Classifying an opponent's behaviour in robot soccer

This paper illustrates the prediction of opponent behaviour in a competitive, highly dynamic, multi-agent and partially observableenvironment, namely RoboCup small size league robot soccer. The performance is illustrated in the context of the highly successful robot soccer team, the RoboRoos. The project is broken into three tasks; classification of behaviours, modelling and prediction of behaviours and integration of the predictions into the existing planning system. A probabilistic approach is taken to dealing with the uncertainty in the observations and with representing the uncertainty in the prediction of the behaviours. Results are shown for a classification system using a Naïve Bayesian Network that determines the opponent’s current behaviour. These results are compared to an expert designed fuzzy behaviour classification system. The paper illustrates how the modelling system will use the information from behaviour classification to produce probability distributions that model the manner with which the opponents perform their behaviours. These probability distributions are show to match well with the existing multi-agent planning system (MAPS) that forms the core of the RoboRoos system.

Achieving cooperation in a distributed multi-robot team

DMAPS (Distributed Multi-Agent Planning System) is a planning system developed for distributed multi-robot teams based on MAPS(Multi-Agent Planning System). MAPS assumes that each agent has the same global view of the environment in order to determine the most suitable actions. This assumption fails when perception is local to the agents: each agent has only a partial and unique view of the environment. DMAPS addresses this problem by creating a probabilistic global view on each agent by fusing the perceptual information from each robot. The experimental results on consuming tasks show that while the probabilistic global view is not identical on each robot, the shared view is still effective in increasing performance of the team.

Highly integrated and automated high-speed grinding system for printer heads constructed by combination materials

The fabrication of heavy-duty printer heads involves a great deal of grinding work. Previously in the printer manufacturing industry, four grinding procedures were manually conducted in four grinding machines, respectively. The productivity of the whole grinding process was low due to the long loading time. Also, the machine floor space occupation was large because of the four separate grinding machines. The manual operation also caused inconsistent quality. This paper reports the system and process development of a highly integrated and automated high-speed grinding system for printer heads. The developed system, which is believed to be the first of its kind, not only produces printer heads of consistently good quality, but also significantly reduces the cycle time and machine floor space occupation.

Exogenous Slit2 does not affect ureteric branching or nephron formation during kidney development

In an attempt to elucidate the role of Slit2 invertebrate kidney development, the effect of adding exogenous human Slit2 protein (hSlit2) to developing murine metanephric kidney explants was examined. To confirm the activity of the recombinant Slit2 protein, neurons from 8 day old chick sympathetic nerve chain dorsal root ganglia were cultured with hSlit2 protein, which induced significant neurite branching and outgrowth. Using kidney explants as a model system, metanephric development in the presence of hSlit2 protein was examined. Addition of hSlit2 up to a final concentration of 1 mug/ml had no detectable effect on the formation of nephrons or on branching morphogenesis of the ureteric tree after 2 or 4 days in culture, as assessed via immunofluorescence for the markers WT1 and calbindin 28K respectively. Similarly, maturation of the nephrogenic mesenchyme occurred in a phenotypically normal fashion. In situ analysis of the Slit receptors, Robot and Robot, the vasculogenic markers VEGFA and Flk-1, and the stromal cell marker BF2 displayed no difference in comparison to controls.