Grounding human vocabulary in robot perception through interaction

This thesis addresses the problem of word learning in computational agents. The motivation behind this work lies in the need to support language-based communication between service robots and their human users, as well as grounded reasoning using symbols relevant for the assigned tasks. The research focuses on the problem of grounding human vocabulary in robotic agent’s sensori-motor perception. Words have to be grounded in bodily experiences, which emphasizes the role of appropriate embodiments. On the other hand, language is a cultural product created and acquired through social interactions. This emphasizes the role of society as a source of linguistic input. Taking these aspects into account, an experimental scenario is set up where a human instructor teaches a robotic agent the names of the objects present in a visually shared environment. The agent grounds the names of these objects in visual perception. Word learning is an open-ended problem. Therefore, the learning architecture of the agent will have to be able to acquire words and categories in an openended manner. In this work, four learning architectures were designed that can be used by robotic agents for long-term and open-ended word and category acquisition. The learning methods used in these architectures are designed for incrementally scaling-up to larger sets of words and categories. A novel experimental evaluation methodology, that takes into account the openended nature of word learning, is proposed and applied. This methodology is based on the realization that a robot’s vocabulary will be limited by its discriminatory capacity which, in turn, depends on its sensors and perceptual capabilities. An extensive set of systematic experiments, in multiple experimental settings, was carried out to thoroughly evaluate the described learning approaches. The results indicate that all approaches were able to incrementally acquire new words and categories. Although some of the approaches could not scale-up to larger vocabularies, one approach was shown to learn up to 293 categories, with potential for learning many more.

On the application of optimal control techniques in lossy fieldbuses

The performance of real-time networks is under continuous improvement as a result of several trends in the digital world. However, these tendencies not only cause improvements, but also exacerbates a series of unideal aspects of real-time networks such as communication latency, jitter of the latency and packet drop rate. This Thesis focuses on the communication errors that appear on such realtime networks, from the point-of-view of automatic control. Specifically, it investigates the effects of packet drops in automatic control over fieldbuses, as well as the architectures and optimal techniques for their compensation. Firstly, a new approach to address the problems that rise in virtue of such packet drops, is proposed. This novel approach is based on the simultaneous transmission of several values in a single message. Such messages can be from sensor to controller, in which case they are comprised of several past sensor readings, or from controller to actuator in which case they are comprised of estimates of several future control values. A series of tests reveal the advantages of this approach. The above-explained approach is then expanded as to accommodate the techniques of contemporary optimal control. However, unlike the aforementioned approach, that deliberately does not send certain messages in order to make a more efficient use of network resources; in the second case, the techniques are used to reduce the effects of packet losses. After these two approaches that are based on data aggregation, it is also studied the optimal control in packet dropping fieldbuses, using generalized actuator output functions. This study ends with the development of a new optimal controller, as well as the function, among the generalized functions that dictate the actuator’s behaviour in the absence of a new control message, that leads to the optimal performance. The Thesis also presents a different line of research, related with the output oscillations that take place as a consequence of the use of classic co-design techniques of networked control. The proposed algorithm has the goal of allowing the execution of such classical co-design algorithms without causing an output oscillation that increases the value of the cost function. Such increases may, under certain circumstances, negate the advantages of the application of the classical co-design techniques. A yet another line of research, investigated algorithms, more efficient than contemporary ones, to generate task execution sequences that guarantee that at least a given number of activated jobs will be executed out of every set composed by a predetermined number of contiguous activations. This algorithm may, in the future, be applied to the generation of message transmission patterns in the above-mentioned techniques for the efficient use of network resources. The proposed task generation algorithm is better than its predecessors in the sense that it is capable of scheduling systems that cannot be scheduled by its predecessor algorithms. The Thesis also presents a mechanism that allows to perform multi-path routing in wireless sensor networks, while ensuring that no value will be counted in duplicate. Thereby, this technique improves the performance of wireless sensor networks, rendering them more suitable for control applications. As mentioned before, this Thesis is centered around techniques for the improvement of performance of distributed control systems in which several elements are connected through a fieldbus that may be subject to packet drops. The first three approaches are directly related to this topic, with the first two approaching the problem from an architectural standpoint, whereas the third one does so from more theoretical grounds. The fourth approach ensures that the approaches to this and similar problems that can be found in the literature that try to achieve goals similar to objectives of this Thesis, can do so without causing other problems that may invalidate the solutions in question. Then, the thesis presents an approach to the problem dealt with in it, which is centered in the efficient generation of the transmission patterns that are used in the aforementioned approaches.

