Skip to main content

Urbano Nunes

Followers

111

Following

28

Co-authors

27

Public Views

Interests

Uploads

Papers by Urbano Nunes

International IEEE Conference on Intelligent Transportation Systems [Society News]

IEEE Intelligent Transportation Systems Magazine, 2010

... ference program committee, which had one program chair (Dr. Yibing Wang), four program co-cha... more

DISCRETE-TIME SLIDING-MODE WMR CONTROL BASED ON PARAMETER IDENTIFICATION

In this paper a discrete-time adaptive sliding mode controller for wheeled mobile robots (WMR) is... more In this paper a discrete-time adaptive sliding mode controller for wheeled mobile robots (WMR) is presented. The dynamical model with time-varying mass has been taken into account. The sliding-mode controller has designed on two components, corresponding to angular and position motion, respectively. In order to accomplish the robustness against parameter uncertainties (robot mass and moment of inertia), an on-line closed loop identification scheme is proposed. In both, angular and position motion controllers, on-line estimation of parameters, which depend on robot mass, is used.

Methodologies, Platforms, Ontologies and Techniques for a Multi-Agent Architecture for Simulation of Traffic with Communications

by Pedro Fernandes and Urbano Nunes

... version. Jason is available as open source and uses jEdit [62] as IDE. ... of Transp., USA 20... more

Vehicle Communications: A Short Survey

Inter-vehicle communications (IVC) consists in a real application of vehicular ad-hoc networks (V... more Inter-vehicle communications (IVC) consists in a real application of vehicular ad-hoc networks (VANET) and is part of Intelligent Transportation Systems (ITS). An overview of IVC is presented. To guarantee IVC effectiveness, attention must be paid to one of the most important component of the system: the driver and the way he/her receives crucial information. A brief summary of the communication issues is presented.

Sensors for Legged Mobile Robots

The article presents a survey of sensors relevant for mobile robot navigation and their sensing p... more The article presents a survey of sensors relevant for mobile robot navigation and their sensing principles. The sensors surveyed include range sensors, inertial systems and positioning systems. There are many applications, from different sectors that could profit from this type of technology: autonomous mobile platforms for materials handling in industry, warehouses, hospitals, etc.; forestry cutting and undergrowth management equipment; autonomous fire-fighting machines; mining machinery; advanced electrical wheel chairs; autonomous cleaning machines; security and surveillance robots. Advanced sensor systems which are now emerging in different activities from the health care services to the transportation sector and domestic services, will significantly increase the capabilities of autonomous vehicles and will enlarge their application potential.

Force Control with a Kalman Active Observer Applied in a Robotic Skill Transfer System

The article describes the design of a force controller for a position-based manipulator with arbi... more The article describes the design of a force controller for a position-based manipulator with arbitrary dead-time applying Kalman Active Observers. The design is based on pole placement using discrete state space theory. An active state variable is introduced to compensate non linearities and parameter variations during the control process. Only the output of the plant is measured. All the discrete

Special Issue on ITSC 2006

aimed to continue the tradition of the ITSC conference series of promoting interaction among rese... more aimed to continue the tradition of the ITSC conference series of promoting interaction among researchers from all over the world and to contribute to the progress of scientific knowledge in the area of intelligent transportation systems (ITS). Presentations of the most recent advances and state of the art in research related to ITS took place, covering a broad range of topics, such as travel information systems, traffic management, ITS modeling and analysis, navigation and guidance, advanced vehicle safety systems, and intelligent vehicle technologies. ITSC 2006 had high technical quality, with a large submission of 426 papers from 30 countries. Each conference paper was peer reviewed, on average, by three reviewers, and additionally, for each paper, an International Program Committee (IPC) member produced a summary review report. Based on reviewer and IPC member evaluation reports and scores, 273 papers were finally selected by the conference Program Committee.

Object Detection On Cell Broadband Engine

Many theoretically conceived, efficient computer vision applications are avoided to run on-the-fl... more Many theoretically conceived, efficient computer vision applications are avoided to run on-the-fly for hardware limitations. For recognizing objects in images and extracting object information, a system usually owns object searching, object classification and object tracking modules. Nevertheless, each one of these modules may be high time demanding, requiring to be implemented in different computers in order to achieve efficient runtime. On the other hand, more multi-core processor computers come to provide powerful processing towards full parallel implementations inside cost effective systems. In this way, the main contribution of this paper is pointing some directions to implement those systems in the Cell broadband engine.

