Table des matières

  • 1. Introduction
  • 2. Aldebaran
    • 2.1. Navigation
    • 2.2. Conception mécanique
  • 3. CEA
  • 4. Strate
  • 5. INRIA
    • 5.1. Manipulation mobile
    • 5.2. Commande référencée vision
  • 6. LIMSI
  • 7. Participation à des Workshops et des tables rondes

1. Introduction

Depuis son démarrage, le projet Romeo2 a donné lieu à 14 publications, dont une dans un journal international et une dans un livre. Les autres ont été présentées à des conférences internationales. Aldebaran et ses partenaires ont également été invités à présenter leurs travaux dans le cadre de Romeo2 lors de différents workshops internationaux.

2. Aldebaran

2.1.Navigation

George, L., & Mazel, A. (2013, October). Humanoid Robot Indoor Navigation Based on 2D Bar Codes: Application to the NAO Robot. In 2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids)-Proceedings.
This paper proposes an efficient method for localization and pose estimation for mobile robot navigation using passive radio-frequency identification (RFID). We assume that the robot is able to identify IC tags and measure the robot’s pose based on the relation between the previous and current location according to the IC tags. However, there arises the problem of uncertainty of location due to the nature of the antenna and IC tags. In other words, an error is always present which is relative to the sensing area of the antenna. Many researches have used external sensors in order to reduce the location errors, with few researches presented involving purely RFID driven systems. Our proposed algorithm that uses only passive RFID is able to estimate the robot’s location and orientation more precisely by using trigonometric functions and the IC tags’ Cartesian coordinates in a regular grid like pattern. The experimental results show that the proposed method effectively estimates both the location and the pose of a mobile robot during navigation.

Wirbel, E., Steux, B., Bonnabel, S., & de La Fortelle, A. (2013, April). Humanoid robot navigation: from a visual SLAM to a visual compass. InNetworking, Sensing and Control (ICNSC), 2013 10th IEEE International Conference on (pp. 678-683). IEEE.
In this paper, we present our work to try and implement a SLAM algorithm on a humanoid robot platform, the NAO robot produced by Aldebaran Robotics. We first start by testing a visual SLAM algorithm which uses keypoints as visual landmarks and tries to estimate their positions, and adapt it to the specific constraints of the platform: restricted CPU, monocular camera, low speed and drifting odometry. We conclude that running a full monocular visual SLAM on the robot is not yet available, but that some specific keypoints can be robustly tracked even while walking. Then we use them to derive the robot orientation and build a compass feature based on the robot camera, which can be used for example to ensure that the robot walks straight. Therefore we showed vision can be efficiently used to improve NAO’s navigation.

2.2.Conception mécanique

En collaboration avec le LPPA
N. Pateromichelakis, A. Mazel, M. A. Hache, T.Koumpogiannis, R. Gelin, B. Maisonnier and A.Berthoz, Head-eyes system and gaze analysis of the humanoid robot Romeo, In IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, IROS’14, Chicago, IL, September 2014.
In this work we present the head assembly and the gaze shifting capabilities of the bipedal humanoid robot Romeo. The purpose of the head system is to provide a reliable hardware platform for Human-Robot Interaction (HRI) applications, stereo vision based navigation, or gazing experiments, either as stand-alone version or in synergy with the body movements. Towards this purpose, the number of joints, the angular range, speed and acceleration of the eyes and neck rotations should be as close as possible to the human values. We present the mechatronic system of the head and neck accompanied by experimental results of head-fixed eye movements, solely head rotations, as well as head-eyes cooperative motion for large angles of gaze shifting. We compare the values achieved by the prototype, with those of the average adult human.

