Anna Montesanto

Navigation with memory in a partially observable environment

Abstract The paper presents an architecture that allows the reactive visual navigation via an unsupervised reinforcement learning. This objective is reached using Q -learning and a hierarchical approach to the developed architecture. Using these techniques requires a deviation from the Partially Observable Markov Decision Processes (POMDP) and some innovations: heuristic techniques for generalizing the experience and for treating the partial observability; a technique for the speed adjournment of the Q function; the definition of a special reinforcement policy adequate for learning a complex task without supervision. The result is a satisfactory learning of the navigation assignment in a simulated environment.

Self-Organizing Maps versus Growing Neural Gas in a Robotic Application

The paper proposes a method for visual based self-localisation of a mobile agent in indoor environment. The images acquired by the camera constitute an implicit topological representation of the environment. The environment is a priori unknown and so the implemented architecture is entirely unsupervised. To compare the performance of some self-organising neural networks, a similar neural network architecture of both Self-Organizing Map (SOM) and Growing Neural Gas (GNG) has been realized. Extensive simulations are provided to characterise the effectiveness of the GNG model in recognition speed, classification tasks and in particular topology preserving as compared to the SOM model. This behaviour depends on the following fact: a network (GNG) that adds nodes into map space can approximate the input space more accurately than a network with a predefined structure and size (SOM). The work shows that the GNG network is able to correctly reconstruct the environment topological map.

Fingerprints Recognition Using Minutiae Extraction: a Fuzzy Approach.

The aim of this paper is to study the fingerprint verification based on local ridge discontinuities features (minutiae) only using grey scale images. We extract minutiae using two algorithms those following ridge lines and then recording ridge endings and bifurcations. Moreover we use a third algorithm able to develop a minutiae verification processing a local area using a neural network ( multilayer perceptron). Fingerprint distortion is filtered using a minutiae whole representation based on regular invariant moments. The results of the three minutiae extraction algorithms are joined during the minutiae pattern matching phase for fingerprint verification. Here we propose a new method of matching that use fuzzy operator to bypass the problem of different numbers of minutiae extracted from the algorithms. Experimental evidences show fingerprint recognition up to 95%.

Scale Free Graphs in Dynamic Knowledge Acquisition

Classical representation forms are not suited to represent knowledge as human mind does. In tasks as discourse comprehension knowledge stuctures have to adapt themselves on the basis of the objectives, the past experiences and the particular context. So we have developed a modular knowledge acquisition system based on cognitive criteria, that dynamically updates a representation by the use of a scale free graph model.

Detecting Anomalous Traffic Using Statistical Discriminator and Neural Decisional Motor

One of the main challenges in the information security concerns the introduction of systems able to identify intrusions. In this ambit this work takes place describing a new Intrusion Detection System based on anomaly approach. We realized a system with a hybrid solution between host-based and network-based approaches, and it consisted of two subsystems: a statistical system and a neural one. The features extracted from the network traffic belong only to the IP Header and their trend allows us detecting through a simple visual inspection if an attack occurred. Really the two-tier neural system has to indicate the status of the system. It classifies the traffic of the monitored host, distinguishing the background traffic from the anomalous one. Besides, a very important aspect is that the system is able to classify different instances of the same attack in the same class, establishing which attack occurs.

Color-Oriented Content Based Image Retrieval

The aim of this work is to study a metrics that represents the perceptive space of the colors. Besides we want to furnish innovative methods and tools for annotate and seek images. The experimental results have shown that in tasks of evaluation of the similarity, the subjects don’t refer to the most general category of “color”, but they create subordinate categories in base to some particular color. Those categories contain all the variations of this color and also they form intersections between categories in which any variations are shared. The perception of the variations is not isometric; on the contrary that perception is weighed in different manner if the variations belong to a particular color. So the variations that belong to the intersection area will have different values of similarity in relation to the own category. We developed a system of color-oriented content-based image retrieval using this metrics. This system analyzes the image through features of color correspondents to the own perception of the human being. Beyond to guarantee a good degree of satisfaction for the user, this approach furnishes a novelty in the development of the CBIR systems. In fact there is the introduction of a criterion to index the figures; it is very synthetic and fast.

Emergence of the Cooperation-Competition between Two Robots

The work studies the trajectories, the emergent strategies and the effects due to the interaction of two robots, in a simulated environment. The robots have the same task: crossing some fixed zones of the environment. The study is focused on the emergence of collaborative or competitive behaviour, which is valued by taking into account the interaction area locations and the impact of the interaction on the behaviour. The results of the research show emergent behaviours with a strong analogy with those of dominance in nature, in which animals organize itself in groups that follow particular geometries. The experiments highlight that the resulting interaction geometries depend on the agent evolution degree and on the interaction area locations, while the relationship between these two factors appears as reciprocal.

Analysis of Fingerprints Through a Reactive Agent

The aim of this job is to study the process of self-organisation of the knowledge in a reactive autonomous agent that navigates throughout a fingerprint image. This fingerprint has been recorded using a low cost sensor, so it has with her a lot of noise. In this particular situation the usual methods of analysis of the minutiae fail or need a strong pre-processing of the image. Our system is a reactive agent that acts independently from the noise in the image because the process of self-organising of the knowledge carries to the emergency of the concept of “run toward the minutiae” through a categorisation of the sensorial input and a generalisation of the situation “state-action”. The system is based on hybrid architecture for the configuration recognition and the knowledge codifies.

Visual self-localisation using automatic topology construction

The paper proposes a machine learning method for self-localising a mobile agent, using the images supplied by a single omni-directional camera. The images acquired by the camera may be viewed as an implicit topological representation of the environment. The environment is a priori unknown and the topological representation is derived by unsupervised neural network architecture. The architecture includes a self-organising neural network, and is constituted by a growing neural gas, which is well known for its topology preserving quality. The growth depends on the topology that is not a priori defined, and on the need of discovering it, by the neural network, during the learning. The implemented system is able to recognise correctly the input frames and to reconstruct a topological map of the environment. Each node of the neural network identifies a single zone of the environment and the connections between the nodes correspond to the real space connections in the environment.

Reactive Navigation Using Reinforment Learning in Situations of POMDPs

The aim of this work is to individualize an architecture that allows the reactive navigation through an unsupervised learning based on the reinforcement learning. To reach the objective quoted, we used the Q-learning and one hirerarchical struture of the architecture developed. To use these techniques in presence of Partially Observable Markov Decision Processes (POMDP) is necessary introduce some innovations: heuristic techniques for the generalization of the experience and for the treatment of the partial observability, a technique for the speed adjournment of the Q function and the definition of reinforcement policy adequate for the unsupervised learning of a complex assignment. The results show a satisfactory learning of the assignment of navigation in a simulated environment.