Bráulio Coelho Ávila

A learning agent to help drive vehicles

This paper presents the development of an intelligent agent used to assist vehicle drivers. The agent has a set of resources to generate its action policy: road and vehicle features and a knowledge base containing conduct rules. The perception of the agent is ensured by a set of sensors, which provide the agent with data such as speed, position and conditions of the brakes. The main agent behaviour is to carry out action plans involving: increase, maintain or reduce speed. The main effort of this research was the induction of conduct rules from data of previous trips. These rules form a classifier used for the selection of actions forming the conduction plan. Results observed with the experiments have showed that the proposed classifier increases the efficiency throughout the conduction of vehicles.

PANDORA: a multi-agent system using paraconsistent logic

This work is part of the Multicheck Project that defines architecture of cognitive and independents agents for the automatic treatment of handwritten Brazilian bank checks. The concept of autonomous agents allows us to organize the application knowledge and brings several own benefits to the approach. The choice of this approach is supported in a triple hypothesis. First, the nature of the problem in question allows decomposition in well-defined tasks, and each of them can be encapsulated in an independent agent. Second, the natural capability of interaction of the agents makes the check treatment process more robust, solving situations apparently difficult. Third, the natural parallelism between the agents can contribute to implement an application with high performance.

Lessons learned from a simulated environment for trains conduction

This paper consolidates and discuss the results of a software agent development, named SDriver, which is able to drive an intercity freight train in a secure, economic and fast way. The SDriver executes a small set of instructions, named: reducing, increasing or maintaining the acceleration point, and start breaking. Three approaches have been studied to implement the core of SDriver: (i) machine learning (classification methods), (ii) distributed constraint optimization, and (iii) specialized rules (if-then). The SDriver performance was evaluated comparing fuel consumption and actions similarity with a real conduction, using a simulated environment. The validation of the knowledge discovered from the machine learning approach was done quantitatively, calculating a degree of similarity between the simulation and the history of travel. The main results are expressed by their mean values: 32% of fuel consumption reduction and 85% action similarity between the SDriver and the real conductor.

Decision tree-based paraconsistent learning

It is possible to apply machine learning, uncertainty management and paraconsistent logic concepts to the design of a paraconsistent learning system, able to extract useful knowledge even in the presence of inconsistent information in a database. This paper presents a decision tree-based machine learning technique capable of handling inconsistent examples. The intention is to define a model able to handle databases with a large quantity of inconsistent examples. The model obtained is evaluated and compared with the C4.5 algorithm in terms of classification accuracy and size of the trees generated. As will be observed, in most situations where high rates of inconsistent examples were found, this presented better results when compared to the C4.5 algorithm.

An architecture of BDI agent for autonomous locomotives controller

In this paper we propose an architecture of intelligent agent for automatic locomotives operating. The system agent generates its action policy using a set of resources, such as type of railway, composition, belief perception and reasoning about the actions. The focus of the operator agent is directed to the choice of acceleration points (gear) and preparation of travel plans in a journey guided by goals and objectives. The system is equipped with a module capable to plan the actions to move the vehicle from an initial point P to an end point Q and an executor module that implements the generated plan and modifies the state of the environment. For this purpose, we use the mental model that is based on the triple Belief, Desire and Intention (BDI) to which the perception of the agent is guaranteed by a set of sensors that provide speed information, position and breaks condition. The main focus on this research is the usage of mental model BDI for the resolution of a problem that combines travel naturally conflicting factors, such as safety, time and fuel consumption. Experimental results show that the developed architecture using the mental model BDI increases the efficiency of autonomous vehicles operating.

Using asymmetric keys in a certified trust model for multiagent systems

We present a contribution based on encryption to the model for the certification of trust in multiagent systems. The originality of the proposal remains in the use of asymmetric keys that allow the local storage of testimonies with the service agents that were assessed. The aim is to raise the level of efficiency that client agents have when contracting specialized service agents. To reach this objective we make three hypotheses: (i) client agents are able to measure and inform the quality of a service they receive from a service agent; (ii) distributed certificate control is possible if every service agent stores the certificates it receives from its client agents and, (iii) the content of a certificate can be considered safe as long as the public and private keys used to encrypt the certificate remain safe. This approach reduces some weak points of trust models that rely on the direct interaction between service and client agents (direct trust) or those that rely on testimony obtained from client agents (propagated trust). Simulation showed that encrypted certificates of trust improved the efficiency of client agents when choosing their service provider agents. The reason seems to be that the reputation of a given service provider agent is based on the reputation it has among the totality of client agents that used its services.

A paraconsistent system of autonomous agents for Brazilian bank check treatment

This work is part of the Multicheck Project that defines the architecture of autonomous agents for the automatic treatment of handwritten Brazilian bank checks. The competence of these agents is implemented in two layers. The first corresponds to pattern recognition algorithms directly applied to image segments. The second one corresponds to reasoning mechanisms applied to the information from the first layer, either to validate or to interpret it. The interpretation process also involves information obtained from other agents. This information can present inconsistencies. This problem is treated properly and naturally through the concepts and operators of paraconsistent logic. This paper focuses on the second layer, on task distribution problems and on communication between agents. The first layer information was obtained through a simulated database.

An intelligent system for driving trains using Case-Based Reasoning

This paper presents a planning approach using Case-Based Reasoning (CBR) to generate plans for driving trains. The main idea of a planning strategy is to generate a sequence of actions for an agent, which can use these actions to change its environment. CBR allows using prior experiences in the situation assessment task. In the proposed approach, each previous experience (if not applicable) is adjusted resulting in cases specializations. Our interest is reducing the number of corrections triggered when a case retrieved is not applicable, based on these specializations. Experiments showed that the plans generated using this proposed method had a significant increase in the number of cases recovered satisfactorily, also reducing the need of adaptations for the cases recovered.

Improving bilateral negotiation with evolutionary learning

This paper proposes an approach to generate offers and counter-offers in a bilateral negotiation process between cognitive agents with the learning machine capacities. The approach is configured, as each participant of a negotiation process improve their satisfaction degree, gaining knowledge from prior experience, i.e., in the next negotiation session, each participant can individually use this knowledge to redefine the configuration parameters of strategies and tactics to generate offers and counter-offers. Each agent refines their strategies using a genetic algorithm application based on the historical offers and counter-offer exchanges dataset. This context can lead to a new dimension in CSCW system development. This approach was tested in a simulated bilateral negotiation environment, which involved, for example, a buyer agent and a seller agent. The discussions about the results confront different negotiation sessions comparing agents provided with strategy and tactics reconfiguration capabilities and agents using static strategies and tactics.

Multiagent-Based Model Integration

This paper presents a distributed data mining technique based on a multiagent environment, called SMAMDD (multiagent system for distributed data mining), which uses model integration. Model integration consists in the amalgamation of local models into a global, consistent one. In each subset, agents perform mining tasks locally and, afterwards, results are merged into a global model. In order to achieve that, agents cooperate by exchanging messages, aiming to improve the process of knowledge discover generating accurate results. The multiagent system for distributed data mining proposed in this paper has been compared with classical machine learning algorithms which are based on model integration as well, simulating a distributed environment. The results obtained show that SMAMDD can produce highly accurate data models