3. CEA

Yakymets, N., Dhouib, S., Jaber, H., & Lanusse, A. (2013, November). Model-driven safety assessment of robotic systems. In Intelligent Robots and Systems (IROS), 2013 IEEE/RSJ International Conference on (pp.1137-1142). IEEE.
Robotic systems (RSs) are often used for performing critical tasks with little or no human intervention. Such RSs must satisfy certain dependability requirements including reliability, availability, security and safety. In this paper, we focus on the safety aspect and propose a methodology and associated framework for safety assessment of RSs in the early phases of development. The methodology relies upon model-driven engineering approach and describes a preliminary safety assessment of safety-critical RSs using fault tree (FT) analysis (FTA). The framework supports a domain specific language for RSs called RobotML and includes facilities (i) to automatically generate or manually construct FTs and perform both qualitative and quantitative FTA, (ii) to make semantic connections with formal verification and FTA tools, (iii) to represent FTA results in the RobotML modeling environment. In the case study, we illustrate the proposed methodology and framework by considering a mobile robot developed in the scope of the Proteus and Romeo2 projects.

4. Strate

Ocnarescu O, Pain F, Robots sociaux : design et recherche aux frontières de l’expérimentation, in Workshop Affect, Compagnon Artificiel, Interaction (Wacai 2014), Rouen, France
Le poster décrit le processus d’évaluation, auprès d’une cible dite dépendante (âgées et/ou handicapés), des scénarios d’usage d’un robot social. Nous présentons dans un premier temps l’apport méthodologique du croisement de la méthode de design avec les protocoles expérimentaux de la recherche en robotique. Dans un deuxième temps nous proposons pour l’étape de l’évaluation un outil spécifique issu de la culture design: les « scénarios d’intention ». Ce sont des pré-scénarios d’usage qui utilisent des objets intermédiaires – prototypes non fonctionnels, et un medium propre au designer – la vidéo stop motion.

5. INRIA

5.1.Manipulation mobile

Escande, A., Mansard, N., & Wieber, P. B. (2014). Hierarchical quadratic programming: Fast online humanoid-robot motion generation. The International Journal of Robotics Research, 0278364914521306.
Hierarchical least-square optimization is often used in robotics to inverse a direct function when multiple incompatible objectives are involved. Typical examples are inverse kinematics or dynamics. The objectives can be given as equalities to be satisfied (e.g. point-to-point task) or as areas of satisfaction (e.g. the joint range). This paper proposes a complete solution to solve multiple least-square quadratic problems of both equality and inequality constraints ordered into a strict hierarchy. Our method is able to solve a hierarchy of only equalities 10 times faster than the iterative-projection hierarchical solvers and can consider inequalities at any level while running at the typical control frequency on whole-body size problems. This generic solver is used to resolve the redundancy of humanoid robots while generating complex movements in constrained environments.

5.2.Commande référencée vision

N. Cazy, C. Dune, P.-B. Wieber, P. Robuffo Giordano, F. Chaumette. Pose Error Correction For Visual Features Prediction. In IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, IROS’14, Chicago, IL, Septembre 2014.
Predicting the behavior of visual features on the image plane over a future time horizon is an important possibility in many different control problems, for example when dealing with occlusions (or other constraints such as joint limits) in a classical visual servoing loop, or also in the more advanced model predictive control schemes recently proposed in the literature. Several possibilities have been proposed to perform the initial correction step for then propagating the visual features by exploiting the measurements currently available by the camera. But the predictions proposed so far are inaccurate in situations where the depths of the tracked points are not correctly estimated. We then propose in this paper a new correction strategy which tries to directly correct the relative pose between the camera and the target instead of only adjusting the error on the image plane. This correction is then analyzed and compared by evaluating the corresponding improvements in the feature prediction phase.

6. LIMSI

International book
Buendia, L. Devillers (2013) From informative cooperative dialogues to long-term social relation with a robot, in IWSDS 2012 book: Towards a Natural Interaction with Robots, Knowbots and Smartphones, Putting Spoken Dialog Systems into Practice, edition Springer (2013)
A lot of progress has been made in the domain of human-machine dialogue, but it is still a real challenge and, most often, only informative cooperative kind of dialogues are explored. This paper tries to explore the ability of a robot to create and maintain a long term social relationship through more advanced dialogue techniques. We expose the social (Goffman), psychological (Scherer) and neural (Mountcastle) theories used to accomplish such kind of complex social interactions. From these theories, we build a consistent model, computationally efficient to create a robot that can understand the concept of lying, and have compassion: a robotic social companion.

