2. TWO BASIC RESEARCH HIGHLIGHTS
2. TWO BASIC RESEARCH HIGHLIGHTS
2.1. Vision basic motion control
Three major research directions concentrate a large part of CNRS and INRIA activities in cooperation with University laboratories : design and microsystems, machine intelligence and sensor based control.
Among the many subjects that relate to this last field, I believe that vision systems stands as a salient effort which gathers many laboratories work. Current research encompasses both vision-based navigation for mobile robots and object recognition and manipulation.
Specially worth to mention for the edge-cutting results obtained are the two following programmes:
ISIS Working Group on Vision Based Control
Within the framework of the French Research Grouping, ISIS (Image Processing and Scene Analysis), a working group comprising eight teams from CNRS, INRIA and University, carries on a coordinated program which emphasizes the role of two central ideas:
Systems and the algorithmics allowing to use uncalibrated cameras
Multi sensory fusion associating to a central vision system other sensing capacities comprising as well ranging and contact sensors.
The Esprit-IV reactive Long Term Research project, VIGOR (n° 26247)
VIGOR (Visually guided robots using uncalibrated cameras), a 3-year project, started in February 1998, is developing new techniques for visual guided control of robot manipulators using several uncalibrated cameras. The VIGOR consortium has six partners, 2 Universities (University of Cambridge and Hebrew University of Jerusalem), 2 research institutes (INRIA and IITB), and 2 industrial partners (Sinters and OSS). Sinters is a SME located in Toulouse which is specialized in robot manufacturing and hardware/software integration of robots and sensors. OSS is a shipyard located in Odense where large-scale robotic platforms are in operation for handling and welding of ship parts.
A succinct project summary follows.
Improving robot efficiency in advanced industrial automation requires the inclusion of sensory information at many levels, one of the most important is the on-line task control. Range finders, proximity sensors or wrist force sensors can only address the sensing problem in a reliable way when the robot is already at its target. Visual sensors can be used on-line through the so-called visual servoing approach. This technique, which consists of realizing an image-based feedback control loop is of increasing popularity. However, generally speaking, it is currently based on the use of a single camera and operates only on the premise that all the components are fully calibrated: camera, robot, and world. The related calibration procedures are tedious, non-flexible and expensive.
The goal of the project is to remove this calibration bottleneck in visually-guided robots, in order to perform industrial tasks with minimal modeling. The self-calibration techniques which will be used constitute the core of the project. They are based on the idea of extracting the required Euclidean information from a projective representation. Through VIGOR, it is expected to complete the mathematical background of the approach, to design the associated algorithms and to validate them on relevant industrial test-beds. Precisely, the project will demonstrate the feasibility of visual-based control loops, which include several uncalibrated cameras and robots with more than 5 joints in complex tool guidance tasks, such as inspection, grasping, and welding.
2.2. Service and Personal Robotics
This is certainly a front line field which is fast expanding in many folded ways. The field encompasses the thematics of Human Friendly Robotics in Japan and the views and approaches of Personal Robotics in the US.
Clearly under those sub-titles, we can find a large overlapping of novel concepts and research issues as well as application opportunities.
One of the major current efforts concerns in fact the cross fertilization between the three research communities, Europe, Japan and the US, throughout dedicated small workshops and symposia. France has contributed in four of those events, in two of them as main organizer, by chronological order:
First International Advanced Robotics Programme (IARP) WS on Humanoid and Human Friendly Robotics, Tsukuba, Ibaraki, Japan, October 26-27, 1998.
US / Europe WS on Personal Robotics, Toulouse, January 14-15, 1999.
The WS was organized by Jing Xiao, J. Canny for the US side, G. Giralt and R. Alami for the European side. It convened about 20 participants from Europe and 15 from the US. Four Experts from Japan were invited.
First International Advanced Robotics Programme (IARP) WS on Biologically Motivated Service Robotics, Jena, Germany, June 21-23, 1999.
Europe/Japan Symposium on Human-Friendly Robotics, Tokyo, November 8-9, 1999.
This symposium is jointly organized by France, H. Angelino (French Embassy), G. Giralt, C. Errani (Italian Embassy), H. Inoue and K. Tanie for Japan (it has also received partial support from the European Commission). It will convene Experts from Japan (about 20) and from Europe (16).
France's research activity in the field has still to be considered as emergent although showing promises and a strong thrust.
This activity can be well characterized by two projects with a very different thematic focus: the projects BIP 2000 and DILIGENT.
The following sub-sections briefly describe those projects.
The BIP2000 project involves for four years four laboratories:
BIP team INRIA Rhône-Alpes, coordinator
Laboratoire d'Automatique de Grenoble (ENSIEG)
Laboratoire de Mécanique des Solides de l'Université de Poitiers
Laboratoire de Metallurgie Physique de l'Université de Poitiers
BIP is aimed at the realization of the lower part of an anthropomorphic biped robot. The project covers mechanical design, control studies and computer architecture integration.
The robot includes two legs, two feet, a pelvis and a trunk. It has 15 active joints and 2 passive in the feet. It is equipped with 3 force sensors in each foot, an inclinometer and ultrasonic sensors.
The links geometry, the mass distribution, the kinematics and the capacities of the robot in terms of joint torques and velocities are close to the ones of humans.
At the present state of the project, the robot has been built and tested; the computer control architecture has been realized and connected with the robot ; basic control schemes are implemented and advanced ones have been tested in simulation.
Building on the large experience of the HILARE project and on the recent Esprit project MARTHA (multi-robot courtyard servicing), LAAS launched on January 1999 an ambitious project, DILIGENT, with the theme of Robots for Public and Personal Servicing and Assistance.
The project emphasizes Human-Robot Interaction both at the communication and physical levels where the machine is in close contact with the Human, either purposefully (assistance) or by accident.
DILIGENT encompasses all the topics linked to situations where the robot performs its tasks in interaction with humans. The human can be an operator, a user of a service performed by the robot or simply a user (a passer-by) of the same environment. More generally, the project tackles problems such as navigation in presence of humans, transporting humans, handling out objects to humans, manipulating and transporting loads in cooperation with humans, assisting handicapped or elderly humans ...
Its aim is to address the real scientific and multi-disciplinary challenge to devise "soft robots" able to "comply" with Humans and to effectively deal with the variety and dynamics of environments where the public is present.
The DILIGENT project is set in the experimental environment which comprises for indoors applications four fully instrumented wheeled mobile-robots, one of which carries a six d.o.f. arm.