On Using Cell Broadband Engine for Object Detection in ITS

Trade-off between accuracy and computational cost is usually hard to achieve in order to build a ... more Trade-off between accuracy and computational cost is usually hard to achieve in order to build a real-time and accurate object recognition system. Many theoretically conceived, efficient computer vision applications are avoided to run on-the-fly for hardware limitations. For recognizing objects in images and extracting object information, a system usually owns object searching, object classification and object tracking modules. Nevertheless, each one of these modules may be high time demanding, requiring to be implemented in different computers in order to achieve efficient runtime. On the other hand, more multi-core processor computers come to provide powerful processing towards full parallel implementations inside cost effective systems. In this way, the main contribution of this paper is not only a survey of works under the main architecture pipeline of object recognition systems in the point of view of computational cost but also pointing some directions to implement those systems in the Cell broadband engine, coming with Playstation 3 TM game console. The main purpose is the implementation of a complete object detection system for Intelligent Transportation Systems.

A Hierarchical Fuzzy Integration of Local and Global Feature-based Classifiers to Recognize Objects in Autonomous Vehicles

Sensing is a paramount task for autonomous vehicles. In this field, machine vision is usually app... more Sensing is a paramount task for autonomous vehicles. In this field, machine vision is usually applied owing to its high dense information per sensing area. This characteristic contributes for the development of classification algorithms that extract information of objects in images. Although individual classifiers have been increasingly enhanced lately, effective integration of classification characteristics from different classifiers is still in a recent stage of investigation. To contribute for early step of classification fusion, we propose a method to combine the decisions of a local and a global feature-based classifiers. The main goal is to use a Label Set Reduction strategy based on a Hierarchical Fuzzy Integration system to make a decision about the results of the classification labels. The proposed architecture has been applied to recognize pedestrians and cars in outdoor environments, but it is easily expansible to include other types of classifiers and object classes. Promising results, in the final classifier, have been achieved.

A behavior based fuzzy control architecture for path tracking and obstacle avoidance

This paper presents an improvement to the Reactive Shared-Control System in development at the IS... more This paper presents an improvement to the Reactive Shared-Control System in development at the ISR (Institute of Systems and Robotics). A path tracking behaviour is being added in the control architecture in order to increase the navigation autonomy of a powered wheelchair (RobChair). The paper focuses the implementation of the path-tracking by means of fuzzy logic and presents possible solutions to combine the behaviours in order to achieve a coherent response. Simulation results are presented to show the effectiveness of the controller.

Path Tracking Controller of a bi-steerable Cybernetic Car using Fuzzy Logic

This paper presents a path-tracking controller of a bi-steerable cybernetic car. The velocity pla... more This paper presents a path-tracking controller of a bi-steerable cybernetic car. The velocity planner is a fundamental block in the architecture. Its implementation uses fuzzy logic, and dynamic issues like vehicle´s dynamics and road-vehicle interaction are taken into account. To make the travel as comfortable as possible for the passengers was one of the main objectives in the controller design. Simulation and experimental results are presented showing the effectiveness of the overall navigation control system.

Autonomous navigation control with magnetic markers guidance of a cybernetic car using fuzzy logic

This paper presents a path-following controller of a bi-steerable cybernetic car with magnetic ma... more This paper presents a path-following controller of a bi-steerable cybernetic car with magnetic markers guidance and a laser based anti-collision behaviour. The velocity planner, the vehicle's pose estimator and the multi-target detection and tracking system are fundamental modules of the navigation control architecture. The paper is focused on the path following controller, which is implemented using fuzzy logic. The smoothness of the acceleration profile was one of requirements taken into account in the controller design. Simulation and experimental results are presented showing the effectiveness of the overall control system.

Data Fusion of wheel encoders and magnetic sensors for autonomous vehicles navigation

by Urbano Nunes and Marcio Barata

This paper presents a guidance system for autonomous vehicles navigation. It integrates redundant... more This paper presents a guidance system for autonomous vehicles navigation. It integrates redundant encoders data and absolute positioning data provided by magnetic sensing rulers that detect magnetic markers placed in the ground. Data from four wheels encoders and one steering encoder are fused by means of an EKF, providing robust odometric information, namely in face of undesirable effects of wheels slippage. Simulation and real experiments using a four wheels actuated electric vehicle (Robucar) are presented.

