João Paulo Pimentão
Universidade Nova de Lisboa
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by João Paulo Pimentão.
ieee international symposium on assembly and manufacturing | 2011
Luis Ribeiro; José Barata; João Paulo Pimentão
Modern control approaches are either designated as complex or tackle complex systems. The concept of Evolv-able Production System (EPS) entails an iterative system design/control loop that supports system Adaptation and Evolution. Both concepts are borrowed from natural systems and, if properly instantiated and explored for the sake of production systems, may come to include a set of self-organizing and emergent process. One of the main challenges in EPS research is to frame these developing natural concepts and set them in a Mechatronic Agent-based framework. Such an approach also brings into the equation the possibility to handle and, potentially, exploit emergent behaviour. Inevitably, the coping of dynamically evolving setups with unforecasted behaviours raises the complexity issue quite substantially, hence the need to begin to analyse the EPS systems as Complex Systems. This paper provides an introduction to the context of Complex Systems, in particular about the self-organization and emergence components, and, from this integration, details how the bridging of the technological and functional challenges is being adopted within EPS. The work is based on assembly systems built within the framework of several European projects, including EUPASS, IPROMS and IDEAS. Finally, the article will provide with an initial evaluation and critical review of the complexity approach.
international power electronics and motion control conference | 2014
Sérgio Onofre; Pedro Sousa; João Paulo Pimentão
Surveillance systems are evolving and analog cameras give way to IP cameras, wireless sensors are used in home surveillance, remote mobile phones access to video surveillance is current practice, but the concept itself, of “surveillance systems”, has not evolved accordingly. Control rooms are still the heart of operations, where several security guards spread their attention over an array of monitors, trying to find events. In some cases, a set of sensors may be used to help detect intrusion or fire, but these are seldom integrated with video surveillance. Under a research project (DVA) we developed a new approach to surveillance systems based in geographic position of events, sensors and security agents. This new architecture, based in geographic positions, is fully distributed (empowering sensors with processing skills), bridging them together in a society of software agents that, supported by inference capabilities, work for a common awareness and, given that they are location aware, can direct the appropriate security officers for each kind of emergency.
International Conference on Rough Sets and Current Trends in Computing | 2014
Bruno Dias; Bruno Rodrigues; Jorge Claro; João Paulo Pimentão; Pedro Sousa; Sérgio Onofre
Nowadays, surveillance systems are less dependent of humans’ interactions, mostly in event’s detection. However, there still are tasks to be performed by humans that could be delegated to autonomous robots. The integration of an autonomous service robot, as an agent, in a multi-agent surveillance system can reduce even more humans’ dependency. This paper proposes a new architecture and a communication protocol that integrates ServRobot’s autonomous robot into DVA’s surveillance system. This integration allows the DVA’s system to use the robot as a mobile unit for validation of triggered events, to perform surveillance missions and to gather sensors information.
Journal of Decision Systems | 2007
Pedro A. C. Sousa; João Paulo Pimentão; Rita A. Ribeiro
Operational Risk management, the least covered component of Enterprise Wide Risk Management, needs intelligent tools to implement Comprehensive Emergency Management Programs. In this paper we discuss how an Intelligent Decision Support System (I-DSS), based on Fuzzy Logic, can be used for supporting the management of complex and critical systems, especially under contingency situations, with limited resources’ availability. This I-DSS is a contingency/emergency management tool and its objectives are: to help users make good decisions under critical and stressful situations; to decrease global risk (e.g. prevention); to increase the level of response (e.g. improved reaction through instruction and simulation); and to ensure process description’s consistency analysis.
