Search

Field experiments in underwater robotics research require a big amount of resources in order to be able to test the system in sea conditions. Moreover, sea conditions are constantly changing making impossible to reproduce specific situations. For these reasons, testing, comparing and evaluating different algorithms in similar conditions is an utopic situation. In order to deal with this, a framework that mixes real experiments and a simulated environment is proposed to allow objective comparison of algorithms in an scenario as close as possible to field experiments. This is possible using real sensors in a controllable environment, for instance a water tank, adding simulated hostile conditions difficult to reproduce in a controlled environment such as water turbidity, composing a Hardware In the Loop (HIL) framework. This framework is formed by UWSim, an underwater simulator, and a benchmarking module able to measure the performance of external software. This setup is used in a search and recovery use case to compare different tracking algorithms, predicting the effect of water turbidity in them. The results allow to choose the best option without the need of dealing with field experiments.

This paper presents recent progress concerning benchmarking issues in the underwater robotics manipulation context. After a very intensive 6-years period of work, under several funding research projects, all of them in the aforementioned area, a strong know-how has been developed. As part of this expertise, a new underwater simulation tool has been implemented. This platform enables the integration, simulation, comparative analysis and experimentation on real data and a detailed characterization of the results, using as input a simple web-based user interface. In fact, our previous experience in related research projects has evidenced the necessity of testing, comparing and evaluating different algorithms in similar conditions. So, the similarity between the virtual scenario, where the benchmarking will be performed, and the real one, will determine the quality of the results. In that sense, a methodology is presented which updates the scenario with real information each time a real trial is performed. Benchmarking, a very active robotic area in nowadays, is the underlying problem to solve. In summary, the main functionalities for benchmarking available in the simulation platform will be highlighted, by using some case studies concerning object tracking under visibility changes, object tracking under variable water current and 3D reconstruction subject to different optical conditions.

The long term of this ongoing research has to do with increasing the autonomy levels for underwater intervention missions. Bearing in mind that the specific mission to face, has been the intervention on a panel, in this paper some preliminary results in water tank conditions are presented by using the real mechatronics and the panel mockup. Furthermore, some details are highlighted describing the methodology implemented for the required visually- guided manipulation algorithms, and also a roadmap explaining the different testbeds used for experimental validation, in increasing complexity order, are presented. It is worth mentioning that the aforementioned results would be impossible without previous generated know-how for both, the complete developed mechatronics for the autonomous underwater vehicle for intervention, and the required 3D simulation tool. In summary, thanks to the implemented approach, the intervention system is able to control the way in which the gripper approximates and manipulate the two panel devices (i.e. a valve and a connector) in autonomous manner and, preliminary results demonstrate the reliability and feasibility of this autonomous intervention system in water tank conditions.

In order to design a Robotics Tele-Laboratory that permits simultaneous remote control and programming of several robots, we must take into account multiple aspects. One of the most important refers to the System Architecture and Communication Technology that permits such a level of multirobot interaction. In this paper we present the system architecture that has been used in our laboratory to let users program remotely two educational and two industrial robots through the same web-based system. Experimental results show different alternatives to organize the architecture and focus on the system performance aspects.

This paper describes a complete vision-based online robot system that allows controlling both an educational and an industrial robot via web. We address some of the limitations of current similar systems particularly concerning the user interface. Some of its novel features are: its adjustable autonomy, so that the user can decide the right level of interaction from high-level voice commands down to mouse clicks, reducing in this way the cognitive fatigue resulting from remote operation; the interface is predictive, by using a 3D virtual environment endowed with augmented reality capabilities, the user can predict the results of the actions before sending the command to the real robot. Thus, network bandwidth is saved and off-line task specification is possible. This high level interaction is possible thanks to some built-in modules for performing basic tasks such as automatic object recognition, image processing, autonomous grasp determination and speech recognition. Finally, the system has been tested by means of an application in the Education and Training domain. One hundred undergraduate students have been using the web-based interface in order to program “Pick and Place” operations with the system. The results show performance, statistics, connection rates, and the students' opinions, as a way of evaluating the convenience and usability of the user interface.

A new strategy is presented to simplify the real-time determination of grasping points in unknown objects from 2D images. We work with a parallel-jaw gripper and assume point contact with friction, taking into account stability conditions. This strategy is supported by a new tool that permits to establish a supervisor mechanism with the aim to seek grasping points from geometric reasoning on the contours extracted from 2D images captured by the system in execution time. This approach is named “curvature-symmetry fusion” (CSF) and its objective is to integrate curvature and symmetry knowledge in a single data structure to provide the necessary information to predict the more suitable directions used by a supervisor mechanism described below. These algorithms have been implemented on a SCARA manipulator with one end point mounted camera. Visual feedback was used in the control system and the total time for the execution is about 2 or 3 seconds in our inexpensive prototype, making real applications feasible.