A Novel Approach to Haptic Tele-operation of Aerial Robot Vehicles

We present a novel, simple and effective approach for tele-operation of aerial robotic vehicles with haptic feedback. Such feedback provides the remote pilot with an intuitive feel of the robot’s state and perceived local environment that will ensure simple and safe operation in cluttered 3D environments common in inspection and surveillance tasks. Our approach is based on energetic considerations and uses the concepts of network theory and port-Hamiltonian systems. We provide a general framework for addressing problems such as mapping the limited stroke of a ‘master’ joystick to the infinite stroke of a ‘slave’ vehicle, while preserving passivity of the closed-loop system in the face of potential time delays in communications links and limited sensor data

Automatic spoken language identification utilizing acoustic and phonetic speech information

Automatic spoken Language Identi¯cation (LID) is the process of identifying the language spoken within an utterance. The challenge that this task presents is that no prior information is available indicating the content of the utterance or the identity of the speaker. The trend of globalization and the pervasive popularity of the Internet will amplify the need for the capabilities spoken language identi¯ca- tion systems provide. A prominent application arises in call centers dealing with speakers speaking di®erent languages. Another important application is to index or search huge speech data archives and corpora that contain multiple languages. The aim of this research is to develop techniques targeted at producing a fast and more accurate automatic spoken LID system compared to the previous National Institute of Standards and Technology (NIST) Language Recognition Evaluation. Acoustic and phonetic speech information are targeted as the most suitable fea- tures for representing the characteristics of a language. To model the acoustic speech features a Gaussian Mixture Model based approach is employed. Pho- netic speech information is extracted using existing speech recognition technol- ogy. Various techniques to improve LID accuracy are also studied. One approach examined is the employment of Vocal Tract Length Normalization to reduce the speech variation caused by di®erent speakers. A linear data fusion technique is adopted to combine the various aspects of information extracted from speech. As a result of this research, a LID system was implemented and presented for evaluation in the 2003 Language Recognition Evaluation conducted by the NIST.

IDOL

Idol is a collaborative performance work for vocal performer and dancers. The work explores movement and sound relative to a vocal interface called the eMic (Extended Microphone Interface Controller). The eMic is a gestural controller designed by the composer for live vocal performance an real-time processing. The process for generating the work involves the choreographer being provided an opportunity to experiment with gestures ad movement relative to the eMic interface. The choreographer explored the interface as an object,a prop, an instrument and as an extension of the body. the movement was then videoed and the data coming from the sensors simultaneously recorded. The data and the video were then used as part of the compositional process, allowing the composer to see what the performance looks like and to experiment with mapping strategies using the captured sensor data. This approach represents a new compositional direction for working with the eMic, in that previously the compositional process commenced at the computer, building processing patches and assigning parameters to eMic sensors. In order to play the composition, the body needed to adapt to 'playing' the instrument. This approach treats the eMic like a traditional instrument that requires the human body to develop a command over the instrument. Working with the movement as a starting point inverts the process using choreographic gestures as the basis for musical structures.

V2V/V2I augmented maps : state-of-the-art and contribution to real-time crash risk assessment

A number of advanced driver assistance systems (ADAS) are currently being released on the market, providing safety functions to the drivers such as collision avoidance, adaptive cruise control or enhanced night-vision. These systems however are inherently limited by their sensory range: they cannot gather information from outside this range, also called their “perceptive horizon”. Cooperative systems are a developing research avenue that aims at providing extended safety and comfort functionalities by introducing vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) wireless communications to the road actors. This paper presents the problematic of cooperative systems, their advantages and contributions to road safety and exposes some limitations related to market penetration, sensors accuracy and communications scalability. It explains the issues of how to implement extended perception, a central contribution of cooperative systems. The initial steps of an evaluation of data fusion architectures for extended perception are exposed.

Sequential nonlinear manifold learning

The computation of compact and meaningful representations of high dimensional sensor data has recently been addressed through the development of Nonlinear Dimensional Reduction (NLDR) algorithms. The numerical implementation of spectral NLDR techniques typically leads to a symmetric eigenvalue problem that is solved by traditional batch eigensolution algorithms. The application of such algorithms in real-time systems necessitates the development of sequential algorithms that perform feature extraction online. This paper presents an efficient online NLDR scheme, Sequential-Isomap, based on incremental singular value decomposition (SVD) and the Isomap method. Example simulations demonstrate the validity and significant potential of this technique in real-time applications such as autonomous systems.

A statistical framework for natural feature representation

This paper presents a robust stochastic framework for the incorporation of visual observations into conventional estimation, data fusion, navigation and control algorithms. The representation combines Isomap, a non-linear dimensionality reduction algorithm, with expectation maximization, a statistical learning scheme. The joint probability distribution of this representation is computed offline based on existing training data. The training phase of the algorithm results in a nonlinear and non-Gaussian likelihood model of natural features conditioned on the underlying visual states. This generative model can be used online to instantiate likelihoods corresponding to observed visual features in real-time. The instantiated likelihoods are expressed as a Gaussian mixture model and are conveniently integrated within existing non-linear filtering algorithms. Example applications based on real visual data from heterogenous, unstructured environments demonstrate the versatility of the generative models.

