Science drives horticulture's progress and profit

Horticultural science linked with basic studies in biology, chemistry, physics and engineering has laid the foundation for advances in applied knowledge which are at the heart of commercial, environmental and social horticulture. In few disciplines is science more rapidly translated into applicable technologies than in the huge range of man’s activities embraced within horticulture which are discussed in this Trilogy. This chapter surveys the origins of horticultural science developing as an integral part of the 16th century “Scientific Revolution”. It identifies early discoveries during the latter part of the 19th and early 20th centuries which rationalized the control of plant growth, flowering and fruiting and the media in which crops could be cultivated. The products of these discoveries formed the basis on which huge current industries of worldwide significance are founded in fruit, vegetable and ornamental production. More recent examples of the application of horticultural science are used in an explanation of how the integration of plant breeding, crop selection and astute marketing highlighted by the New Zealand industry have retained and expanded the viability of production which supplies huge volumes of fruit into the world’s markets. This is followed by an examination of science applied to tissue and cell culture as an example of technologies which have already produced massive industrial applications but hold the prospect for generating even greater advances in the future. Finally, examples are given of nascent scientific discoveries which hold the prospect for generating horticultural industries with considerable future impact. These include systems modeling and biology, nanotechnology, robotics, automation and electronics, genetics and plant breeding, and more efficient and effective use of resources and the employment of benign microbes. In conclusion there is an estimation of the value of horticultural science to society.

A Floating-point Extended Kalman Filter Implementation for Autonomous Mobile Robots

Localization and Mapping are two of the most important capabilities for autonomous mobile robots and have been receiving considerable attention from the scientific computing community over the last 10 years. One of the most efficient methods to address these problems is based on the use of the Extended Kalman Filter (EKF). The EKF simultaneously estimates a model of the environment (map) and the position of the robot based on odometric and exteroceptive sensor information. As this algorithm demands a considerable amount of computation, it is usually executed on high end PCs coupled to the robot. In this work we present an FPGA-based architecture for the EKF algorithm that is capable of processing two-dimensional maps containing up to 1.8 k features at real time (14 Hz), a three-fold improvement over a Pentium M 1.6 GHz, and a 13-fold improvement over an ARM920T 200 MHz. The proposed architecture also consumes only 1.3% of the Pentium and 12.3% of the ARM energy per feature.

A Parallel Hardware Architecture for Scale and Rotation Invariant Feature Detection

This paper proposes a parallel hardware architecture for image feature detection based on the Scale Invariant Feature Transform algorithm and applied to the Simultaneous Localization And Mapping problem. The work also proposes specific hardware optimizations considered fundamental to embed such a robotic control system on-a-chip. The proposed architecture is completely stand-alone; it reads the input data directly from a CMOS image sensor and provides the results via a field-programmable gate array coupled to an embedded processor. The results may either be used directly in an on-chip application or accessed through an Ethernet connection. The system is able to detect features up to 30 frames per second (320 x 240 pixels) and has accuracy similar to a PC-based implementation. The achieved system performance is at least one order of magnitude better than a PC-based solution, a result achieved by investigating the impact of several hardware-orientated optimizations oil performance, area and accuracy.

Semantic mapping using mobile robots

Robotic mapping is the process of automatically constructing an environment representation using mobile robots. We address the problem of semantic mapping, which consists of using mobile robots to create maps that represent not only metric occupancy but also other properties of the environment. Specifically, we develop techniques to build maps that represent activity and navigability of the environment. Our approach to semantic mapping is to combine machine learning techniques with standard mapping algorithms. Supervised learning methods are used to automatically associate properties of space to the desired classification patterns. We present two methods, the first based on hidden Markov models and the second on support vector machines. Both approaches have been tested and experimentally validated in two problem domains: terrain mapping and activity-based mapping.

A Road Following Approach Using Artificial Neural Networks Combinations

Navigation is a broad topic that has been receiving considerable attention from the mobile robotic community over the years. In order to execute autonomous driving in outdoor urban environments it is necessary to identify parts of the terrain that can be traversed and parts that should be avoided. This paper describes an analyses of terrain identification based on different visual information using a MLP artificial neural network and combining responses of many classifiers. Experimental tests using a vehicle and a video camera have been conducted in real scenarios to evaluate the proposed approach.

Cross-situational learning of object-word mapping using Neural Modeling Fields

The issue of how children learn the meaning of words is fundamental to developmental psychology. The recent attempts to develop or evolve efficient communication protocols among interacting robots or Virtual agents have brought that issue to a central place in more applied research fields, such as computational linguistics and neural networks, as well. An attractive approach to learning an object-word mapping is the so-called cross-situational learning. This learning scenario is based on the intuitive notion that a learner can determine the meaning of a word by finding something in common across all observed uses of that word. Here we show how the deterministic Neural Modeling Fields (NMF) categorization mechanism can be used by the learner as an efficient algorithm to infer the correct object-word mapping. To achieve that we first reduce the original on-line learning problem to a batch learning problem where the inputs to the NMF mechanism are all possible object-word associations that Could be inferred from the cross-situational learning scenario. Since many of those associations are incorrect, they are considered as clutter or noise and discarded automatically by a clutter detector model included in our NMF implementation. With these two key ingredients - batch learning and clutter detection - the NMF mechanism was capable to infer perfectly the correct object-word mapping. (C) 2009 Elsevier Ltd. All rights reserved.

