1,721,039 research outputs found
Bayesian Belief Networks: Introduction and Learning
No full textBayesian Belief Networks are graph-based representations of probability distributions. In the last decade they became popular for modeling and using uncertain knowledge in many and different contexts. In this paper an introduction to the framework and a review of the main issues related to learning Bayesian Belif Networks are presented. The first part focuses on the definition of the framework: the mathematical and representational properties are described and discussed as well as Belief Networks from data, a topic which received much attention recently. A large amount of works, approaches and methodologies proposed in the literature is surveye
A Hybrid Framework for Indoor Robot Navigation
No full textThis paper introduces a hybrid system for modeling, learning and recognition of sequences of ‘states’ in indoor robot navigation. States are broadly defined as local relevant situations (in the real world) in which the robot happens to be during the navigation. The hybrid is based on parallel Recurrent neural Networks trained to perform a-posteriori state probability estimates of an underlying Hidden Markov Model given a sequence of sensory (e.g. sonar) observations. The approach is suitable for navigation and for map learning. Encouraging experiments of recognition of noisy sequences acquired by a mobile robot equipped with 16 sonars are presente
Learning perception for indoor robot navigation with a hybrid Hidden Markov Model/Recurrent neural networks approach
No full textThis paper introduces a hybrid system for modeling, learning and recognition of sequences of 'states' in indoor robot navigation. States are broadly defined as local relevant situations (in the real world) in which the robot happens to be during the navigation. The hybrid is based on parallel recurrent neural networks trained to perform a posteriori state probability estimates of an underlying hidden Markov model (HMM) given a sequence of sensory (e.g. sonar) observations. Discriminative training is accomplished in a supervised manner, using gradient-descent. Recognition is carried out either in a dynamic programming framework, i.e. searching the maximum a posteriori probability of state-posteriors along paths of the HMM, or in real time. The approach is suitable for navigation and for map learning. Experiments of learning and recognition of noisy sequences acquired by a mobile robot equipped with 16 sonars are presented
Evaluating the deployment of FIPA Standards when developing application services
No full textWe draw upon various practical experiences of designing and implementing complex systems through a multi-agent approach which supports engineering of dynamic open distributed services. The general scope of multi-agent system software engineering is reviewed with focus on the analysis and evaluation of certain aspects of the current specification standards provided by FIPA (Foundation of Intelligent Physical Agents). The benefits and drawbacks of a multi-agent approach, using the FIPA standards ad a benchmark, are evaluated and further illustrated though the deployment of an audio video entertainment broadcasting (AVEB) system. The development and testing of the AVEB application was part of an EU project called FACTS (acts AC317). A main result of using agent engineering paradigm for complex distributed development, especially apparent in FIPA standards, has been the identification of the usefulness and power of its protocols. The reason for the importance of the protocols in developing multi-agent systems (MAS) is it provides a degree of expressing cooperation within MAS architecture. As the protocols stand currently they are not sufficient to capture a complete explicit model of the cooperative requirements in multi-agent systems. However, they provide a basis from which to start. We examine this feature of FIPA further in order to evaluate its role as a bridge between the mental agency and social agency requirements in the development of cooperation in multi-agent systems
From Standard Specifications to a Multi-agent Software System: Audio Video Entertainment Application in Practice
No full textThe paper focuses on two particular aspects of using a set of current standards for building a Multi-agent system: analysis and evaluation of certain aspects of the current specification standards provided by FIPA (Foundation of Intelligent Physical Agents) when implementing Multi-agent systems and bridging the gap between the specification and getting a multi-agent system to work. The work reported here is based on one of the developments of a Multi-agent architecture to test certain features of a standards specification. This testing has resulted in determining certain limitations and advantages of using the FIPA standards. The application used for deployment is an audio video entertainment broadcasting (AVEB) system. The development and testing are part of an EU project called - FACTS (acts AC317
Learning Perception for Indoor Robot Navigation with a Hybrid HMM/Recurrent Neural Networks Approach
No full textThis paper introduces a hybrid system for modeling, learning and recognition of sequences of “states'' in indoor robot navigation. States are broadly defined as local relevant situations (in the real world) in which the robot happens to be during the navigation. The hybrid is based on parallel recurrent neural networks trained to perform a-posteriori state probability estimates of an underlying Hidden Markov Model (HMM) given a sequence of sensory (e.g. sonar) observations. Discriminative training is accomplished in a supervised manner, using gradient-descent. Recognition is carried out either in a Dynamic Programming framework, i.e. searching the Maximun A Posteriori probability of state-posteriors along paths of the HMM, or in real-time. The approach is suitable for navigation and for map learning. Encouraging experiments of recognition of noisy sequences acquired by a mobile robot equipped with 16 sonars are presente
An hybrid HMM/recurrent neural networks approach to indoor robot navigation
No full textThis paper introduces an hybrid system for modeling and recognition of sequences of ‘states’ in indoor robot navigation. States are broadly defined as relevant situations (in the real world) in which the robot happens to be during the navigation. The hybrid is based on parallel, state-space recurrent neural networks trained to perform a-posteriori state probability estimates of an underlying hidden Markov model (HMM) with fixed transition probabilities, given a sequence of sensory (e.g. sonar) observations. Training is accomplished in a supervised manner. Recognition is carried out either in a Dynamic Programming framework, i.e. searching the Maximum A Posteriori (MAP) joint probability of state-posteriors and transitions along paths of the HMM (useful to learn maps of the environment), or in real-time (useful for navigation itself). Encouraging experimental results of state-emission probability estimation and recognition of noisy sequences acquired by a mobile robot equipped with 16 sonars are presente
- …
