Robotics and Sensor Networks

Robotics in mines, aerospace, underwater, everyday unstructured environments and sensor networks with communicating devices that collect data.

Acoustic keyword spotting in speech with applications to data mining

Keyword Spotting is the task of detecting keywords of interest within continu- ous speech. The applications of this technology range from call centre dialogue systems to covert speech surveillance devices. Keyword spotting is particularly well suited to data mining tasks such as real-time keyword monitoring and unre- stricted vocabulary audio document indexing. However, to date, many keyword spotting approaches have su®ered from poor detection rates, high false alarm rates, or slow execution times, thus reducing their commercial viability. This work investigates the application of keyword spotting to data mining tasks. The thesis makes a number of major contributions to the ¯eld of keyword spotting. The ¯rst major contribution is the development of a novel keyword veri¯cation method named Cohort Word Veri¯cation. This method combines high level lin- guistic information with cohort-based veri¯cation techniques to obtain dramatic improvements in veri¯cation performance, in particular for the problematic short duration target word class. The second major contribution is the development of a novel audio document indexing technique named Dynamic Match Lattice Spotting. This technique aug- ments lattice-based audio indexing principles with dynamic sequence matching techniques to provide robustness to erroneous lattice realisations. The resulting algorithm obtains signi¯cant improvement in detection rate over lattice-based audio document indexing while still maintaining extremely fast search speeds. The third major contribution is the study of multiple veri¯er fusion for the task of keyword veri¯cation. The reported experiments demonstrate that substantial improvements in veri¯cation performance can be obtained through the fusion of multiple keyword veri¯ers. The research focuses on combinations of speech background model based veri¯ers and cohort word veri¯ers. The ¯nal major contribution is a comprehensive study of the e®ects of limited training data for keyword spotting. This study is performed with consideration as to how these e®ects impact the immediate development and deployment of speech technologies for non-English languages.

Design and implementation of sensor networks for the observation and research of harmful algal blooms in southern California coastal waters

Harmful Algal Blooms (HABs) have become an important environmental concern along the western coast of the United States. Toxic and noxious blooms adversely impact the economies of coastal communities in the region, pose risks to human health, and cause mortality events that have resulted in the deaths of thousands of fish, marine mammals and seabirds. One goal of field-based research efforts on this topic is the development of predictive models of HABs that would enable rapid response, mitigation and ultimately prevention of these events. In turn, these objectives are predicated on understanding the environmental conditions that stimulate these transient phenomena. An embedded sensor network (Fig. 1), under development in the San Pedro Shelf region off the Southern California coast, is providing tools for acquiring chemical, physical and biological data at high temporal and spatial resolution to help document the emergence and persistence of HAB events, supporting the design and testing of predictive models, and providing contextual information for experimental studies designed to reveal the environmental conditions promoting HABs. The sensor platforms contained within this network include pier-based sensor arrays, ocean moorings, HF radar stations, along with mobile sensor nodes in the form of surface and subsurface autonomous vehicles. FreewaveTM radio modems facilitate network communication and form a minimally-intrusive, wireless communication infrastructure throughout the Southern California coastal region, allowing rapid and cost-effective data transfer. An emerging focus of this project is the incorporation of a predictive ocean model that assimilates near-real time, in situ data from deployed Autonomous Underwater Vehicles (AUVs). The model then assimilates the data to increase the skill of both nowcasts and forecasts, thus providing insight into bloom initiation as well as the movement of blooms or other oceanic features of interest (e.g., thermoclines, fronts, river discharge, etc.). From these predictions, deployed mobile sensors can be tasked to track a designated feature. This focus has led to the creation of a technology chain in which algorithms are being implemented for the innovative trajectory design for AUVs. Such intelligent mission planning is required to maneuver a vehicle to precise depths and locations that are the sites of active blooms, or physical/chemical features that might be sources of bloom initiation or persistence. The embedded network yields high-resolution, temporal and spatial measurements of pertinent environmental parameters and resulting biology (see Fig. 1). Supplementing this with ocean current information and remotely sensed imagery and meteorological data, we obtain a comprehensive foundation for developing a fundamental understanding of HAB events. This then directs labor- intensive and costly sampling efforts and analyses. Additionally, we provide coastal municipalities, managers and state agencies with detailed information to aid their efforts in providing responsible environmental stewardship of their coastal waters.