Modular Product Verifications Based on Design for Assembly

The desire to conquer markets through advanced product design and trendy business strategies are still predominant approaches in industry today. In fact, product development has acquired an ever more central role in the strategic planning of companies, and it has extended its influence to R&D funding levels as well. It is not surprising that many national R&D project frameworks within the EU today are dominated by product development topics, leaving production engineering, robotics, and systems on the sidelines. The reasons may be many but, unfortunately, the link between product development and the production processes they cater for are seldom treated in depth. The issue dealt with in this article relates to how product development is applied in order to attain the required production quality levels a company may desire, as well as how one may counter assembly defects and deviations through quantifiable design approaches. It is recognized that product verifications (tests, inspections, etc.) are necessary, but the application of these tactics often result in lead-time extensions and increased costs. Modular architectures improve this by simplifying the verification of the assembled product at module level. Furthermore, since Design for Assembly (DFA) has shown the possibility to identify defective assemblies, it may be possible to detect potential assembly defects already in the product and module design phase. The intention of this paper is to discuss and describe the link between verifications of modular architectures, defects and design for assembly. The paper is based on literature and case studies; tables and diagrams are included with the intention of increasing understanding of the relation between poor designs, defects and product verifications.

Monitoring vegetation on railway embankments : supporting maintenance decisions

The national railway administrations in Scandinavia, Germany, and Austria mainly resort to manual inspections to control vegetation growth along railway embankments. Manually inspecting railways is slow and time consuming. A more worrying aspect concerns the fact that human observers are often unable to estimate the true cover of vegetation on railway embankments. Further human observers often tend to disagree with each other when more than one observer is engaged for inspection. Lack of proper techniques to identify the true cover of vegetation even result in the excess usage of herbicides; seriously harming the environment and threating the ecology. Hence work in this study has investigated aspects relevant to human variationand agreement to be able to report better inspection routines. This was studied by mainly carrying out two separate yet relevant investigations.First, thirteen observers were separately asked to estimate the vegetation cover in nine imagesacquired (in nadir view) over the railway tracks. All such estimates were compared relatively and an analysis of variance resulted in a significant difference on the observers’ cover estimates (p<0.05). Bearing in difference between the observers, a second follow-up field-study on the railway tracks was initiated and properly investigated. Two railway segments (strata) representingdifferent levels of vegetationwere carefully selected. Five sample plots (each covering an area of one-by-one meter) were randomizedfrom each stratumalong the rails from the aforementioned segments and ten images were acquired in nadir view. Further three observers (with knowledge in the railway maintenance domain) were separately asked to estimate the plant cover by visually examining theplots. Again an analysis of variance resulted in a significant difference on the observers’ cover estimates (p<0.05) confirming the result from the first investigation.The differences in observations are compared against a computer vision algorithm which detects the "true" cover of vegetation in a given image. The true cover is defined as the amount of greenish pixels in each image as detected by the computer vision algorithm. Results achieved through comparison strongly indicate that inconsistency is prevalent among the estimates reported by the observers. Hence, an automated approach reporting the use of computer vision is suggested, thus transferring the manual inspections into objective monitored inspections

Machine learning and small robot navigation

Developing successful navigation and mapping strategies is an essential part of autonomous robot research. However, hardware limitations often make for inaccurate systems. This project serves to investigate efficient alternatives to mapping an environment, by first creating a mobile robot, and then applying machine learning to the robot and controlling systems to increase the robustness of the robot system. My mapping system consists of a semi-autonomous robot drone in communication with a stationary Linux computer system. There are learning systems running on both the robot and the more powerful Linux system. The first stage of this project was devoted to designing and building an inexpensive robot. Utilizing my prior experience from independent studies in robotics, I designed a small mobile robot that was well suited for simple navigation and mapping research. When the major components of the robot base were designed, I began to implement my design. This involved physically constructing the base of the robot, as well as researching and acquiring components such as sensors. Implementing the more complex sensors became a time-consuming task, involving much research and assistance from a variety of sources. A concurrent stage of the project involved researching and experimenting with different types of machine learning systems. I finally settled on using neural networks as the machine learning system to incorporate into my project. Neural nets can be thought of as a structure of interconnected nodes, through which information filters. The type of neural net that I chose to use is a type that requires a known set of data that serves to train the net to produce the desired output. Neural nets are particularly well suited for use with robotic systems as they can handle cases that lie at the extreme edges of the training set, such as may be produced by "noisy" sensor data. Through experimenting with available neural net code, I became familiar with the code and its function, and modified it to be more generic and reusable for multiple applications of neural nets.

