This paper presents a computer vision-based approach of an automated stocktaking of servers in a data center using a camera and an inertial measurement unit. During the process, labels of servers are first detected and deprojected in an absolute frame of reference. The distance measure between servers are then computed and analyzed to state whether labels are missings. Experiments were carried out at OVHcloud’s experimental data center, using an iPhone to collect the data. iPhone sensor data was collected with the ARKit library and an average absolute location error of 3.16 mm was estimated for the worst situations.

In the context of the industry 4.0, production lines must be flexible, easily configurable and quickly adaptable to the variation of production. For assembly operations, which are usually done by special machines or human operators, a multirobot cell gives a more flexible solution. Robots trajectories are generated using a CAD model of the cell with an offline programming software. The drawback when using offline programming is the difference between the real trajectories of robots and the theoretical ones. In this paper, a method to calibrate multirobot cell is proposed. This calibration consist in identifying the real positions and orientations of each robot frame with respect to the other. This operation allows to improve the accuracy of the robotic cell by reducing the gap between the CAD model and the physical cell. The calibration is carried out by using a laser profiler and a reference sphere.

In this paper, a framework combining base placement, path planning and redundancy resolution for a mobile manipulator performing sequential tasks, such as screwing, drilling or assembling tasks, is proposed. For a set of given tasks, the outputs of the proposed algorithm meet the following practical performance indicators: minimization of the number of the base positions, minimization of the number of manipulator joint configuration changes, feasibility of each task considering the force capacity of the manipulator (which takes benefit of redundancy resolution) and path planning of the end-effector motion with obstacle avoidance. The effectiveness of the proposed approach is evaluated considering a 3 DOFs mobile platform and a 7 DOFs manipulator performing screwing in a application with 42 tasks.

Industrial robots are known to have good repeatability and poor accuracy. However, accuracy can be improved through calibration process. Different methods of calibration can be found in the literature. In this paper, a hybrid calibration approach was applied to improve the accuracy of a lightweight collaborative robot. The approach is based on an analytical model to compensate geometric errors and on an artificial neural network to compensate residual errors (stiffness, gear errors,…. etc). The suggested approach is analysed and optimised in the work. The approach can reduce the positioning error from 3.10mm to 0.13mm on a lightweight collaborative robot in a specific sub-workspace.

This paper addresses the problem of reducing the elastic deformations and the residual vibrations of flexible loads when they are handled by a robot manipulator. During the manipulation of the low-stiffness load, such as bumper or exhaust system in automotive industry, large motion-induced deformations and vibrations may be induced. These deformations will have detrimental effects on the settling time, on the accuracy and on the integrity of the operational process in a constrained environment. The trajectory shaping approaches, i.e smoothing filter or input shaping method are well-known solutions for the suppression of the residual vibrations at the end of a rest-to-rest motion. However, using trajectory shaping technique alone may not be sufficient to suppress the static elastic deformations during the transfer phase of the object. Thus, the main contribution of this paper is to propose a two stages feedforward based approach that combines trajectory shaping technique for vibrations reduction, with a deformation compensation trajectory. The latter exploits the rotation space of the manipulator to mitigate the flexural motion of the flexible load. The effectiveness of the proposed method is demonstrated by experimental validations on an industrial robot Kuka iiwa.