Assistive navigation control architecture

An advanced class of robots and intelligent machines that adapt, extend, and work in a symbiotic ... more An advanced class of robots and intelligent machines that adapt, extend, and work in a symbiotic way with humans, is required and is under research in University and Industry laboratories. These robots do not only work for humans, but also they work with or assist humans, and share with the users the same environment. This paper presents an hybrid control architecture with reactive, deliberative, and cognitive components appropriate to human-oriented mobile robots. The architecture is under development and has been tested in a motorized wheechair equipped with several sensors and a multimodal HMI (Human-Machine Interface). A joystick and a voice unit interface (VUI) are used to steer the wheelchair, giving accessibility to handicaped persons.

Fieldbuses in Real-Time Control of Autonomous Vehicles

Robotica

In this article a survey on fieldbuses is conducted with a special emphasis in real-time control ... more In this article a survey on fieldbuses is conducted with a special emphasis in real-time control applications for autonomous vehicles. Actual tendencies as well as major characteristics of fieldbuses are described. Applications in high demand systems, either in terms of reliability as in terms of real-time restrictions, are analyzed. Autonomous vehicles are comp lex systems requiring real-time distributed embedded control composed by multiple acquisition, processing and actuation devices. The interconnection of the distributed intelligent devices is a key factor in the overall performance of the system. To better understanding the requirements in terms of connections in an autonomous vehicle, the main modules of a global navigation system are conceptually described in a systematic way. A special focus in CAN fieldbus is made in order to point out some potentialities, which make it very attractive in autonomous vehicles real-time applications.

BRAIN COMPUTER INTERFACE APPROACHES TO CONTROL MOBILE ROBOTIC DEVICES

Advances in Mobile Robotics, 2008

This paper presents and compares two approaches for brain computer interface to steer a wheelchai... more This paper presents and compares two approaches for brain computer interface to steer a wheelchair, namely a new visual based P300 paradigm consisting of 8 arrows randomly intensified used for direction selection and a motor imagery paradigm for discrimination of three commands. Classification follows Bayesian and Fisher Linear Discriminant approaches both based on prior statistical knowledge. Results in P300 paradigm reached false positive and false negative classification accuracies above 90%. Motor imagery experiments presented about 70% accuracy for left vs. right imagery and imagery vs. non-imagery.

DC MOTORS CONTROL USING ACTIVE OBSERVERS

The paper analyses the behaviour of active observers applied on a DC motor controlled with state ... more The paper analyses the behaviour of active observers applied on a DC motor controlled with state feedback . The observers are used to provide the feedback of the state variables in order to control the motor. Two kinds of active observers are studied: deterministic observers and stochastic (Kalman based) observers. The deterministic observers are designed to have a dead-beat dynamics and will be applied to simple and augmented models of the motor, in order to deal with constant disturbances. The stochastic (Kalman based) observer is designed to cope with more general disturbances. Copyright CONTROLO 2000.

Obstacle Avoidance in Local Navigation

A reactive navigation system for an autonomous non-holonomic mobile robot in dynamic environments... more A reactive navigation system for an autonomous non-holonomic mobile robot in dynamic environments is presented. A new object detection algorithm and a new reactive collision avoidance method are presented. The sensory perception is based in a laser range finder (LRF) system. Simulation results are presented to verify the effectiveness of the proposed local navigational system in unknown environments with multiple moving objects.

Feature Extraction for Moving Objects Tracking System in Indoor Environments

In this paper a feature extraction and classification methodology for a laser based detection and... more In this paper a feature extraction and classification methodology for a laser based detection and tracking of moving objects (DATMO) system in indoors environments is presented. The sensory perception is based in a SICK Laser Measurement System (LMS). An adaptation of the Hough Transform is used in the feature extraction procedure to interpret scanned segments, as primitive features, defined by geometric evidence (points, lines, circles and blobs), and high-level features, generally referred to as landmarks (corners, columns, doors, etc.). The classification system uses features data, some heuristic rules, and data from a Kalman filter based tracking system to classify multiple objects. Real and simulated results are presented to verify the effectiveness of the proposed DATMO system in unknown environments with multiple moving objects.