Robust Web content extraction

We present an empirical evaluation and comparison of two content extraction methods in HTML: absolute XPath expressions and relative XPath expressions. We argue that the relative XPath expressions, although not widely used, should be used in preference to absolute XPath expressions in extracting content from human-created Web documents. Evaluation of robustness covers four thousand queries executed on several hundred webpages. We show that in referencing parts of real world dynamic HTML documents, relative XPath expressions are on average significantly more robust than absolute XPath ones.

The role of offsets in compensating for damage in the coastal and marine environments

This thesis examines the extent of which economic instruments can be used to minimise environmental damage in the coastal and marine environments, and the role of offsets to compensate for residual damage. Economic principles are used to review current command and control systems, potential incentive based mechanisms, and the development of appropriate offsets. Implementing offsets in the marine environment has a number of challenges, so alternative approaches may be necessary. The study finds that offsets in areas remote from the initial impact, or even to protect different species, may be acceptable provided they result in greater conservation benefits than the standard like-for-like offset. This study is particularly relevant for the design of offsets in the coastal and marine environments where there is limited scope for like-for-like offsets.

Towards the development of a low cost airborne sensing system to monitor dust particles after blasting at open-pit mine sites

Blasting is an integral part of large-scale open cut mining that often occurs in close proximity to population centers and often results in the emission of particulate material and gases potentially hazardous to health. Current air quality monitoring methods rely on limited numbers of fixed sampling locations to validate a complex fluid environment and collect sufficient data to confirm model effectiveness. This paper describes the development of a methodology to address the need of a more precise approach that is capable of characterizing blasting plumes in near-real time. The integration of the system required the modification and integration of an opto-electrical dust sensor, SHARP GP2Y10, into a small fixed-wing and multi-rotor copter, resulting in the collection of data streamed during flight. The paper also describes the calibration of the optical sensor with an industry grade dust-monitoring device, Dusttrak 8520, demonstrating a high correlation between them, with correlation coefficients (R2) greater than 0.9. The laboratory and field tests demonstrate the feasibility of coupling the sensor with the UAVs. However, further work must be done in the areas of sensor selection and calibration as well as flight planning.

A compliant, banded outflow cannula for decreased afterload sensitivity of rotary right ventricular assist devices

Biventricular support with dual rotary ventricular assist devices (VADs) has been implemented clinically with restriction of the right VAD (RVAD) outflow cannula to artificially increase afterload and, therefore, operate within recommended design speed ranges. However, the low preload and high afterload sensitivity of these devices increase the susceptibility of suction events. Active control systems are prone to sensor drift or inaccurate inferred (sensor-less) data, therefore an alternative solution may be of benefit. This study presents the in vitro evaluation of a compliant outflow cannula designed to passively decrease the afterload sensitivity of rotary RVADs and minimize left-sided suction events. A one-way fluid-structure interaction model was initially used to produce a design with suitable flow dynamics and radial deformation. The resultant geometry was cast with different initial cross-sectional restrictions and concentrations of a softening diluent before evaluation in a mock circulation loop. Pulmonary vascular resistance (PVR) was increased from 50 dyne s/cm5 until left-sided suction events occurred with each compliant cannula and a rigid, 4.5 mm diameter outflow cannula for comparison. Early suction events (PVR ∼ 300 dyne s/cm5) were observed with the rigid outflow cannula. Addition of the compliant section with an initial 3 mm diameter restriction and 10% diluent expanded the outflow restriction as PVR increased, thus increasing RVAD flow rate and preventing left-sided suction events at PVR levels beyond 1000 dyne s/cm5. Therefore, the compliant, restricted outflow cannula provided a passive control system to assist in the prevention of suction events with rotary biventricular support while maintaining pump speeds within normal ranges of operation.

Artificial Neural Network Based Automatic Emergency Landing Site Selection for UAVs and Highly Automated Aircraft

In this report an artificial neural network (ANN) based automated emergency landing site selection system for unmanned aerial vehicle (UAV) and general aviation (GA) is described. The system aims increase safety of UAV operation by emulating pilot decision making in emergency landing scenarios using an ANN to select a safe landing site from available candidates. The strength of an ANN to model complex input relationships makes it a perfect system to handle the multicriteria decision making (MCDM) process of emergency landing site selection. The ANN operates by identifying the more favorable of two landing sites when provided with an input vector derived from both landing site's parameters, the aircraft's current state and wind measurements. The system consists of a feed forward ANN, a pre-processor class which produces ANN input vectors and a class in charge of creating a ranking of landing site candidates using the ANN. The system was successfully implemented in C++ using the FANN C++ library and ROS. Results obtained from ANN training and simulations using randomly generated landing sites by a site detection simulator data verify the feasibility of an ANN based automated emergency landing site selection system.