Spectral–texture feature extraction using statistical moments with application to object-based vegetation species classification

The use of appropriate features to characterise an output class or object is critical for all classification problems. In order to find optimal feature descriptors for vegetation species classification in a power line corridor monitoring application, this article evaluates the capability of several spectral and texture features. A new idea of spectral–texture feature descriptor is proposed by incorporating spectral vegetation indices in statistical moment features. The proposed method is evaluated against several classic texture feature descriptors. Object-based classification method is used and a support vector machine is employed as the benchmark classifier. Individual tree crowns are first detected and segmented from aerial images and different feature vectors are extracted to represent each tree crown. The experimental results showed that the proposed spectral moment features outperform or can at least compare with the state-of-the-art texture descriptors in terms of classification accuracy. A comprehensive quantitative evaluation using receiver operating characteristic space analysis further demonstrates the strength of the proposed feature descriptors.

Arterial travel time estimation : revisiting the classical procedure

Travel time is an important network performance measure and it quantifies congestion in a manner easily understood by all transport users. In urban networks, travel time estimation is challenging due to number of reasons such as, fluctuations in traffic flow due to traffic signals, significant flow to/from mid link sinks/sources, etc. The classical analytical procedure utilizes cumulative plots at upstream and downstream locations for estimating travel time between the two locations. In this paper, we discuss about the issues and challenges with classical analytical procedure such as its vulnerability to non conservation of flow between the two locations. The complexity with respect to exit movement specific travel time is discussed. Recently, we have developed a methodology utilising classical procedure to estimate average travel time and its statistic on urban links (Bhaskar, Chung et al. 2010). Where, detector, signal and probe vehicle data is fused. In this paper we extend the methodology for route travel time estimation and test its performance using simulation. The originality is defining cumulative plots for each exit turning movement utilising historical database which is self updated after each estimation. The performance is also compared with a method solely based on probe (Probe-only). The performance of the proposed methodology has been found insensitive to different route flow, with average accuracy of more than 94% given a probe per estimation interval which is more than 5% increment in accuracy with respect to Probe-only method.

Sampling environmental acoustic recordings to determine species richness : I

Acoustic sensors provide an effective means of monitoring biodiversity at large spatial and temporal scales. They can continuously and passively record large volumes of data over extended periods, however these data must be analysed to detect the presence of vocal species. Automated analysis of acoustic data for large numbers of species is complex and can be subject to high levels of false positive and false negative results. Manual analysis by experienced users can produce accurate results, however the time and effort required to process even small volumes of data can make manual analysis prohibitive. Our research examined the use of sampling methods to reduce the cost of analysing large volumes of acoustic sensor data, while retaining high levels of species detection accuracy. Utilising five days of manually analysed acoustic sensor data from four sites, we examined a range of sampling rates and methods including random, stratified and biologically informed. Our findings indicate that randomly selecting 120, one-minute samples from the three hours immediately following dawn provided the most effective sampling method. This method detected, on average 62% of total species after 120 one-minute samples were analysed, compared to 34% of total species from traditional point counts. Our results demonstrate that targeted sampling methods can provide an effective means for analysing large volumes of acoustic sensor data efficiently and accurately.

Assessment of daily light and ultraviolet exposure in young adults

Purpose: There are some limited reports, based on questionnaire data, which suggest that outdoor activity decreases the risk of myopia in children and may offset the myopia risk associated with prolonged near work. The aim of this study was to explore the relationship between near work, indoor illumination, daily sunlight and ultraviolet (UV) exposure in emmetropic and myopic University students, given that University students perform significant amounts of near work and as a group have a high prevalence of myopia. Methods: Participants were 35 students, aged 17 to 25 years who were classified as being emmetropic (n=13), or having stable (n=12) or progressing myopia (n=10). During waking hours on three separate days participants wore a light sensor data logger (HOBO) and a polysulphone UV dosimeter; these devices measured daily illuminance and accumulative UV exposure respectively; participants also completed a daily activity log. Results: No significant between group differences were observed for average daily illuminance (p=0.732), number of hours per day spent in sunlight (p=0.266), outdoor shade (p=0.726), bright indoor/dim outdoor light (p=0.574) or dim room illumination (p=0.484). Daily UV exposure was significantly different across the groups (p=0.003); with stable myopes experiencing the greatest UV exposure (versus emmetropes p=0.002; versus progressing myopes p=0.004). Conclusions: The current literature suggests there is a link between myopia protection and spending time outdoors in children. Our data provides some evidence of this relationship in young adults and highlights the need for larger studies to further investigate this relationship longitudinally.

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.

Street Computing : Urban Informatics and City Interfaces

This book develops tools and techniques that will help urban residents gain access to urban computing. Metaphorically speaking, it is taking computing to the street by giving the general public – rather than just researchers and professionals – the power to leverage available city infrastructure and create solutions tailored to their individual needs. It brings together five chapters that are based on presentations given at the Street Computing Workshop held on 24 November 2009 in Melbourne in conjunction with the Australian Computer-Human Interaction Conference (OZCHI 2009). This book focuses on applying urban informatics, urban and community sensing and open application programming interfaces (APIs) to the public space through the delivery of online services, on demand and in real time. It then offers a case study of how the city of Singapore has harnessed the potential of an online infrastructure so that residents and visitors can access services electronically. This book was published as a special issue of the Journal of Urban Technology, 19(2), 2012.

Modelling bluetooth and fusing with loops

The invited presentation was delivered at Queensland Department of Main Roads, Brisbane Australia, 17th June 2013

Integrated traveller information

This poster summarises the current findings from STRC’s Integrated Traveller Information research domain that aims for accurate and reliable travel time prediction, and optimisation of multimodal trips. Following are the three selected discussions: a) Fundamental understanding on the use of Bluetooth MAC Scanner (BMS) for travel time estimation b) Integration of multi-sources (Loops and Bluetooth) for travel time and density estimation c) Architecture for online and predictive multimodal trip planner