This month, the special issue we handled together with L. Brayda was published by the International Journal of Social Robotics. You can find it here: http://rd.springer.com/article/10.1007/s12369-012-0150-2#
May
16
(Italiano) New contribution
A paper entitled:”EMBLEMATIC GESTURES RECOGNITION” was accepted and will presented during the ASME conference ESDA-ASME 2012, in France next July. This work was partly achieved during the PhD research of Ilaria Renna.
The paper abstract:
This paper presents a framework allowing emblematic
gestures detection, segmentation and their recognition for human-robots interaction purposes. This framework is based on a new coding of arms’ kinematics reflecting both the muscular activity of the performer and the appearance of arm seen by the recipient when a gesture is performed. Following that, gestures can be seen as sequences of torques activations leading arm’s parts to express a comprehensive meaning. In addition, these sequences have very stable topologies and shapes regardless to performers. This facilitates the generalization of the recognition process with a minimalistic learning effort for online usages. Promising results were obtained for a set of 5 classes of
gestures performed by 19 different persons.
May
16
Ilaria Renna finished her PhD thesis
Ilaria Renna worked with me and with C. Achard from University of Paris for her PhD thesis. Her work was dealing with gesture recognition for robots control. Ilaria presented successfully her work last week in Paris.
Congratulations Dotoressa Ilaria!
Thesis Abstract:
Robots are artificial agents that can act in humans’ world thanks to perception capacities. Especially in a Human-Robot interaction context, it is important to note that humans and robots share the same communication space. In particular robots companion are expected to communicate with humans in a natural and intuitive way: one of the most natural ways is based on gestures and reactive body motions. To make this friendly interaction possible, a robot companion has to be endowed with one or more capabilities allowing him to perceive, recognize and react to human gestures.
My PhD thesis has been focused on the design and the development of a gesture recognition system in a human-robot interaction context. This system includes a limbs-tracking algorithm that permits knowing human body position during movements and a higher-level module that recognizes gestures performed by human users. New contributions were made in both topics.
First, a new approach is proposed for visual tracking of upper-body limbs. Analyzing human body motion is challenging due to the important number of degrees of freedom of the articulated object modeling the upper body. To circumvent the computational complexity, each limb is tracked with an Annealed Particle Filter and the different filters interact through Belief Propagation. 3D human body is so described as a graphical model in which the relationships between the body parts are represented by conditional probability distributions. Pose estimation problem is thus formulated as a probabilistic inference over a graphical model, where the random variables correspond to the individual limb parameters (position and orientation) and Belief Propagation messages ensure coherence between limbs.
Secondly, we propose a framework allowing emblematic gestures detection and recognition. The most challenging issue in gesture recognition is to find good features with a discriminant power (to distinguish between different gestures) and a good robustness to intrinsic gestures variability (the context in which gestures are expressed, the morphology of the person, the point of view, etc.). In this work we propose a new arm’s kinematics normalization scheme reflecting both the muscular activity and arm’s appearance when a gesture is performed. The obtained signals are first segmented and then analyzed by two machine learning techniques: Hidden Markov Models and Support Vector Machine. The two methods are compared in a 5 classes emblematic gestures recognition task. Both systems show good performances with a minimalistic training database regardless to performer’s anthropometry, gender, age or pose with regard to the sensing system.
The work presented here has been done within the framework of a PhD thesis in joint supervision between the “Pierre et Marie Curie” University (ISIR laboratory, Paris) and the University of Genova (IIT-Tera department) and was labeled by the French-Italian University.
Mar
01
IEEE VR 2012
The next week, Orange County, (CA) will host the famous IEEE VR conference. I’m happy to be there to meet friends and colleagues. For sure, there will be some fascinating stuff, including our work with Djallil. I will present our findings around depth perception in real and virtual worlds. The conference site is the following:
Nov
19
First JNRI- Interactive Robotics – Paris Nov 21&22 2011
Next week, Paris and my colleagues in P&M Curie University will host the first French Workshop on Interactive Robotics (for more information http://jnri2011.isir.upmc.fr/). I’ll let you know about these days.
Oct
21
Two new papers in IEEE Robio 2011
Two other papers have been accepted in the IEEE Robio 2011 Conference:
1- Distributed Feature based RBPF Multi Robot SLAM, by S. R. A Jafri and R. Chellali
2-Multi-Objective Control through Evolutionary Neuro-Controller for Interactive Mobile Robot Manipulator, by Amal Meddahi and Ryad Chellali
Oct
11
New contribution
The paper entitled :
Frequency Modulation Based Vibrotactile Feedback, By P. Phong and R. Chellali, has been accepted for a presentation during the IEEE Robio 2011 Conference, that will take place in Dec 2011.
Feb
03
Launch
Bonjour à tous,
D’abord merci pour votre visite. Ce site vient d’etre lancé. J’espère en faire un lieu de discussions, d’échanges et de propositions pour un enrichissement mutuel. Pour l’instant, je n’ai pas encore mis en ligne mes documents, ni encore des tutoriels et autres bout de codes. Cela viendra très bientot, le temps que j’arrange mes accès ftp 
A bientot,