Engineering Commons^™

Application Of Advanced Algorithms And Statistical Techniques For Weed-Plant Discrimination, Saman Akbar Zadeh

Theses: Doctorates and Masters

Precision agriculture requires automated systems for weed detection as weeds compete with the crop for water, nutrients, and light. The purpose of this study is to investigate the use of machine learning methods to classify weeds/crops in agriculture. Statistical methods, support vector machines, convolutional neural networks (CNNs) are introduced, investigated and optimized as classifiers to provide high accuracy at high vehicular speed for weed detection.

Initially, Support Vector Machine (SVM) algorithms are developed for weed-crop discrimination and their accuracies are compared with a conventional data-aggregation method based on the evaluation of discrete Normalised Difference Vegetation Indices (NDVIs) at two different …

Real-Time Classification Of Multivariate Olfaction Data Using Spiking Neural Networks, Arnup Vanarse, Adam Osseiran, Alexander Rassau, Therese O'Sullivan, Jonny Lo, Amanda Devine

Research outputs 2014 to 2021

Recent studies in bioinspired artificial olfaction, especially those detailing the application of spike-based neuromorphic methods, have led to promising developments towards overcoming the limitations of traditional approaches, such as complexity in handling multivariate data, computational and power requirements, poor accuracy, and substantial delay for processing and classification of odors. Rank-order-based olfactory systems provide an interesting approach for detection of target gases by encoding multi-variate data generated by artificial olfactory systems into temporal signatures. However, the utilization of traditional pattern-matching methods and unpredictable shuffling of spikes in the rank-order impedes the performance of the system. In this paper, we present an …

A Hardware-Deployable Neuromorphic Solution For Encoding And Classification Of Electronic Nose Data, Anup Vanarse, Alexander Rassau, Peter Van Der Made

Research outputs 2014 to 2021

In several application domains, electronic nose systems employing conventional data processing approaches incur substantial power and computational costs and limitations, such as significant latency and poor accuracy for classification. Recent developments in spike-based bio-inspired approaches have delivered solutions for the highly accurate classification of multivariate sensor data with minimized computational and power requirements. Although these methods have addressed issues related to efficient data processing and classification accuracy, other areas, such as reducing the processing latency to support real-time application and deploying spike-based solutions on supported hardware, have yet to be studied in detail. Through this investigation, we proposed a spiking …

Effective Plant Discrimination Based On The Combination Of Local Binary Pattern Operators And Multiclass Support Vector Machine Methods, Vi N T Le, Beniamin Apopei, Kamal Alameh

Research outputs 2014 to 2021

Accurate crop and weed discrimination plays a critical role in addressing the challenges of weed management in agriculture. The use of herbicides is currently the most common approach to weed control. However, herbicide resistant plants have long been recognised as a major concern due to the excessive use of herbicides. Effective weed detection techniques can reduce the cost of weed management and improve crop quality and yield. A computationally efficient and robust plant classification algorithm is developed and applied to the classification of three crops: Brassica napus (canola), Zea mays (maize/corn), and radish. The developed algorithm is based on the …

Review Of Deep Learning Methods In Robotic Grasp Detection, Shehan Caldera, Alexander Rassau, Douglas Chai

Research outputs 2014 to 2021

For robots to attain more general-purpose utility, grasping is a necessary skill to master. Such general-purpose robots may use their perception abilities to visually identify grasps for a given object. A grasp describes how a robotic end-effector can be arranged to securely grab an object and successfully lift it without slippage. Traditionally, grasp detection requires expert human knowledge to analytically form the task-specific algorithm, but this is an arduous and time-consuming approach. During the last five years, deep learning methods have enabled significant advancements in robotic vision, natural language processing, and automated driving applications. The successful results of these methods …

Investigation On The Mobile Robot Navigation In An Unknown Environment, Ahmed S. Khusheef

Theses: Doctorates and Masters

Mobile robots could be used to search, find, and relocate objects in many types of manufacturing operations and environments. In this scenario, the target objects might reside with equal probability at any location in the environment and, therefore, the robot must navigate and search the whole area autonomously, and be equipped with specific sensors to detect objects. Novel challenges exist in developing a control system, which helps a mobile robot achieve such tasks, including constructing enhanced systems for navigation, and vision-based object recognition. The latter is important for undertaking the exploration task that requires an optimal object recognition technique.

In …

Terminal Sliding Mode Control For Rigid Robotic Manipulators With Uncertain Dynamics, Nicola Ritter

Theses: Doctorates and Masters

This thesis presents two new adaptive control laws that use the terminal sliding mode technique for the tracking problem of rigid robotic manipulators with non-linearities, dynamic couplings and uncertain parameters. The first law provides a robust scheme which uses several properties of rigid robotic mauipulators and adaptively adjusts seven uncertain parameter bounds. The law ensures finite time error convergence to the system origin and is simple to implement The second law treats the manipulator as a partially known system. The known dynamics are used to build a nominal control law and the effects of unknown system dynamics arc compensated for …

Robust Decentralised Variable Structure Control For Rigid Robotic Manipulators, Thasapalan Kuhan

Theses : Honours

In this thesis, the problem of robust variable structure control for non-linear rigid robotic manipulators is investigated. Robustness and convergence results are presented for variable structure control systems of robotic manipulators with bounded unknown disturbances, nonlinearities, dynamical couplings and parameter uncertainties. The major outcomes of the work described in this thesis are summarised as given below. The basic variable structure theory is surveyed, and some basic ideas such as sliding mode designs, robustness analysis and control1er design methods for linear or non-linear systems are reviewed. Three recent variable structure control schemes for robotic manipulators are discussed and compared to highlight …