Implementation of an embedded sensor network for the coordination of Slocum gliders for coastal monitoring and observation

Autonomous Underwater Vehicles (AUVs) are revolutionizing oceanography through their versatility, autonomy and endurance. However, they are still an underutilized technology. For coastal operations, the ability to track a certain feature is of interest to ocean scientists. Adaptive and predictive path planning requires frequent communication with significant data transfer. Currently, most AUVs rely on satellite phones as their primary communication. This communication protocol is expensive and slow. To reduce communication costs and provide adequate data transfer rates, we present a hardware modification along with a software system that provides an alternative robust disruption- tolerant communications framework enabling cost-effective glider operation in coastal regions. The framework is specifically designed to address multi-sensor deployments. We provide a system overview and present testing and coverage data for the network. Additionally, we include an application of ocean-model driven trajectory design, which can benefit from the use of this network and communication system. Simulation and implementation results are presented for single and multiple vehicle deployments. The presented combination of infrastructure, software development and deployment experience brings us closer to the goal of providing a reliable and cost-effective data transfer framework to enable real-time, optimal trajectory design, based on ocean model predictions, to gather in situ measurements of interesting and evolving ocean features and phenomena.

Networked robotic sensor platform deployments for use in coastal environmental assessment in southern California

Mobile sensor platforms such as Autonomous Underwater Vehicles (AUVs) and robotic surface vessels, combined with static moored sensors compose a diverse sensor network that is able to provide macroscopic environmental analysis tool for ocean researchers. Working as a cohesive networked unit, the static buoys are always online, and provide insight as to the time and locations where a federated, mobile robot team should be deployed to effectively perform large scale spatiotemporal sampling on demand. Such a system can provide pertinent in situ measurements to marine biologists whom can then advise policy makers on critical environmental issues. This poster presents recent field deployment activity of AUVs demonstrating the effectiveness of our embedded communication network infrastructure throughout southern California coastal waters. We also report on progress towards real-time, web-streaming data from the multiple sampling locations and mobile sensor platforms. Static monitoring sites included in this presentation detail the network nodes positioned at Redondo Beach and Marina Del Ray. One of the deployed mobile sensors highlighted here are autonomous Slocum gliders. These nodes operate in the open ocean for periods as long as one month. The gliders are connected to the network via a Freewave radio modem network composed of multiple coastal base-stations. This increases the efficiency of deployment missions by reducing operational expenses via reduced reliability on satellite phones for communication, as well as increasing the rate and amount of data that can be transferred. Another mobile sensor platform presented in this study are the autonomous robotic boats. These platforms are utilized for harbor and littoral zone studies, and are capable of performing multi-robot coordination while observing known communication constraints. All of these pieces fit together to present an overview of ongoing collaborative work to develop an autonomous, region-wide, coastal environmental observation and monitoring sensor network.

Decentralised particle filtering for multiple target tracking in wireless sensor networks

Record 8 of 29

Range sensor pose estimation

This paper presents a method of recovering the 6 DoF pose (Cartesian position and angular rotation) of a range sensor mounted on a mobile platform. The method utilises point targets in a local scene and optimises over the error between their absolute position and their apparent position as observed by the range sensor. The analysis includes an investigation into the sensitivity and robustness of the method. Practical results were collected using a SICK LRS2100 mounted on a P&H electric mining shovel and present the errors in scan data relative to an independent 3D scan of the scene. A comparison to directly measuring the sensor pose is presented and shows the significant accuracy improvements in scene reconstruction using this pose estimation method.

Ontology-based specific and exhaustive user profiles for constraint information fusion for multi-agents

Intelligent agents are an advanced technology utilized in Web Intelligence. When searching information from a distributed Web environment, information is retrieved by multi-agents on the client site and fused on the broker site. The current information fusion techniques rely on cooperation of agents to provide statistics. Such techniques are computationally expensive and unrealistic in the real world. In this paper, we introduce a model that uses a world ontology constructed from the Dewey Decimal Classification to acquire user profiles. By search using specific and exhaustive user profiles, information fusion techniques no longer rely on the statistics provided by agents. The model has been successfully evaluated using the large INEX data set simulating the distributed Web environment.

