Robot learning through task identification

The operation of an autonomous mobile robot in a semi-structured environment is a complex, usually non-linear and partly unpredictable process. Lacking a theory of robot–environment interaction that allows the design of robot control code based on theoretical analysis, roboticists still have to resort to trial-and-error methods in mobile robotics.The RobotMODIC project aims to develop a theoretical understanding of a robot’s interaction with its environment, and uses system identification techniques to identify the system robot–task–environment. In this paper, we present two practical examples of the RobotMODIC process: mobile robot self-localisation and mobile robot training to achieve door traversal.In both examples, a transparent mathematical function is obtained that maps inputs–sensory perception in both cases–to output — location and steering velocity respectively. Analysis of the obtained models reveals further information about the way in which a task is achieved, the relevance of individual sensors, possible ways of obtaining more parsimonious models, etc.     

Applications of data analysis techniques for oil production prediction

This paper describes two data analysis techniques adopted in a Decision Support System (DSS) that aids users in predicting oil production of an infill well. The system generates predictions in the form of a possible range of cumulative production and length of production life of an infill well. The system also shows the worst and best case scenarios based on different production curves so that the expert can examine the plots of predicted production rates for each existing well and decide which model gives the best fit. The production curve of each individual well was mathematically modeled so that production values beyond the historical data can be produced. Decline curve estimation and neural network approaches were adopted for data analysis in the system. The system was tested with data from two groups of wells from two different fields in Saskatchewan, Canada. Observations on the suitable duration that the historical data set should cover and a comparison among different curve estimation and neural network models are presented.     

Towards a platform for wide-area overlay network deployment and management

This paper presents an experimental set of self-organising mechanisms to support application-level service overlays across the internet. These mechanisms include a base node discovery service and protocol that is resilient to node and network failure, which in turn is a basis for the construction of service-specific overlays. We have also developed a generic service overlay structured according to IP network latencies which uses the GNP virtual coordinate system. We discuss our results and experiences of implementing our platform using an active service infrastructure deployed on PlanetLab. While we have been successful in meeting many of our aims, we have identified some practical shortcomings with regard to latency estimation accuracy, and scalability of some of our mechanisms to internet size. The paper describes lessons learned from experimental development and deployment.     

A structural approach for modelling the hierarchical dynamic process of Web workload in a large-scale campus network

A new structural approach based on hidden Markov model is proposed to describe the hierarchical nature of dynamic process of Web workload. The proposed approach includes two latent Markov chains and one observable process. One of the latent Markov chains is called macro-state process which is used to describe the large-scale trends of Web workload. The remaining latent Markov chain is called sub-state process which is used to describe the small-scale fluctuations that are happening within the duration of a given macro-state. An efficient parameter re-estimation algorithm and a workload simulation algorithm are derived for the proposed discrete model. Experiments based on a real workload of a large-scale campus network are implemented to validate the proposed model.     

A new admissibility condition of discrete-time singular systems with time-varying delays

This paper gives a novel delay-dependent admissibility condition of discrete-time singular systems with time-varying delays. For convenience, the time-varying delay is assumed to be the sum of delay lower bound and the integral multiples of a constant delay. Specially, if the constant delay is of unit length, the delay is an interval-like time-varying delay. The proposed admissibility condition is presented and expressed in terms of linear matrix inequality (LMI) by Lyapunov approach. Generally, the uncertainty of time-varying delay would lead to conservatism. In this paper, this critical issue is tackled by accurately estimating the time-varying delay. Consequently, the proposed admissibility condition is less conservative than the existing results, which is demonstrated by a numerical example.     

