Past Projects - Collaboration as
HANDLE: Developmental pathway towards autonomy and dexterity in robot in-hand manipulation, was a
Large Scale IP project coordinated by the university Pierre and Marie Curie of Paris and included a consortium formed by nine partners from six EU countries: France, UK, Spain, Portugal, Sweden, and Germany. The HANDLE project objective was to understand how humans perform the manipulation of objects in order to replicate grasping and skilled in-hand movements with an anthropomorphic artificial hand, and thereby move robot grippers from current best practice towards more autonomous, natural and effective articulated hands. The project implied not only focusing on technological developments but also working with fundamental multidisciplinary research aspects in order to endow the robotic hand system with advanced perception capabilities, high level feedback control and elements of intelligence that allow recognition of objects and context, reasoning about actions and a high degree of recovery from failure during the execution of dexterous tasks.
This collaborative project was funded by the European Commission within the Seventh Framework Programme FP7, as part of theme 2: Cognitive Systems, Interaction, Robotics, under grant agreement 231640.
Start date: The 2nd of February 2009
Finish date: The 1st of February 2013
Bayesian Approach to Cognitive Systems was an Integrated Project conducted under the Thematic Priority: Information Society Technologies - Sub-topic: Cognitive Systems - of the 6th Framework Program of the European Commission.
Project duration: 01/01/2006 – 28/02/2010
Project coordinated by ETH-Zurich and included a consortium formed by 9 partners from 5 countries.
Logic is both the mathematical foundation of rational reasoning and the fundamental principle of present day computing. However, logic, by essence, is restricted to problems where information is both complete and certain. Within the BACS project the Bayesian mathematical framework was proposed as an alternative computing framework capable to deal with incompleteness and uncertainty.
To demonstrate that Bayesian probability theory is a feasible alternative mathematical framework. To propose a new modeling methodology to both, better understand the cognition of living beings, and to build more efficient artificial cognitive systems. To validate the whole approach by demonstrating effective Bayesian cognitive models for living beings and artificial systems by producing results. This can clearly and objectively be assessed with new designed experimental paradigms.
The fundamental scientific work resulted in new technologies enabling intelligent embodied systems like robots or smart cars.
|Current Project - Participation as
Assisted Mobility Supported by Shared-Control and Advanced Human-Machine Interfaces
Funded By The Portuguese Foundation for Science and Technology. Start Date: 2013
This interdisciplinary project, aims to develop theoretical and experimental frameworks for the design, control and evaluation of a new generation of networked assistive mobile robots. This project addresses human-centered mobile robotics and will contribute for safer and more user-friendly mobile robotic assistants adapted to human environments. In partnership with the APCC (Associação de Paralisia Cerebral de Coimbra), we aim to contribute with results towards better mobility of people suffering from neuromotor disorders. Human factors will be taken into account, namely by benchmarking and evaluating the developed approaches by end users.
Human-machine interfaces are a central key in Human-centered mobile robotics since they define how users can input commands to steer the mobile robot. Users with severe motor disabilities need interfaces that can be controlled with minimal or zero muscular activity, such as brain-computer interfaces and eye-trackers. However, this type of interface provides information that is sparse in time and that may be unreliable. The use of multi-modal interfaces can help to increase both information transfer rate and reliability, but it is still not enough to operate efficiently a mobile robot (e.g., a wheelchair) in domestic environments. Therefore, human-machine collaborative navigation, accepting input commands from user is required to have a safer and efficient navigation. The development of 2D/3D perception/reconstruction is a major requirement for SLAM and to plan navigation trajectories in cluttered and dynamic environments.
To accomplish the project objectives, the following research topics are addressed:
1- 3D Reconstruction Algorithms
2- Real-time Dense Reconstruction
3- Visual Odometry from Planes
4- Signal Processing and Classification of Biosignals
5- BCI-based Human-Machine Interface (HMI)
6- Multimodal HMI and User’s State Characterization
7– Collaborative Control, Planning and Safety for Assistive Robot Navigation
8– Human-robot Interaction
10- Experimental Tests
Past Project - Collaboration as Researcher Fellow
Pedestrian Detection in Urban Challenging Scenarios
the various capabilities required by an intelligent vehicle perception
system, object detection is a key one to provide safe and reliable vehicle
autonomy or assistance (e.g. collision detection). Over the plethora of
world objects which a human being learns how to avoid in driving situations,
the human being himself is one of the most difficult for an intelligent
machine to detect. This is so because the human body can appear in several
poses, positions, forms, sizes and colors. Research in the area of
pedestrian detection has been intense in the last years in our research
group with state of the art results. However there are some 'critical'
situations, regarding pedestrian detection on urban scenarios that were not
satisfactory resolved. The key problem behind these critical situations
occurs when pedestrians appear in the scene partially occluded, close to
each other (cluttered situations) or in scenes with complex backgrounds
(problematical object-background segmentation). New challenges are now faced
by the research team on developing pedestrian detection systems suitable for
more real-world applications, focused on specific challenging urban
scenarios. These new approaches will embody scene contextual information
aiming to improve the detection performance in the above mentioned
challenging situations, while performing also the assessment of danger
situations. To accomplish the project objectives, the following tasks were
defined: 1) Laser and vision data segmentation; 2) Feature Extraction and
Feature Selection; 3) Neural Classifiers - Training; 4) Classifier fusion -
Trainable approaches; 5) Context-aware multi-sensor fusion; 6) Scenarios
definition, datasets and field tests.