IEEE ICRA'06. The video demonstrates the full navigation system of the robotic wheelchair. Download paper
The video demonstrates the Nearness Diagram Navigation operating on indoor and outdoor robots with different shapes, kinematics and dynamics. Download paper
The video demonstrates the control of a robotic wheelchair only using voice commands Download paper
The video demonstrates the control of a robotic wheelchair using a PDA (the user selects rooms to direct the robot by touching the screen) Download paper
The video demonstrates the autonomous people tracking of the robotic wheelchair (with obstacle avoidance) Download paper
For historial and sentimental reasons I have added this video. It shows the moment when in 1999 I achieved with a lot of enthusiasm (see video) the first implementation of the Nearness Diagram in a XR4000 in the LAAS-CNRS, France
Javier Minguez (Associate Professor)
Javier Minguez (S’00–A’02) received the physics science degree in 1996 from the Universidad Complutense de Madrid, Madrid, Spain, and the Ph.D. degree in computer science and systems engineering in 2002 from the University of Zaragoza, Zaragoza, Spain. During this period, in 1999 he was with the Robotics and Artificial Intelligence Group, LAASCNRS, Toulouse, France, for eight months. In 2000, he visited the Robot and Computer Vision Laboratory (ISR-IST), Technical University of Lisbon, Lisbon, Portugal, for ten months. In 2001, he was with the Robotics Laboratory, Stanford University, Stanford, CA, for five months. From 2003 to 2008 he was Ramón y Cajal researcher in the University of Zaragoza. In 2008 he was visiting professor at the Institute of Medical Psychology and Behavioural Neurobiology, Tubingen, Germany for six months. Since 2008, he is an associate professor in the Computer Science and Systems Engineering in the University of Zaragoza.
Brain-Computer Interfaces research team in the University of Zaragoza.
Research on Brain-Computer Interfaces
During the last two years we have been working on the copupling between brain-computer interfaces and robotics with focuss on rehabilitation devices. In this direction we have developed two prototypes:
Brain-Actuated Robotic Wheelchair
Our research team has developed a prototype of a brain-actuated wheelchair. During May 2008, five subjects, only using their thoughts, successfully carried navigation and manoeuvrability tasks with the wheelchair in the University. The non-invasive method to record the human neural activity was the EEG and the wheelchair was robotized and equipped with a laser sensor.
The first week of June 2008 a research team of the University of Zaragoza achieved a brain-actuated robot teleoperation between two remote cities (260km). During one week, five subjects used the brain-machine interface to develop navigation and exploration tasks with the robot in a remote place. The non-invasive method to record the human neural activity was the EEG, the communication channel between Zaragoza and Barcelona was internet, and the mobile robot was equipped with an orientable camera.
Our research now focuss on the Brain Machine Interfaces for Neuroprosthetics and Robot Control.
Research on Mobile Robot Navigation
During the last years we have been working in many aspects related to mobile robot navigation.
Nearness Diagram Navigation: Reactive Collicion Avoidance in Constrained Spaces
Nearness Diagram operating on a Robotic Whelchair
This research addresses the reactive collision avoidance for mobile robots that move in arduous environments (i.e. very dense, complex and cluttered). To achieve this goal, the technique simplifies the difficulty of the navigation by a divide and conquer strategy, which is based on identifying navigational situations and applying the corresponding motion laws. As a result, navigation with this method is successfully achieved in scenarios where existing techniques present a high degree of difficulty to navigate (download paper).
This method is the obstacle avoidance technique base for the Stage & Player.
Global Nearness Diagram Navigation
Global Nearness Diagram navigation operating on a XR4000 robot
This research addresses a sensor-based motion control system was designed to autonomously drive vehicles free of collisions in unknown, troublesome and dynamic scenarios. The system was developed based on hybrid architecture with three layers (modeling, planning and reaction). The interaction of the modules was based on a synchronous planner-reactor configuration where the planner computes tactical information to direct the reactivity. It can achieve robust and reliable navigation in difficult scenarios that are troublesome for many existing methods. Experiments carried out in these scenarios with a real vehicle confirm the effectiveness of this technique.(download paper).
Modeling static and dynamic scenarios for Mobile Robot Navigation
Modeling dynamic and static scenarios: a robot working in an indoor environment mapping the static parts and tracking the people around.
This research addresses the modeling of the static and dynamic parts of the scenario
and how to use this information with a sensor-based motion planning system. The
contribution in the modeling aspect is a formulation of the detection and tracking of mobile objects and the mapping of the static structure in such a way that the nature (static/dynamic) of the observations is included in the estimation process. The algorithm provides a set of filters tracking the moving objects and a local map of the static structure constructed on line (download paper).
Scan Matching: Mobile robot local localization
This research addresses the scan matching problem
for mobile robot displacement estimation. The contribution is
a new metric distance and all the tools necessary to be used
within the Iterative Closest Point framework. The metric distance is defined in the configuration space of the sensor and takes into
account both translation and rotation error of the sensor. The
new scan matching technique ameliorates previous methods in terms of robustness, precision, convergence and computational
load. Furthermore, it has been extensively tested (download paper).
The role of the shape, kinematics and dynamics in the obstacle avoidance problem
Robotic Whelchair moving with Ego-Kinodynamic space (taking into account the exact robot shape, kinematics and dynamics).
Most collision avoidance methods do not consider the vehicle shape and its kinematic and dynamic constraints,
assuming the robot to be point-like and omnidirectional with
no acceleration constraints. The contribution of this research is
a methodology to consider the exact shape and kinematics, as well as the effects of dynamics in the collision avoidance layer, since the original avoidance method does not address them. This is achievable by abstracting the constraints from the avoidance methods in such a way that, when the method is applied, the constraints already have been considered. This work is a starting point to extend the domain of applicability to a wide range of collision avoidance methods (download paper).
Equipos para monitorización de Biosensores como ExG, GSR, TEMP, BVP, etc., de movimiento como EMG, IMUs, etc., de localización en interiores y exteriores, y tecnologías de Eye-Tracking..
¿Qué es la estimulación cognitiva? La estimulación cognitiva es un conjunto de técnicas y estrategias que tienen como objetivo la mejora del rendimiento y eficacia en el funcionamiento de capacidades cognitivas como la memoria, la atención o la percepción, entre otras. Según el tipo de persona al que va dirigido y el objetivo a conseguir podemos considerar dos tipos: el entrenamiento cognitivo o la rehabilitación cognitiva. El funcionamiento de la estimulación cognitiva se basa en la plasticidad cerebral, una propiedad del cerebro que le permite cambiar, no sólo aspectos cognitivos sino también emocionales. Existen diversas técnicas de estimulación cognitiva como las actividades o ejercicios que se pueden ver en numerosos talleres o las aplicaciones de Brain Training, pero todos son técnicas indirectas. Gracias a la neurotecnología se pueden entrenar de forma directa los ritmos que se asocian a las capacidades cognitivas de cada usuario.
.JPG)