as the front-end to speech recognition systems. With advances in sensor and sensor network technology, there is considerable potential for applications that employ ad-hoc networks of microphone-equipped devices collaboratively as a virtual microphone array. By allowing such devices to be distributed throughout the users’ environment, the microphone positions are no longer constrained to traditional fixed geometrical arrangements. This flexibility in the means of data acquisition allows different audio scenes to be captured to give a complete picture of the working environment. In such ad-hoc deployment of microphone sensors, however, the lack of information about the location of devices and active speakers poses technical challenges for array signal processing algorithms which must be addressed to allow deployment in real-world applications. While not an ad-hoc sensor network, conditions approaching this have in effect been imposed in recent National Institute of Standards and Technology (NIST) ASR evaluations on distant microphone recordings of meetings. The NIST evaluation data comes from multiple sites, each with different and often loosely specified distant microphone configurations. This research investigates how microphone array methods can be applied for ad-hoc microphone arrays. A particular focus is on devising methods that are robust to unknown microphone placements in order to improve the overall speech quality and recognition performance provided by the beamforming algorithms. In ad-hoc situations, microphone positions and likely source locations are not known and beamforming must be achieved blindly. There are two general approaches that can be employed to blindly estimate the steering vector for beamforming. The first is direct estimation without regard to the microphone and source locations. An alternative approach is instead to first determine the unknown microphone positions through array calibration methods and then to use the traditional geometrical formulation for the steering vector. Following these two major approaches investigated in this thesis, a novel clustered approach which includes clustering the microphones and selecting the clusters based on their proximity to the speaker is proposed. Novel experiments are conducted to demonstrate that the proposed method to automatically select clusters of microphones (ie, a subarray), closely located both to each other and to the desired speech source, may in fact provide a more robust speech enhancement and recognition than the full array could.