Microbe-mediated recovery of salt marshes contaminated with oil hydrocarbons

Salt marshes are highly productive intertidal habitats that serve as nursery grounds for many commercially and economically important species. Because of their location and physical and biological characteristics, salt marshes are considered to be particularly vulnerable to anthropogenic inputs of oil hydrocarbons. Sediment contamination with oil is especially dangerous for salt marsh vegetation, since low molecular weight aromatic hydrocarbons can affect plants at all stages of development. However, the use of vegetation for bioremediation (phytoremediation), by removal or sequestration of contaminants, has been intensively studied. Phytoremediation is an efficient, inexpensive and environmental friendly approach for the removal of aromatic hydrocarbons, through direct incorporation by the plant and by the intervention of degrading microbial populations in the rhizosphere (microbe-assisted phytoremediation). Rhizosphere microbial communities are enriched in important catabolic genotypes for degradation of oil hydrocarbons (OH) which may have a potential for detoxification of the sediment surrounding the roots. In addition, since rhizosphere bacterial populations may also internalize into plant tissues (endophytes), rhizocompetent AH degrading populations may be important for in planta AH degradation and detoxification. The present study involved field work and microcosms experiments aiming the characterization of relevant plant-microbe interactions in oilimpacted salt marshes and the understanding of the effect of rhizosphere and endosphere bacteria in the role of salt marsh plants as potential phytoremediation agents. In the field approach, molecular tools were used to assess how plant species- and OH pollution affect sediment bacterial composition [bulk sediment and sediment surrounding the roots (rhizosphere) of Halimione portulacoides and Sarcocornia perennis subsp. perennis] in a temperate estuary (Ria de Aveiro, Portugal) chronically exposed to OH pollution. In addition, the 16S rRNA gene sequences retrieved in this study were used to generate in silico metagenomes and to evaluate the distribution of potential bacterial traits in different microhabitats. Moreover, a combination of culture-dependent and -independent approaches was used to investigate the effect of oil hydrocarbons contamination on the structure and function of endophytic bacterial communities of salt marsh plants.Root systems of H. portulacoides and S. perennis subsp. perennis appear to be able to exert a strong influence on bacterial composition and in silico metagenome analysis showed enrichment of genes involved in the process of polycyclic aromatic hydrocarbon (PAH) degradation in the rhizosphere of halophyte plants. The culturable fraction of endophytic degraders was essentially closely related to known OH-degrading Pseudomonas species and endophytic communities revealed sitespecific effects related to the level of OH contamination in the sediment. In order to determine the effects of oil contamination on plant condition and on the responses in terms of structure and function of the bacterial community associated with plant roots (rhizosphere, endosphere), a microcosms approach was set up. The salt marsh plant Halimione portulacoides was inoculated with a previous isolated Pseudomonas sp. endophytic degrader and the 2-methylnaphthalene was used as model PAH contaminant. The results showed that H. portulacoides health and growth were not affected by the contamination with the tested concentration. Moreover, the decrease of 2-methylnaphthalene at the end of experiment, can suggest that H. portulacoides can be considered as a potential plant for future uses in phytoremedition approaches of contaminated salt marsh. The acceleration of hydrocarbon degradation by inoculation of the plants with the hydrocarbon-degrading Pseudomonas sp. could not, however, be demonstrated, although the effects of inoculation on the structure of the endophytic community observed at the end of the experiment indicate that the strain may be an efficient colonizer of H. portulacoides roots. The results obtained in this work suggest that H. portulacoides tolerates moderate concentrations of 2-methylnaphthalene and can be regarded as a promising agent for phytoremedition approaches in salt marshes contaminated with oil hydrocarbons. Plant/microbe interactions may have an important role in the degradation process, as plants support a diverse endophytic bacterial community, enriched in genetic factors (genes and plasmids) for hydrocarbon degradation.