(Soury et al., 2013) M. Soury, C., Gossart, M., Adda, L., Devillers (2013) “A tool to elicit and collectmulticultural and multimodal laughter”, Show & Tell, Proceedings of Interspeech, 2013.
We present the implementation of a data collection tool of multicultural and multimodal laughter for the 14th Interspeech conference. The application will automatically record and analyze audio and video stream to provide real-time feedback. Using this tool, we expect to collect multimodal cues of different kind of laughers elicited in participants with funny videos, as well as jokes and tongue-twisters games with the Nao robot.

(Soury & Devillers, 2013), M. Soury, L. Devillers (2013), “Nao makes me laugh: the impact of humor in human-robot interactions”, Workshop at IROS, Tokyo.
Which are the aspects of human-likeness that are more relevant for human-robot interaction? We present an experiment using humor in interactions with Aldebaran robot Nao to make users laugh. Our aim is to evaluate the correlations between the user’s profile (gender, cultural background, sense of humor, personality traits) and his propensity to laugh with a humanoid robot. We analyze audio data collected during the Interspeech 2013 conference. Some correlations appear, suggesting the interest of a priori knowledge of the user to make him laugh. This work will provide new insight on the building of human-robot relationships in the French project ROMEO2.

(Devillers & Soury, 2013a) L. Devillers, M. Soury (2013) A social interaction system for studying humor with the robot NAO, session demonstration, ICMI 2013.
The video of our demonstrator will present a social interaction system for studying humor with the Aldebaran robot NAO (Project ROMEO2). Our application records and analyzes audio and video stream to provide real-time feedback. The participants were involved in a verbal exchange with NAO, including tongue-twisters games and jokes, as well as witty remarks and laughs from the robot. Using this dialog system during show & tell sessions at Interspeech 2013, we have collected different kind of laughter (positive and negative) from 45 subjects. The conversation data captured is used here to study subject behaviors from various personalities and cultural backgrounds.

(Devillers & Soury, 2013b) L. Devillers, M. Soury (2013) Prosody analysis of positive and negative laughter: a multicultural study, 4ieme Colloquium of speech prosody Brasil.
We present a prosodic analysis of a data collection of multicultural laughter. Our application records and analyzes audio stream. Using this tool during show & tell sessions of Interspeech2013, we collected different kind of laughter (positive and negative) elicited in participants with funny videos, tongue-twisters games and jokes in interaction with the robot NAO. The collected corpus is used here for studying prosodic features for positive and negative laughter from various cultural backgrounds.

(Soury & Devillers, 2014) M. Soury, L. Devillers (2014) Smile and Laughter in Human-Machine Interaction: a study of engagement, LREC 2014
This article presents a corpus featuring adults playing games in interaction with machine trying to induce laugh. This corpus was collected during Interspeech 2013 at Lyon to study behavioral differences correlated to different personalities and cultures. We first present the collection protocol, then the corpus obtained and finally different quantitative and qualitative measures. Smiles and laughs are types of affect bursts which are defined as short emotional “non-speech” expressions. We correlate here smile and laughter with personality traits and cultural background. Our final result is to propose a measure of engagement deduced from those affect bursts.

(Sehili et al., 2014) M. Sehili, F. Yang, V. Leynaert, L. Devillers, (2014), A corpus of social interaction between Nao and elderly people, 5th International Workshop on EMOTION, SOCIAL SIGNALS, SENTIMENT & LINKED OPEN DATA ( ES3 LOD2014), LREC 2014
This paper presents a corpus featuring social interaction between elderly people in a retirement home and the humanoid robot Nao. This data collection is part of the French project ROMEO2 that follows the ROMEO project. The goal of the project is to develop a humanoid robot that can act as a comprehensive assistant for persons suffering from loss of autonomy. In this perspective, the robot is able to assist a person in their daily tasks when they are alone. The aim of this study is to design an affective interactive system driven by interactional, emotional and personality markers. In this paper we present the data collection protocol and the interaction scenarios designed for this purpose. We will then describe the collected corpus (27 subjects, average age: 85) and discuss the results obtained from the analysis of two questionnaires (a satisfaction questionnaire, and the Big-five questionnaire).