An indication that non-informative vision eliminates the Kinaesthetic Fusion Effect

This study investigated the Kinaesthetic Fusion Effect (KFE) first described by Craske and Kenny in 1981. The current study did not replicate these findings. Participants did not perceive any reduction in the sagittal separation of a button pressed by the index finger of one arm and a probe touching the other, following repeated exposure to the tactile stimuli present on both unseen arms. This study’s failure to replicate the widely-cited KFE as described by Craske et al. (1984) suggests that it may be contingent on several aspects of visual information, especially the availability of a specific visual reference, the role of instructions regarding gaze direction, and the potential use of a line of sight strategy when referring felt positions to an interposed surface. In addition, a foreshortening effect was found; this may result from a line-of-sight judgment and represent a feature of the reporting method used. The transformed line of sight data were regressed against the participant reported values, resulting in a slope of 1.14 (right arm) and 1.11 (left arm), and r > 0.997 for each. The study also provides additional evidence that mis-perceptions of the mediolateral position of the limbs specifically their separation and consistent with notions of Gestalt grouping, is somewhat labile and can be influenced by active motions causing touch of one limb by the other. Finally, this research will benefit future studies that require participants to report the perceived locations of the unseen limbs.

Robust speaker verification via fusion of speech and lip modalities

This paper investigates the use of lip information, in conjunction with speech information, for robust speaker verification in the presence of background noise. It has been previously shown in our own work, and in the work of others, that features extracted from a speaker's moving lips hold speaker dependencies which are complementary with speech features. We demonstrate that the fusion of lip and speech information allows for a highly robust speaker verification system which outperforms the performance of either sub-system. We present a new technique for determining the weighting to be applied to each modality so as to optimize the performance of the fused system. Given a correct weighting, lip information is shown to be highly effective for reducing the false acceptance and false rejection error rates in the presence of background noise

Gaussian process models for sensor-centric robot localisation

This paper presents an approach to building an observation likelihood function from a set of sparse, noisy training observations taken from known locations by a sensor with no obvious geometric model. The basic approach is to fit an interpolant to the training data, representing the expected observation, and to assume additive sensor noise. This paper takes a Bayesian view of the problem, maintaining a posterior over interpolants rather than simply the maximum-likelihood interpolant, giving a measure of uncertainty in the map at any point. This is done using a Gaussian process framework. To validate the approach experimentally, a model of an environment is built using observations from an omni-directional camera. After a model has been built from the training data, a particle filter is used to localise while traversing this environment

Program your city : designing an urban integrated open data API

Cities accumulate and distribute vast sets of digital information. Many decision-making and planning processes in councils, local governments and organisations are based on both real-time and historical data. Until recently, only a small, carefully selected subset of this information has been released to the public – usually for specific purposes (e.g. train timetables, release of planning application through websites to name just a few). This situation is however changing rapidly. Regulatory frameworks, such as the Freedom of Information Legislation in the US, the UK, the European Union and many other countries guarantee public access to data held by the state. One of the results of this legislation and changing attitudes towards open data has been the widespread release of public information as part of recent Government 2.0 initiatives. This includes the creation of public data catalogues such as data.gov.au (U.S.), data.gov.uk (U.K.), data.gov.au (Australia) at federal government levels, and datasf.org (San Francisco) and data.london.gov.uk (London) at municipal levels. The release of this data has opened up the possibility of a wide range of future applications and services which are now the subject of intensified research efforts. Previous research endeavours have explored the creation of specialised tools to aid decision-making by urban citizens, councils and other stakeholders (Calabrese, Kloeckl & Ratti, 2008; Paulos, Honicky & Hooker, 2009). While these initiatives represent an important step towards open data, they too often result in mere collections of data repositories. Proprietary database formats and the lack of an open application programming interface (API) limit the full potential achievable by allowing these data sets to be cross-queried. Our research, presented in this paper, looks beyond the pure release of data. It is concerned with three essential questions: First, how can data from different sources be integrated into a consistent framework and made accessible? Second, how can ordinary citizens be supported in easily composing data from different sources in order to address their specific problems? Third, what are interfaces that make it easy for citizens to interact with data in an urban environment? How can data be accessed and collected?

