A direct adaptive neural command controller design for an unstable helicopter

This paper presents an off-line (finite time interval) and on-line learning direct adaptive neural controller for an unstable helicopter. The neural controller is designed to track pitch rate command signal generated using the reference model. A helicopter having a soft inplane four-bladed hingeless main rotor and a four-bladed tail rotor with conventional mechanical controls is used for the simulation studies. For the simulation study, a linearized helicopter model at different straight and level flight conditions is considered. A neural network with a linear filter architecture trained using backpropagation through time is used to approximate the control law. The controller network parameters are adapted using updated rules Lyapunov synthesis. The off-line trained (for finite time interval) network provides the necessary stability and tracking performance. The on-line learning is used to adapt the network under varying flight conditions. The on-line learning ability is demonstrated through parameter uncertainties. The performance of the proposed direct adaptive neural controller (DANC) is compared with feedback error learning neural controller (FENC).

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.

Active Adaptive Gyrostabiliser Control System

A gyrostabiliser control system and method for stabilising marine vessel motion based on precession information only. The control system employs an Automatic Gain Control (AGC) precession controller (60). This system operates with a gain factor that is always being gradually minimized so as to let the gyro flywheel (12) develop as much precession as possible - the higher the precession, the higher the roll stabilising moment. This continuous gain change provides adaptation to changes in sea state and sailing conditions. The system effectively predicts the likelihood of maximum precession being reached. Should this event be detected, then the gain is rapidly increased so as to provide a breaking precession torque. Once the event has passed, the system again attempts to gradually decrease the gain.

A pattern adaptive thinning algorithm

A simple sequential thinning algorithm for peeling off pixels along contours is described. An adaptive algorithm obtained by incorporating shape adaptivity into this sequential process is also given. The distortions in the skeleton at the right-angle and acute-angle corners are minimized in the adaptive algorithm. The asymmetry of the skeleton, which is a characteristic of sequential algorithm, and is due to the presence of T-corners in some of the even-thickness pattern is eliminated. The performance (in terms of time requirements and shape preservation) is compared with that of a modern thinning algorithm.

Conceptualising the challenge of integrating digital technologies in pedagogy

The integration of digital technologies in pedagogy is positioned as an important change in education, but widespread innovative use of digital technologies is yet to be truly realised. The gap between the potential and the reality of digital technology integration is commonly attributed to a range of challenging extrinsic and intrinsic influences. Activity Theory (Engeström, 2009) is used to analyse challenges created by extrinsic influences (Nielsen, Miller, & Hoban, 2012); a complementary theory is needed to conceptualise intrinsic influences. System 1 and System 2 thinking theory (Kahneman, 2011) will be advanced as a conceptual framework for understanding conscious and unconscious aspects of teacher practice, particularly the interaction between innovation and teacher routine, attitudes and beliefs. Transformative Learning Theory (Mezirow, 2009) will be positioned to comprehend the nexus of extrinsic and intrinsic influences. This paper will propose how, when faced with extrinsic and intrinsic influences on innovative practice, educators can use these theories to conceptualise the challenge of integrating digital technologies in pedagogy.

Adaptive significance of the Indian caste system: an ecological perspective

Indian society is an agglomeration of several thousand endogamous groups or castes each with a restricted geographical range and a hereditarily determine mode of subsistence. These reproductively isolated castes may be compared to biological species, and the society thought of as a biological community with each caste having its specific ecological niche. In this paper we examine the ecological-niche relationships of castes which are directly dependent on natural resources. Evidence is presented to show that castes living together in the same region had so organized their pattern of resource use as to avoid excessive intercaste competition for limiting resources. Furthermore, territorial division of the total range of the caste regulated intra-caste competition. Hence, a particular plant or animal resource in a given locality was used almost exclusively by a given lineage within a caste generation after generation. This favoured the cultural evolution of traditions ensuring sustainable use of natural resources. This must have contributed significantly to the stability of Indian caste society over several thousand years. The collapse of the base of natural resources and increasing monetarization of the economy has, however, destroyed the earlier complementarity between the different castes and led to increasing conflicts between them in recent years.