doctoral conference on computing, electrical and industrial systems | 2016
Sérgio Onofre; Bernardo Caseiro; João Paulo Pimentão; Pedro A. C. Sousa
Accuracy and precision are key parameters in the definition of indoor positioning systems. We want to provide a mobile robot with the capacity to autonomously determining its location inside buildings, to allow it to autonomously navigate. The solution developed is based on spreading emitter beacons of Bluetooth Low Energy in the building and use location finding techniques to determine the robot’s location. The main challenge is the capacity to obtain accurate readings of signal strength and the low repeatability of readings even under unchanged conditions. To improve the signal strength measurements it is necessary to deal with this imprecision. Our approach is based on the use of Fuzzy Logic to deal with the accuracy problem. Once better signal strength readings are achieved, using this method, approximate distances are calculated based on signal strength and the trilateration method is implemented to provide the location of the mobile robot.
international conference on information technology | 1996
João Paulo Pimentão; Ricardo Gonçalves; T. Gonçalves; H. Silva; M. Vital; Pedro A. C. Sousa; A. Garção
This paper presents the experience of Uninova on the European Commission’s (EC) ESPRIT III project 6660 — RoadRobot — Operator Assisted Mobile Road Robot for Heavy Duty Civil Engineering Applications.
international symposium on mechatronics and its applications | 2015
Sérgio Onofre; Pedro A. C. Sousa; João Paulo Pimentão
The miniaturization and cost reduction of sensors is encouraging its wide spreading and application in diverse usage areas. The use of multiple types of sensors can improve the current surveillance systems, by reducing false positives, extending the type of detected events and increasing systems redundancy. Also, geo-location is becoming more precise and available at lower costs, thus enabling its use in the surveillance of large areas where events can be geo-referenced and allowing the dynamic event handling based in its location. This paper describes a new surveillance systems architecture based in multi-sensor georeferenced events and in dynamic events handling. This system can contribute to an efficient response to events based on the location of events and security agents as well as reduce system fails with multiple sensors use.
doctoral conference on computing, electrical and industrial systems | 2015
Tiago Cabral Ferreira; Fábio Miranda; Pedro A. C. Sousa; José Barata; João Paulo Pimentão
In this paper a context classifier for service robots is presented. Independently of the application, service robots need to have the notion of their context in order to behave appropriately. A context classification architecture that can be integrated in service robots reliability calculation is proposed. Sensorial information is used as input. This information is then fused (using Fuzzy Sets) in order to create a knowledge base that is used as an input to the classifier. The classification technique used is Bayes Networks, as the object of classification is partially observable, stochastic and has a sequential activity. Although the results presented refer to indoor/outdoor classification, the architecture is scalable in order to be used in much wider and detailed context classification. A community of service robots, contributing with their own contextual experience to dynamically improve the classification architecture, can use cloud-based technologies.
doctoral conference on computing electrical and industrial systems | 2015
Sérgio Onofre; João Paulo Pimentão; Pedro A. C. Sousa
A fast and efficient response to hazardous events can make the difference between life and death. Using this necessity as premise, surveillance systems are evolving, increasing the number of sensors used in event detection and developing new methods and algorithms for events handling. Nevertheless the timeliness and efficiency of response to events could be improved using new technologies, such as mobile devices with GPS capabilities, georeferenced location of events, and event classification. Having access to events and security agents’ locations could improve event’s handling in terms of responsiveness and appropriate distribution of work load per agent. Under the scope of a research project Advanced Surveillance System (DVA) a new approach to surveillance systems based in this geographic position of sensors, detected events and security agents was developed. DVA implements new algorithms for events’ assignment and processing. This paper describes DVA’s new approach to event handling.
multiagent system technologies | 2004
João Paulo Pimentão; Pedro A. C. Sousa; Pedro Amaral; Adolfo Steiger-Garção
This paper presents an application of agent technology to the field of communication security. The proposed method, Split and Merge, is presented. The generic approach is on the denying of access to the message, instead of ciphering the message at the source and then sending it over a communication channel. This is achieved by splitting the message in parts and sending them to the destination through different routes, in an ad-hoc network of cooperating agents. The implementation of the method using multi-agent systems is detailed. The solutions found to deal with error detection and correction (loss of message fragments, message integrity and node misbehavior) are then discussed. An emphasis is put on the use reputation and trust mechanisms, with a fuzzy approach, to detect and cope with nodes with different levels of reliability.