Search

Tese de doutoramento, Engenharia Informática, Faculdade de Ciências e Tecnologia, Universidade do Algarve, 2016 As technology and our understanding of the human brain evolve, the idea of creating robots that behave and learn like humans seems to get more and more attention. However, although that knowledge and computational power are constantly growing we still have much to learn to be able to create such machines. Nonetheless, that does not mean we cannot try to validate our knowledge by creating biologically inspired models to mimic some of our brain processes and use them for robotics applications. In this thesis several biologically inspired models for vision are presented: a keypoint descriptor based on cortical cell responses that allows to create binary codes which can be used to represent speci c image regions; and a stereo vision model based on cortical cell responses and visual saliency based on color, disparity and motion. Active vision is achieved by combining these vision modules with an attractor dynamics approach for head pan control. Although biologically inspired models are usually very heavy in terms of processing power, these models were designed to be lightweight so that they can be tested for real-time robot navigation, object recognition and vision steering. The developed vision modules were tested on a child-sized robot, which uses only visual information to navigate, to detect obstacles and to recognize objects in real time. The biologically inspired visual system is integrated with a cognitive architecture, which combines vision with short- and long-term memory for simultaneous localization and mapping (SLAM). Motor control for navigation is also done using attractor dynamics.

We present a biologically-inspired method for object detection which is capable of online and one-shot learning of object appearance. We use a computationally efficient model of V1 keypoints to select object parts with the highest information content and model their surroundings by a simple binary descriptor based on responses of cortical cells. We feed these features into a dynamical neural network which binds compatible features together by employing a Bayesian criterion and a set of previously observed object views. We demonstrate the feasibility of our algorithm for cognitive robotic scenarios by evaluating detection performance on a dataset of common household items. © Springer International Publishing Switzerland 2014.

Human-robot interaction is an interdisciplinary research area which aims at integrating human factors, cognitive psychology and robot technology. The ultimate goal is the development of social robots. These robots are expected to work in human environments, and to understand behavior of persons through gestures and body movements. In this paper we present a biological and realtime framework for detecting and tracking hands. This framework is based on keypoints extracted from cortical V1 end-stopped cells. Detected keypoints and the cells’ responses are used to classify the junction type. By combining annotated keypoints in a hierarchical, multi-scale tree structure, moving and deformable hands can be segregated, their movements can be obtained, and they can be tracked over time. By using hand templates with keypoints at only two scales, a hand’s gestures can be recognized.

SiPLAB Report 02/10, FCT, University of Algarve,2010. This document describes a data acquisition/data generation system, which consists of a portable waterproof case with all the integrated electronics. It features a high power battery, a precision DAQ board, a state-of-the-art GPS board and a complete computer system. Acquired data can be stored in the internal hard drive and download into another storage device or directly to another computer using the Ethernet connection. It is intended to be used with the Portable Acoustic Source Unit (PASU) for acoustic data transmission and with single or multiple hydrophones for acoustic data acquisition. The system also features a easy and ready-to-use graphical user interface that allows the user to use the system using the integrated LCD touch screen. A user manual is included as an installation, setup and maintenance guide for the system and its practical applications. The developed hardware and software is described in detail. Detailed schematics and designs can be found in the final section of this document, which can be used to further develop the system, perform maintenance, purchase spare parts or perform any type of modifications. A support equipment named OCU (Outdoor Communications Unit) is also described in this document. The OCU consists of a waterproof case that can be used to supply the AERU or the PASU and to add wireless connectivity to the AERU it can also provide a handy solution to charge the batteries of the AOB2 buoys in a wet deck environment. ACKNOWLEDGMENT: This work was supported by project UAN (Underwater Acoustic Network) from the European Community's Seventh Framework Programme (FP7/2007-2013) under Grant Agreement # 225669.

Most simultaneous localisation and mapping (SLAM) solutions were developed for navigation of non-cognitive robots. By using a variety of sensors, the distances to walls and other objects are determined, which are then used to generate a map of the environment and to update the robot’s position. When developing a cognitive robot, such a solution is not appropriate since it requires accurate sensors and precise odometry, also lacking fundamental features of cognition such as time and memory. In this paper we present a SLAM solution in which such features are taken into account and integrated. Moreover, this method does not require precise odometry nor accurate ranging sensors.

Dissertação de mest., Engenharia Eléctrica e Electrónica (Tecnologias de Informação e Telecomunicações), Instituto Superior de Engenharia, Univ. do Algarve, 2011 Submitted by Maria Viegas (mcviegas@ualg.pt) on 2013-01-14T17:23:29Z No. of bitstreams: 1 VisãoActivaRobotCognitivo.pdf: 5217615 bytes, checksum: 7c82d973b60e9ea4002fb9a7d5389fbe (MD5) Made available in DSpace on 2013-01-14T17:23:29Z (GMT). No. of bitstreams: 1 VisãoActivaRobotCognitivo.pdf: 5217615 bytes, checksum: 7c82d973b60e9ea4002fb9a7d5389fbe (MD5) Previous issue date: 2010

Senior citizens, very young children and users with different kinds of impairments are often prevented from enjoying the benefits of latest technologies for assistance, accessibility and usability, often due to unfriendly or expensive interfaces. We present a friendly and inexpensive system that allows one to interact with a computer, using only a few distinct but intuitive gestures which are translated into mouse actions. The gestures can be carried out by the head or by the hand, which are automatically selected, without any kind of prior calibration or special environment. For each kind of user a different frontend is presented, adapted to specific needs, nevertheless access to all the functionalities of the operating systems can be given if requested.

Rep 04/09 - SiPLAB January 10th 2009 Submitted by Pedro Sousa (a19661@ualg.pt) on 2014-10-10T11:10:24Z No. of bitstreams: 1 Releaser operation manual.pdf: 1264393 bytes, checksum: db03457731f1f264755350d823b087ee (MD5) Approved for entry into archive by Sofia Lopes (silopes@ualg.pt) on 2014-10-10T20:09:05Z (GMT) No. of bitstreams: 1 Releaser operation manual.pdf: 1264393 bytes, checksum: db03457731f1f264755350d823b087ee (MD5) Made available in DSpace on 2014-10-10T20:09:05Z (GMT). No. of bitstreams: 1 Releaser operation manual.pdf: 1264393 bytes, checksum: db03457731f1f264755350d823b087ee (MD5) Previous issue date: 2009

SiPLAB Report 05/09, FCT, University of Algarve,2009. This document describes a Portable Acoustic Source Unit, which is a system composed of an acoustic projector (Lubell LL916C) and a waterproof case containing all the electronics. The waterproof case contains an audio amplifier, an impedance converter, a switching regulator, measuring equipment and a high power battery to supply the whole system in a vessel or on shore in a field test standalone configuration. This is a system that can be used to transmit acoustic signals generated by a computer or by another system such as the AERU which has also been developed for the UAN project. A user manual is included as an installation, setup and maintenance guide for the system and its practical applications. The developed hardware and software is described in detail. Detailed schematics and designs can be found in the final section of this document, which can be used to further develop the system, perform maintenance, purchase spare parts or perform any type of modifications.