Non-stationary signal analysis by least mean fourth (LMF) adaptive algorithm

A modified least mean fourth (LMF) adaptive algorithm applicable to non-stationary signals is presented. The performance of the proposed algorithm is studied by simulation for non-stationarities in bandwidth, centre frequency and gain of a stochastic signal. These non-stationarities are in the form of linear, sinusoidal and jump variations of the parameters. The proposed LMF adaptation is found to have better parameter tracking capability than the LMS adaptation for the same speed of convergence.

Structured model-following neuro-adaptive design for attitude maneuver of rigid bodies

A new structured model-following adaptive approach is presented in this paper to achieve large attitude maneuvers of rigid bodies. First, a nominal controller is designed using the dynamic inversion philosophy. Next, a neuro- adaptive design is proposed to augment the nominal design in order to assure robust performance in the presence of parameter inaccuracies as well as unknown constant external disturbances. The structured approach proposed in this paper (where kinematic and dynamic equations are handled separately), reduces the complexity of the controller structure. From simulation studies, this adaptive controller is found to be very effective in assuring robust performance.

A global convergence criterion for discrete-time multivariable adaptive systems

The paper deals with the basic problem of adjusting a matrix gain in a discrete-time linear multivariable system. The object is to obtain a global convergence criterion, i.e. conditions under which a specified error signal asymptotically approaches zero and other signals in the system remain bounded for arbitrary initial conditions and for any bounded input to the system. It is shown that for a class of up-dating algorithms for the adjustable gain matrix, global convergence is crucially dependent on a transfer matrix G(z) which has a simple block diagram interpretation. When w(z)G(z) is strictly discrete positive real for a scalar w(z) such that w-1(z) is strictly proper with poles and zeros within the unit circle, an augmented error scheme is suggested and is proved to result in global convergence. The solution avoids feeding back a quadratic term as recommended in other schemes for single-input single-output systems.

Developments in controlled green-water larval culture technologies for estuarine fishes in Queensland, Australia and elsewhere

Since 1989, researchers with the Department of Primary Industries and Fisheries (DPI&F) in Queensland, Australia, have successfully used controlled low-water exchange green-water cultures to rear the larvae of estuarine fishes and crustaceans through to metamorphosis. High survivals and excellent fry condition have been achieved for several commercially important endemic species produced for various projects. They include barramundi or sea bass, Lates calcarifer, Australian bass, Macquaria novemaculeata, dusky flathead, Platycephalus fuscus, sand whiting, Sillago ciliata, red sea bream or snapper, Pagrus auratus, banana prawn, Fenneropenaeus merguiensis, and others. The consistent success of our standardised and relatively simple approach at different localities has led to it being incorporated into general fingerling production practices at several establishments in Australia. Although post-metamorphosis rearing methods have differed for each species investigated, due to various biological and behavioural traits and project requirements, these larval rearing methods have been successful with few species-specific modifications. Initially modelled on the Taiwanese approach to rearing Penaeids in aerated low-water exchange cultures, the approach similarly appears to rely on a beneficial assemblage of micro-organisms. Conceptually, these micro-organisms may include a mixture of the air-borne primary invaders of pure phytoplankton cultures when exposed to outdoor conditions. Whilst this would vary with different sites, our experiences with these methods have consistently been favourable. Mass microalgal cultures with eco-physiological youth are used to regularly augment larval fish cultures so that rearing conditions simulate an exponential growth-phase microalgal bloom. Moderate to heavy aeration prevents settlement of particulate matter and encourages aerobic bacterial decomposition of wastes. The green-water larval rearing approach described herein has demonstrated high practical utility in research and commercial applications, and has greatly simplified marine finfish hatchery operations whilst generally lifting production capacities for metamorphosed fry in Australia. Its potential uses in areas of aquaculture other than larviculture are also discussed.