Ouvindo o silêncio: a construção identitária por meio da prática do mergulho scuba como consumo hedônico

This work aims to explore the context and emotions related to the experience of scuba diving as hedonic consumption, as well as to understand in which conditions the benefit arising from the regular practice of this activity impact the identity construction of the practitioner. Through in-depth interviews, data were collected from scuba divers living in the city of Rio de Janeiro, during the months of January and February of 2008. In order to obtain the expected objectives, the chosen methodology of research was qualitative, with priority of the subject and the subjectivity, using an interpretative approach for the data analysis. The research results confirm some benefits of high-risk sports practice such as flow, self-evolution and communitas. Two additional benefits are presented: the condition of alterity of the ¿underwater world¿, which attributes extraordinany meaning to scuba diving and impacts identity construction, and the scuba ¿buddy¿ practice, that helps to build-up an overall sense of trust to the other. The work is concluded with some managerial recommendations aiming the development of scuba diving industry and related tourism. These above mentioned suggestions include a new industry positioning, integrated marketing communications with specific references to alterity and flow, market segmentation, the creation of gathering spaces and a gradation scale among practitioners.

Automação e robótica nas indústrias brasileiras: um estudo exploratório

A Automação e o processo de Robotização vêm, cada vem mais, se tornando pauta nas discussões de centenas de indústrias brasileiras, onde a tendência clara e identificada é a de investimentos expressivos na melhoria de processos e produtos, por intermédio dessas tecnologias; com foco, sempre que possível, na nacionalização de equipamentos. O presente trabalho tem como objetivo avaliar o modelo proposto por Paul Kennedy (1993) com relação à tendência de Automação e Robotização nas Indústrias Mundiais, analisando o estudo realizado diante de uma economia emergente como a brasileira. Para tanto, foram pesquisadas empresas no Brasil, em diferentes segmentos industriais, o estado da arte em termos de tecnologia de automação e robótica aplicada a processos industriais, e sugerido um modelo diferente do idealizado originalmente por Kennedy. A análise do autor se baseou no teorema que, na matemática discreta, chamamos de “law of the excluded middle”, ou seja, segundo Kennedy, o Brasil estaria vivendo hoje uma migração gradual das indústrias para os países ricos. O Brasil é um exemplo de país industrializado, de economia emergente, que investe intensamente em processos automatizados, mas que não é classificado dentro do grupo desses países ricos. Através da pesquisa realizada será apresentado um novo modelo, no qual países emergentes como o Brasil têm acesso à tecnologia de ponta em automação e robótica, aplicando a mesma em seus processos industriais.

Contribution to the chemoreception capacity of juvenile Loggerhead sea turtles (Caretta caretta, L.)

Loggerhead sea turtle juveniles (Caretta caretta), pelagic stage, are found in waters of Madeira archipelago. Pelagic turtles are in the main growth phase of their life cycle and consequently higher energy needs. However, knowledge about the ecology of pelagic loggerhead sea turtles is still quite rudimentary, mainly about the mechanisms that lead them to find food in the vast ocean. Studies with other pelagic species, such as procellariiform birds, revealed that the olfactory system play an important role for the detection of feeding areas, through the detection of concentration peaks of DMS (dimethylsulfide), a scent compound that naturally exists in the marine environment and it is related to areas of high productivity. Based on the assumption that loggerhead sea turtles use a similar mechanism, behavioural experiments were conducted in order to analyze the chemoreception capacity to DMS (airborne chemoreception - theoretically responsible for the long distance detection of areas with food patches; and aquatic chemoreception - theoretically responsible for the short distance detection of preys). The first step was to observe if pelagic loggerheads demonstrate sensitivity to DMS and the second was to verify if they really use the DMS, in natural conditions, as an airborne cue to find areas where food patches might be available. Four juveniles of loggerhead sea turtles were tested in captivity and three wild turtles in the open ocean. The results of airborne chemoreception experiments in captivity revealed that one turtle clearly demonstrated sensitivity to DMS and the sea experiments confirmed this result. However, the experiments were not conclusive on the question whether the pelagic turtles actually use the DMS as an airborne cue to detect long distance food patches. In aquatic chemoreception experiments was not observed sensitivity to DMS by the three sea turtles tested. In the classical conditioning experiment, where DMS and food were given nearly at the same time revealed that after a certain period of time, the sea turtle tested did not associated the DMS stimulus with a possible food reward. The main cause of mortality of loggerhead sea turtles in Madeira waters is due to the accidental capture (bycatch) by deep pelagic longlines fishery which the target species is the black-scabbard (Aphanopus carbo) fish. Chub mackerel (Scomber japonicus) is one of the baits used in this fishery. Aquatic chemoreception experiments were conducted in order to evaluate the attractiveness of the chub mackerel for sea turtles. For the three sea turtles tested, the results showed that in 90% of the cases the sea turtles were extremely attracted by the underwater smell of this fish.

Representation of odometry errors on occupancy grids

SOUZA, Anderson A. S. ; SANTANA, André M. ; BRITTO, Ricardo S. ; GONÇALVES, Luiz Marcos G. ; MEDEIROS, Adelardo A. D. Representation of Odometry Errors on Occupancy Grids. In: INTERNATIONAL CONFERENCE ON INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS, 5., 2008, Funchal, Portugal. Proceedings... Funchal, Portugal: ICINCO, 2008.