In road layer compaction, it is essential that the right level of energy should be transmitted to the material, with a uniform distribution. This energy depends on the number of runs, or passes, of the machine. The main objective of CIRCOM is to assist the driver to perform the exact number of passes, at the right speed, everywhere on the surface to be compacted. From this improvement of quality in terms of level and uniformity of density, will result significant gains in road life-time, equipment operating time and material savings. To perform this task, it is essential to provide the operator and the system with an accurate and continuous location of the machine. The second objective is to record the actual work achieved by the compactor, in terms of trajectory and number of passes on every point, in order to feed the site database and to perform a global quality control at the site level. The main constraint is at the level of ergonomics; the system must be very simple and user-friendly.

FIRST is a mobile robotic system suited to the transport within hospitals of heavy trolleys such as those containing laundry, meal trays, drugs, etc. The system comprises a fleet of mobile robots, a central control station and several distributed control stations. The robots may use any route following a network of paths taught during a teleoperation phase. They navigate autonomously in the environment of the hospital, in particular in the presence of humans, be they hospital staff, patients or visitors, all in complete safety. Autonomous navigation requires the ability to react to unexpected events, hence the importance of a perceptual system which has two functions to recognise obstacles in order to avoid them in a safe and autonomous fashion, and to detect all situations which could endanger people and goods during the transport and handling of the trolleys. This paper presents the design principles and the performance of the perception system observed during site trials.

Mobile robotics is entering in a new phase. After using mobile robots in research laboratories, and factories it is now possible to consider the development of service mobile robots in public environments. Environments which are considerably more challenging due to their unpredictability and dynamic characteristics. The authors present in this paper the development of a prototype transport system dealing with heavy loads in hospitals. The system must perform tasks in or regular and timely fashion and be sufficiently predictable to be of use to the hospital staff. To solve such problem the authors propose a combination of planning and simulation for mission validation and central supervision for execution monitoring.

A model-based method for identifying convex or nonconvex polyhedral objects from a single image is described. An object is known by a region-edge-vertex model and an aspect graph. A few hypotheses are searched in a topological compatibility graph in which each node corresponds to a matching between chains of segments extracted from the image and model faces. The construction of this graph depends only on qualitative or topological criteria (number of edges for a face, syntactic description, perceptual organization, visibility, etc.). The search for hypotheses in the graph relies on the maximal cliques technique modified to deal with the global topological compatibility.>