7. LAAS

M. Garcia, O. Stasse, J.B. Hayet, C. Esteves and J.P. Laumond, Vision-Based Motion Primitives for Reactive Walking, IEEE-RAS Int. Conf. on Humanoid Robots 15-17 Octobre 2013, Atlanta (USA),
This paper presents a method for reactive walking allowing visual servoing and adaptation of footsteps trajectories in real-time. This is done by building upon recent advances in the fields of optimal control for a walking pattern generator [1] and planning for a nonholomic robot with field-of-view constraints [2]. Herdt et al. [1] provided a controller where a humanoid robot is driven by its Center-of-Mass (CoM) velocity. A natural extension, proposed in [3], is to control a humanoid robot directly by using vision-based control techniques. However, the trajectories realized by the robot in that case are generated to minimize the distance in the image feature space and might create unnecessary motion in the space of the footprints. This paper aims at solving this problem by making the CoM follow a convenient space of trajectories for which the robot behaves overall better. The motion primitives obtained in [2] provide the space of trajectories used in this work.

A. Orthey, O. Stasse, Towards Reactive Whole-Body Motion Planning in Cluttered Environments by Precomputing Feasible Motion Spaces, IEEE-RAS Int. Conf. on Humanoid Robots 15-17 Octobre 2013, Atlanta (USA),
To solve complex whole-body motion planning problems in near real-time, we think it essentials to pre-compute as much information as possible, including our intended movements and how they affect the geometrical reasoning process. In this paper, we focus on the pre-computation of the feasibility of contact transitions in the context of discrete contact planning. Our contribution is twofold: First, we introduce the contact transition and object (CTO) space, a joint space of contact states and geometrical information. Second, we develop an algorithm to pre-compute the decision boundary between feasible and no feasible spaces in the CTO space. This boundary is used for online-planning in classical contact-transition spaces to quickly prune the number of possible future states. By using a classical planning setup of A* together with a l2-norm heuristic, we demonstrate how the prior knowledge about object geometries can achieve near real-time performance in highly-cluttered environments, thereby not only outperforming the state-of-the-art algorithm, but also having a significantly lower model sparsity.

Y. Huang, P. Souères, J. Li, Contact Dynamics and Coupled Stability of Massage Compliant Robotic Arm with Impedance Controller, IEEE Int. Conf. on Robotics and Automation, Honk- Hong, China, May 2014
In this paper, contact dynamics of robot massage is described by the port-Hamiltonian modelling approach. In order to capture accurately the inherent characteristics of the human body in lumped-parameter manners, the conventional linear Kelvin-Voigt models are replaced by the nonlinear Hunt-Crossley models. As an application of the contact dynamics, coupled stability of compliant robotic arm with impedance control is theoretically analyzed from energetic viewpoints. Experiments are done to verify the massage stability. The proposed contact dynamics evidently has great potential on performance improvement of robot massage, which will be our research subject.

M. Benallegue, J.P. Laumond and A. Berthoz, A head-neck-system to walk without thinking, LAAS Report, Submitted to PLOS ONE, June 2014.
Most of the time, humans do not watch their steps when walking, especially on even grounds. They walk without thinking. How robust is that strategy? How rough can be the terrain to walk this way? Walking performance depends on the dynamical contribution of each part of the body. For instance, arms swinging is a noticeable factor of gait stability (Sjoerd et al. (2010) J Exp Bio 213(23):3945-3952). While it is well known that the head is stabilized during the motions of humans and animals (Berthoz (2002) The Brains Sense of Movement, Harvard Univ Press), its contribution to walking equilibrium remains unexplored. To address the question we operate a simplified walking model inspired by biped robots (Collins et al. (2005) Science, 307(5712):1082- 1085). We show that, when equipped with a stabilized head-neck system, biped robots are drastically more robust to perturbations. Our results indicate that the head-neck system contributes significantly to the dynamics of walking and hence to the balance, by storing an amount of the kinematic energy, in order to restore it at a relevant phase of the gait. This study is the starting point of a wider research on the involvement of vertebral limbs in the mechanics and control of the human steady gait and the benefits of such simple control schemes capable to produce complex behaviors.