Field portable time resolved SORS sensor for the identification of concealed hazards

Raman spectroscopy, when used in spatially offset mode, has become a potential tool for the identification of explosives and other hazardous substances concealed in opaque containers. The molecular fingerprinting capability of Raman spectroscopy makes it an attractive tool for the unambiguous identification of hazardous substances in the field. Additionally, minimal sample preparation is required compared with other techniques. We report a field portable time resolved Raman sensor for the detection of concealed chemical hazards in opaque containers. The new sensor uses a pulsed nanosecond laser source in conjunction with an intensified CCD detector. The new sensor employs a combination of time and space resolved Raman spectroscopy to enhance the detection capability. The new sensor can identify concealed hazards by a single measurement without any chemometric data treatments.

Volume estimation from multiplanar 2D ultrasound images using a remote electromagnetic position and orientation sensor

A system is described for calculating volume from a sequence of multiplanar 2D ultrasound images. Ultrasound images are captured using a video digitising card (Hauppauge Win/TV card) installed in a personal computer, and regions of interest transformed into 3D space using position and orientation data obtained from an electromagnetic device (Polbemus, Fastrak). The accuracy of the system was assessed by scanning 10 water filled balloons (13-141 ml), 10 kidneys (147  200 ml) and 16 fetal livers (8  37 ml) in water using an Acuson 128XP/10 (5 MHz curvilinear probe). Volume was calculated using the ellipsoid, planimetry, tetrahedral and ray tracing methods and compared with the actual volume measured by weighing (balloons) and water displacement (kidneys and livers). The mean percentage error for the ray tracing method was 0.9 ± 2.4%, 2.7 ± 2.3%, 6.6 ± 5.4% for balloons, kidneys and livers, respectively. So far the system has been used clinically to scan fetal livers and lungs, neonate brain ventricles and adult prostate glands.

Reliability of clinical measurement for assessing spinal fusion: An experimental sheep study

Study Design. A sheep study designed to compare the accuracy of static radiographs, dynamic radiographs, and computed tomographic (CT) scans for the assessment of thoracolumbar facet joint fusion as determined by micro-CT scanning. Objective. To determine the accuracy and reliability of conventional imaging techniques in identifying the status of thoracolumbar (T13-L1) facet joint fusion in a sheep model. Summary of Background Data. Plain radiographs are commonly used to determine the integrity of surgical arthrodesis of the thoracolumbar spine. Many previous studies of fusion success have relied solely on postoperative assessment of plain radiographs, a technique lacking sensitivity for pseudarthrosis. CT may be a more reliable technique, but is less well characterized. Methods. Eleven adult sheep were randomized to either attempted arthrodesis using autogenous bone graft and internal fixation (n = 3) or intentional pseudarthrosis (IP) using oxidized cellulose and internal fixation (n = 8). After 6 months, facet joint fusion was assessed by independent observers, using (1) plain static radiography alone, (2) additional dynamic radiographs, and (3) additional reconstructed spiral CT imaging. These assessments were correlated with high-resolution micro-CT imaging to predict the utility of the conventional imaging techniques in the estimation of fusion success. Results. The capacity of plain radiography alone to correctly predict fusion or pseudarthrosis was 43% and was not improved using plain radiography and dynamic radiography with also a 43% accuracy. Adding assessment by reformatted CT imaging to the plain radiography techniques increased the capacity to predict fusion outcome to 86% correctly. The sensitivity, specificity, and accuracy of static radiography were 0.33, 0.55, and 0.43, respectively, those of dynamic radiography were 0.46, 0.40, and 0.43, respectively, and those of radiography plus CT were 0.88, 0.85, and 0.86, respectively. Conclusion. CT-based evaluation correlated most closely with high-resolution micro-CT imaging. Neither plain static nor dynamic radiographs were able to predict fusion outcome accurately. © 2012 Lippincott Williams & Wilkins.