From vision to actions: Towards adaptive and autonomous humanoid robots

Although robotics research has seen advances over the last decades robots are still not in widespread use outside industrial applications. Yet a range of proposed scenarios have robots working together, helping and coexisting with humans in daily life. In all these a clear need to deal with a more unstructured, changing environment arises. I herein present a system that aims to overcome the limitations of highly complex robotic systems, in terms of autonomy and adaptation. The main focus of research is to investigate the use of visual feedback for improving reaching and grasping capabilities of complex robots. To facilitate this a combined integration of computer vision and machine learning techniques is employed. From a robot vision point of view the combination of domain knowledge from both imaging processing and machine learning techniques, can expand the capabilities of robots. I present a novel framework called Cartesian Genetic Programming for Image Processing (CGP-IP). CGP-IP can be trained to detect objects in the incoming camera streams and successfully demonstrated on many different problem domains. The approach requires only a few training images (it was tested with 5 to 10 images per experiment) is fast, scalable and robust yet requires very small training sets. Additionally, it can generate human readable programs that can be further customized and tuned. While CGP-IP is a supervised-learning technique, I show an integration on the iCub, that allows for the autonomous learning of object detection and identification. Finally this dissertation includes two proof-of-concepts that integrate the motion and action sides. First, reactive reaching and grasping is shown. It allows the robot to avoid obstacles detected in the visual stream, while reaching for the intended target object. Furthermore the integration enables us to use the robot in non-static environments, i.e. the reaching is adapted on-the- fly from the visual feedback received, e.g. when an obstacle is moved into the trajectory. The second integration highlights the capabilities of these frameworks, by improving the visual detection by performing object manipulation actions.

Evaluation of Two MCDM Methods for UAV Emergency Landing

One of the major impediments for the use of UAVs in civilian environment is the capability to replicate some of the functionality of safe manned aircraft operations. One critical aspect is emergency landing. Once the possible landing sites have been rated, a decision on the most suitable choice to land is required. This is a multi-criteria decision making (MCDM) problem which needs to take into account various factors in its selection of landing site. This report summarises relevant literature in MCDM in the context of emergency forced landing and proposes and compares two algorithms and methods for this task.

Variable Size Population NSGA-II: VPNSGA-II

Multi-objective optimization is an active field of research with broad applicability in aeronautics. This report details a variant of the original NSGA-II software aimed to improve the performances of such a widely used Genetic Algorithm in finding the optimal Pareto-front of a Multi-Objective optimization problem for the use of UAV and aircraft design and optimsaiton. Original NSGA-II works on a population of predetermined constant size and its computational cost to evaluate one generation is O(mn^2 ), being m the number of objective functions and n the population size. The basic idea encouraging this work is that of reduce the computational cost of the NSGA-II algorithm by making it work on a population of variable size, in order to obtain better convergence towards the Pareto-front in less time. In this work some test functions will be tested with both original NSGA-II and VPNSGA-II algorithms; each test will be timed in order to get a measure of the computational cost of each trial and the results will be compared.

Hybrid game strategies for MO problems in aerospace design

Game strategies have been developed in past decades and used in the field of economics, engineering, computer science and biology due to their efficiency in solving design optimisation problems. In addition, research on Multi-Objective (MO) and Multidisciplinary Design Optimisation (MDO) has focused on developing robust and efficient optimisation method to produce quality solutions with less computational time. In this paper, a new optimisation method Hybrid Game Strategy for MO problems is introduced and compared to CMA-ES based optimisation approach. Numerical results obtained from both optimisation methods are compared in terms of computational expense and model quality. The benefits of using Game-strategies are demonstrated.

Reasoning about natural language phrases for semantic goal driven exploration

This paper presents a symbolic navigation system that uses spatial language descriptions to inform goal-directed exploration in unfamiliar office environments. An abstract map is created from a collection of natural language phrases describing the spatial layout of the environment. The spatial representation in the abstract map is controlled by a constraint based interpretation of each natural language phrase. In goal-directed exploration of an unseen office environment, the robot links the information in the abstract map to observed symbolic information and its grounded world representation. This paper demonstrates the ability of the system, in both simulated and real-world trials, to efficiently find target rooms in environments that it has never been to previously. In three unexplored environments, it is shown that on average the system travels only 8.42% further than the optimal path when using only natural language phrases to complete navigation tasks.