An adaptive power-system stabiliser which cancels the negative damping torque of a synchronous generator

The paper presents a new criterion for designing a power-system stabiliser, which is that it should cancel the negative damping torque inherent in a synchronous generator and automatic voltage regulator. The method arises from analysis based on the properties of tensor invariance, but it is easily implemented, and leads to the design of an adaptive controller. Extensive computations and simulation have been performed, and laboratory tests have been conducted on a computer-controlled micromachine system. Results are presented illustrating the effectiveness of the adaptive stabiliser.

Invited paper Application of the least mean fourth (LMF) adaptive algorithm to signals associated with gaussian noise

This paper considers the applicability of the least mean fourth (LM F) power gradient adaptation criteria with 'advantage' for signals associated with gaussian noise, the associated noise power estimate not being known. The proposed method, as an adaptive spectral estimator, is found to provide superior performance than the least mean square (LMS) adaptation for the same (or even lower) speed of convergence for signals having sufficiently high signal-to-gaussian noise ratio. The results include comparison of the performance of the LMS-tapped delay line, LMF-tapped delay line, LMS-lattice and LMF-lattice algorithms, with the Burg's block data method as reference. The signals, like sinusoids with noise and stochastic signals like EEG, are considered in this study.

An Adaptive Scheme for Learning the Probability Threshold in Pattern Recognition

The statistical minimum risk pattern recognition problem, when the classification costs are random variables of unknown statistics, is considered. Using medical diagnosis as a possible application, the problem of learning the optimal decision scheme is studied for a two-class twoaction case, as a first step. This reduces to the problem of learning the optimum threshold (for taking appropriate action) on the a posteriori probability of one class. A recursive procedure for updating an estimate of the threshold is proposed. The estimation procedure does not require the knowledge of actual class labels of the sample patterns in the design set. The adaptive scheme of using the present threshold estimate for taking action on the next sample is shown to converge, in probability, to the optimum. The results of a computer simulation study of three learning schemes demonstrate the theoretically predictable salient features of the adaptive scheme.

Spectral Sensing for Cognitive Radio: Estimation of Adaptive Frequency Hopping Signal

The issue of dynamic spectrum scene analysis in any cognitive radio network becomes extremely complex when low probability of intercept, spread spectrum systems are present in environment. The detection and estimation become more complex if frequency hopping spread spectrum is adaptive in nature. In this paper, we propose two phase approach for detection and estimation of frequency hoping signals. Polyphase filter bank has been proposed as the architecture of choice for detection phase to efficiently detect the presence of frequency hopping signal. Based on the modeling of frequency hopping signal it can be shown that parametric methods of line spectral analysis are well suited for estimation of frequency hopping signals if the issues of order estimation and time localization are resolved. An algorithm using line spectra parameter estimation and wavelet based transient detection has been proposed which resolves above issues in computationally efficient manner suitable for implementation in cognitive radio. The simulations show promising results proving that adaptive frequency hopping signals can be detected and demodulated in a non cooperative context, even at a very low signal to noise ratio in real time.

Black Sigatoka disease: new technologies to strengthen eradication strategies in Australia

In 2001, an incursion of Mycosphaerella fijiensis, the causal agent of black Sigatoka, was detected in Australia's largest commercial banana growing region, the Tully Banana Production Area in North Queensland. An intensive surveillance and eradication campaign was undertaken which resulted in the reinstatement of the disease-free status for black Sigatoka in 2005. This was the first time black Sigatoka had ever been eradicated from commercial plantations. The success of the eradication campaign was testament to good working relationships between scientists, growers, crop monitors, quarantine regulatory bodies and industry. A key contributing factor to the success was the deployment of a PCR-based molecular diagnostic assay, developed by the Cooperative Research Centre for Tropical Plant Protection (CRCTPP). This assay complemented morphological identification and allowed high throughput diagnosis of samples facilitating rapid decision-making during the eradication campaign. This paper describes the development and successful deployment of molecular diagnostics for black Sigatoka. Shortcomings in the gel-based assay are discussed and the advantages of highly specific real-time PCR assays, capable of differentiating between Mycosphaerella fijiensis, Mycosphaerella musicola and Mycosphaerella eumusae are outlined. Real-time assays may provide a powerful diagnostic tool for applications in surveillance, disease forecasting and resistance testing for Sigatoka leaf spot diseases.