Catalytic behavior of potassium containing compounds for diesel soot combustion

Alkali doped oxides were synthesized and tested as catalysts for diesel soot combustion using a combinatorial method. It has been found that potassium shows better promotion of the catalytic activity than other alkali elements, and most of the potassium-rich oxides showed similar catalytic behaviors when catalysts and soot were mixed in a slurry. The influence of different mixing methods, including loose contact, tight contact and slurry (wet) mixing with different soot suspensions, on the catalytic behavior of some transition metal oxides, alkali metal carbonates and potassium-containing oxides were studied through thermogravimetry and XRD. The high activity of potassium-containing catalysts is found to be due to the intimate contact between soot and potassium cations caused by polar solvents. Potassium containing catalysts degraded after repeated thermal cycles due to the loss of potassium. It was also found that the addition of transition elements can inhibit the loss of potassium.     

Pavement crack detection using hessian structure propagation

Pavement images are widely used in transportation agencies to detect cracks accurately so that the best proper plans of maintenance and rehabilitation could be made. Although crack in a pavement image is perceived because the intensity of crack pixels contrasts with that of the pavement background, there are still challenges in distinguishing cracks from complex textures, heavy noise, and interference. Unlike the intensity or the first-order edge feature of crack, this paper proposes the second-order directional derivative to characterize the directional valley-like structure of crack. The multi-scale Hessian structure is first proposed to analytically adapt to the direction and valley of cracking in the Gaussian scale space. The crack structure field is then proposed to mimic the curvilinear propagation of crack in the local area, which is iteratively applied at every point of the crack curve to infer the crack structure at the gaps and intersections. Finally, the most salient centerline of the crack within its curvilinear buffer is exactly located with non-maximum suppression along the perpendicular direction of crack. The experiments on large numbers of images of various crack types and with diverse conditions of noise, illumination and interference demonstrate the proposed method can detect pavement cracks well with an average Precision, Recall and F-measure of 92.4%, 88.4%, and 90.4% respectively. Also, the proposed method achieves the best performance of crack detection on the benchmark datasets among methods that also require no training and publicly offer the detection results for every image.     

A data mining approach to characterize road accident locations

Data mining has been proven as a reliable technique to analyze road accidents and provide productive results. Most of the road accident data analysis use data mining techniques, focusing on identifying factors that affect the severity of an accident. However, any damage resulting from road accidents is always unacceptable in terms of health, property damage and other economic factors. Sometimes, it is found that road accident occurrences are more frequent at certain specific locations. The analysis of these locations can help in identifying certain road accident features that make a road accident to occur frequently in these locations. Association rule mining is one of the popular data mining techniques that identify the correlation in various attributes of road accident. In this paper, we first applied k-means algorithm to group the accident locations into three categories, high-frequency, moderate-frequency and low-frequency accident locations. k-means algorithm takes accident frequency count as a parameter to cluster the locations. Then we used association rule mining to characterize these locations. The rules revealed different factors associated with road accidents at different locations with varying accident frequencies. The association rules for high-frequency accident location disclosed that intersections on highways are more dangerous for every type of accidents. High-frequency accident locations mostly involved two-wheeler accidents at hilly regions. In moderate-frequency accident locations, colonies near local roads and intersection on highway roads are found dangerous for pedestrian hit accidents. Low-frequency accident locations are scattered throughout the district and the most of the accidents at these locations were not critical. Although the data set was limited to some selected attributes, our approach extracted some useful hidden information from the data which can be utilized to take some preventive efforts in these locations.

     

On the Range of the Common Cycle Time in a Road Network

In a coordinated road network, the optimal common cycle time is determined by evaluating the performance of the network in the given range of cycles. Normally, this range is determined by users’ experience. And a large range of common cycle time, e.g. \[0,0\] is chosen, which requires long computation time. This study considers that the optimal common cycle time ranges between the minimal and maximal value of intersections’ individual optimal cycle time. It is proved mathematically from the convexity condition, that the delay of the network and each individual intersection are convex functions of the cycle time according to Webster delay model. Finally, 2 000 random cases for the network composed of two intersections and of eight intersections are created to underline the proposed conclusions. The results of all cases confirm the validity, and show up to 90% improvement in computation time to compare with experience range. The signal optimization tool, Synchro, is also used to validate the conclusion by 50 random cases. The results confirm reliability further.