Enhancing human action recognition with region proposals

Deep convolutional network models have dominated recent work in human action recognition as well as image classification. However, these methods are often unduly influenced by the image background, learning and exploiting the presence of cues in typical computer vision datasets. For unbiased robotics applications, the degree of variation and novelty in action backgrounds is far greater than in computer vision datasets. To address this challenge, we propose an “action region proposal” method that, informed by optical flow, extracts image regions likely to contain actions for input into the network both during training and testing. In a range of experiments, we demonstrate that manually segmenting the background is not enough; but through active action region proposals during training and testing, state-of-the-art or better performance can be achieved on individual spatial and temporal video components. Finally, we show by focusing attention through action region proposals, we can further improve upon the existing state-of-the-art in spatio-temporally fused action recognition performance.

Heat-Capacity Measurements - Progress In Experimental-Techniques

The heat capacity of a substance is related to the structure and constitution of the material and its measurement is a standard technique of physical investigation. In this review, the classical methods are first analyzed briefly and their recent extensions are summarized. The merits and demerits of these methods are pointed out. The newer techniques such as the a.c. method, the relaxation method, the pulse methods, the laser flash calorimetry and other methods developed to extend the heat capacity measurements to newer classes of materials and to extreme conditions of sample geometry, pressure and temperature are comprehensively reviewed. Examples of recent work and details of the experimental systems are provided for each method. The introduction of automation in control systems for the monitoring of the experiments and for data processing is also discussed. Two hundred and eight references and 18 figures are used to illustrate the various techniques.

Autonomous UAVs wildlife detection using thermal imaging, predictive navigation and computer vision

There is an increased interest on the use of Unmanned Aerial Vehicles (UAVs) for wildlife and feral animal monitoring around the world. This paper describes a novel system which uses a predictive dynamic application that places the UAV ahead of a user, with a low cost thermal camera, a small onboard computer that identifies heat signatures of a target animal from a predetermined altitude and transmits that target’s GPS coordinates. A map is generated and various data sets and graphs are displayed using a GUI designed for easy use. The paper describes the hardware and software architecture and the probabilistic model for downward facing camera for the detection of an animal. Behavioral dynamics of target movement for the design of a Kalman filter and Markov model based prediction algorithm are used to place the UAV ahead of the user. Geometrical concepts and Haversine formula are applied to the maximum likelihood case in order to make a prediction regarding a future state of the user, thus delivering a new way point for autonomous navigation. Results show that the system is capable of autonomously locating animals from a predetermined height and generate a map showing the location of the animals ahead of the user.

Design and flight testing of a bio-inspired plume tracking algorithm for unmanned serial vehicles

There is an increased interest on the use of UAVs for environmental research such as tracking bush fires, volcanic eruptions, chemical accidents or pollution sources. The aim of this paper is to describe the theory and results of a bio-inspired plume tracking algorithm. A method for generating sparse plumes in a virtual environment was also developed. Results indicated the ability of the algorithms to track plumes in 2D and 3D. The system has been tested with hardware in the loop (HIL) simulations and in flight using a CO2 gas sensor mounted to a multi-rotor UAV. The UAV is controlled by the plume tracking algorithm running on the ground control station (GCS).

MPC controlled multirotor with suspended slung load: System architecture and visual load detection

There is an increased interest in the use of Unmanned Aerial Vehicles for load transportation from environmental remote sensing to construction and parcel delivery. One of the main challenges is accurate control of the load position and trajectory. This paper presents an assessment of real flight trials for the control of an autonomous multi-rotor with a suspended slung load using only visual feedback to determine the load position. This method uses an onboard camera to take advantage of a common visual marker detection algorithm to robustly detect the load location. The load position is calculated using an onboard processor, and transmitted over a wireless network to a ground station integrating MATLAB/SIMULINK and Robotic Operating System (ROS) and a Model Predictive Controller (MPC) to control both the load and the UAV. To evaluate the system performance, the position of the load determined by the visual detection system in real flight is compared with data received by a motion tracking system. The multi-rotor position tracking performance is also analyzed by conducting flight trials using perfect load position data and data obtained only from the visual system. Results show very accurate estimation of the load position (~5% Offset) using only the visual system and demonstrate that the need for an external motion tracking system is not needed for this task.