O. E. Ramos, M. Garcia, N. Mansard, O. Stasse, J.B. Hayet, P. Souères, Towards Reactive Vision-Guided Walking On Rough Terrain: An Inverse-Dynamics Based Approach, International Journal of Humanoid Robtics, 2014, in press.
This work presents a method to handle walking on rough terrain using inverse dynamics control and information from a stereo vision system. The ideal trajectories for the center of mass and the next position of the feet are given by a pattern generator. The pattern generator is able to automatically find the footsteps for a given direction. Then, an inverse dynamics control scheme relying on a quadratic programming optimization solver is used to let each foot go from its initial to its final position, controlling also the center of mass and the waist. A 3D model reconstruction of the ground is obtained through the robot cameras located on its head as a stereo vision pair. The model allows the system to know the ground structure where the swinging foot is going to step on. Thus, contact points can be handled to adapt the foot position to the ground conditions.

8. Participation à des Workshops et des tables rondes

Le projet ROMEO2 a également été présenté à l’occasion de plusieurs workshops auxquels les participants du projet étaient invités:

  • 28 juin 2013 : Worshop CEA LETI « Imagine Imaging » – Aldebaran présente les besoins spécifique en perception pour les robots humanoïdes de service.
  • 27 aout 2013 : Interspeech 2014 – Participation à la table ronde sur les besoins de
    traitement du langage naturel (Aldebaran, Google, Amazon, Apple…)
  • Septembre 2013: Geneva Bridge meeting on vocal parameters (Geneva,) «Benchmarking of a common minimalistic set of vocal parameters» – présentation du LIMSI
  • Novembre 2013 : Dagstuhl_Seminar13451 (Dagstuhl allemagne,) «Computational Audio Analysis» – présentation du LIMSI
  • 8 novembre Z013 : Conférence ICT organisée par la commission européenne à Vilnius –Aldebaran est invité à présenter les enjeux du transfert technologique entre recherche et industrie.
  • 14 février 2014 : International Conference « Going Beyond the Laboratory – Ethical and Societal Challenges for Robotics », Hanse-Wissenschaftskolleg, Delmenhorst, Allemagne – Aldebaran présente les aspects éthiques de la robotique d’assistance aux personnes âgées.
  • 4 mars 2014 : HRI, Bielefeld, Allemagne – Workshop sur la sûreté de fonctionnement, Aldebaran et le CEA présentent les travaux sur le sujet dans le cadre de Romeo2.
  • 13 mars 2014 : European Robotic Forum 2014, Rovereto, Italie – Aldebaran présente les applications d’assistance aux personnes âgées

9. Organisation des Workshops et Les rapports produits

  • International Workshop on Developmental Social Robotics (DevSoR): Reasoning about Human, Perspective, Affordances and Effort for Socially Situated Robots
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2013
    7 Nov 2013 Tokyo (Japan) http://socialapprob14.sciencesconf.org/
  • Workshop on Societal Applications of Humanoid Robots European Robotics Forum (ERF) 2014, Rovereto, Italy 13 Mar 2014 Rovereto (Italy) http://devsor2013.sciencesconf.org/

10. References

[1] A. Herdt, H. Diedam, P.-B. Wieber, D. Dimitrov, K. Mombaur, and M. Diehl, “Online walking motion generation with automatic footstep placement,” Advanced Robotics, vol. 24, no. 5-6, pp. 719–737, 2010.
[2] P. Salaris, D. Fontanelli, L. Pallottino, and A. Bicchi, “Shortest paths for a robot with nonholonomic and field-of-view constraints,” IEEE Trans. on Robotics, vol. 26, pp. 269–281, 2010.
[3] M. Garcia, O. Stasse, and J.-B. Hayet, “A watching-while-walking pattern generator,” in IROS, 2013, p. submitted.