Josep Fernández

Online Competitions: An Open Space to Improve the Learning Process

Experimentation and practical work, which are usually accomplished in a laboratory, are the basics of technological fields. Laboratory activities enable students to acquire methodologies, work habits, knowledge, and experience of equipment operation, in conditions as near as possible to their future professional activities. The evolution of communication and information technologies opens new possibilities in educational methods. This article describes a project that aims to facilitate the use of real robots in an educational laboratory via Web, allowing users to learn different robotics aspects while performing a competition. Students can remotely program several robots to participate in games to accomplish a set of goals in a remote stadium (the RoboStadium). To facilitate the use of robots, the online robot stadium provides a set of training resources. Having these resources, previous knowledge on robotics is not required to use the system. Since robotics is a multidisciplinary field (mechanics, electronics, control, mathematics, computers, etc.), students of different degrees can take advantage of the presented system. Researchers of two Spanish universities are participating in this project, which provides robotics telelaboratories via Web.

Autonomous navigation in ill-structured outdoor environment

Presents a methodology for autonomous navigation in weakly structured outdoor environments such as dirt roads or mountain ways. The main problem to solve is the detection of an ill-defined structure-the way-and the obstacles in the scene, when working in variable lighting conditions. First, we discuss the road description requirements to perform autonomous navigation in this kind of environment and propose a simple sensors configuration based on vision. A simplified road description is generated from the analysis of a sequence of color images, considering the constraints imposed by the model of ill-structured roads. This environment description is done in three steps: region segmentation, obstacle detection and coherence evaluation.

Remote Programming of Network Robots Within the UJI Industrial Robotics Telelaboratory: FPGA Vision and SNRP Network Protocol

This paper presents the UJI Industrial Robotics Telelaboratory, which lets Ph.D. and Masters degree students perform robotics and computer vision tele-experiments. By using this system, students are able to program experiments remotely via the Web, in order to combine the use of a field-programmable gate array (FPGA) to provide real-time vision processing, a conveyor belt, and a Motoman industrial manipulator. This paper introduces the novel SNRP protocol (i.e., Simple Network Robot Protocol), which permits the integration of network robots and sensors within an e-learning platform in a simple and reliable manner. As long as the students are able to interact remotely with a real robotic scenario, this system helps students very much to learn robotics control techniques like visual servoing control, vision for industrial applications, and robotics manipulation. The various components of the system are connected via a 100BaseT Ethernet network and follow the SNRP protocol, which grants simple access to generic networked devices using enhanced HTTP-based connections. Moreover, the whole telelaboratory is connected to the Internet through a router that permits the user to control the networked devices according to security constraints. The SNRP architecture is compared with a Common Object Request Broker Architecture-based approach, which was used in a previous telelaboratory. This paper describes two principle contributions: the design of a novel SNRP network architecture for the intercommunication of robots and sensors within an e-learning telelaboratory and the integration of a programmable FPGA vision system, which allows students to learn not only robotic techniques but also the design of high-performance circuits for industrial vision applications.

Visual human machine interface by gestures

Like oral communication, gestures are a natural way to carry out human machine interface. In the early days of robotic systems, human gesture was used to control robot movements by means of a master-slave structure. In spite of the use if robot programming languages, manual control is the most reliable way to carry out complex tasks in unstructured environments. In these situations, a non-contact, passive and remote system can be helpful to control a teleoperated robot by means of human gestures. In this paper, a vision system able to detect, locate and track the head and hands of a human body is presented. The system uses several calibrated cameras placed around the operator scenario to locate the body parts of a person in 3D. The system combines different computer vision techniques to increase the reliability of the body parts detection: image movement detection, user skin colour segmentation and stereo. The data provided by these modules are focused looking for coherence according to the human body dimensions. With the scheme proposed it is possible to obtain a low-cost real-time system for human computer interfacing based in a natural way of communication (gestures). Civil area such as big robots in shipyards, mines, public works or cranes is some possible applications.

Increasing autonomy within underwater intervention scenarios: The user interface approach

The present work represents working progress for designing a Graphical User Interface (GUI) within an ongoing research project named RAUVI (e.g. Reconfigurable AUV for Intervention Missions). This GUI should help the user to identify the target using images compiled by the I-AUV through a previous survey stage. After that, the user is able to specify the most suitable intervention task selected among a set of predefined ones. Thus, a very intuitive and user-friendly interface has been designed, enabling a non qualified user to succeed in the specification of an intervention mission. Furthermore, some implementation details and their performance about different facilities integrated within this GUI to assist the user in the required specification of underwater intervention missions will be addressed.

GRASPER: A Multisensory Based Manipulation System for Underwater Operations

This paper presents the progress that has been made recently in the TRITON project. The TRITON project is an on going research project being carried out in Spain which has as principal objective the production of an AUV capable of autonomous underwater interventions. The GRASPER sub-project focuses on developing the necessary manipulation skills. Currently, a lot of research in the underwater robotics context is developing increasing levels of autonomy for all kinds of intervention operations, which always require some kind of physical interaction. However, if autonomous robotic manipulation on land remains a relatively undeveloped field, the situations is at an even more primitive stage in underwater scenarios where currently the systems are tele-operated by an expert user from a surface vessel. Only very few underwater systems have the capacity to carry out manipulation without any kind of umbilical cables teleoperating these actions. In particular, this work introduces a new approach for increasing the autonomy levels of an underwater manipulation system, discussing also preliminary results. In order to test this concept, different objects, without predefined models, are approached and recovered from the bottom in water tank conditions. To achieve this purpose, a scan of the scene is performed using a structured laser beam attached to the forearm of the manipulator. At the same time, a digital video camera is used to capture the scene with the laser beam projected onto the object. The laser stripes are triangulated to obtain a 3D point cloud. Moreover, the underwater robot gripper is provided with strain gauge tactile sensors, which enable the execution of a more reliable grasp. On the other hand, the process is shown inside an underwater simulator previously developed, named UWSim, acting in this case as a virtual representation of the real environment. This virtual representation allows the user to specify the grasp, highlighting how the virtual grasp will be defined for the selected target. The feasibility and reliability of the underwater manipulation system is demonstrated though the experimental results.

End-to-end congestion control protocols for remote programming of robots, using heterogeneous networks: A comparative analysis

There are many interesting aspects of Internet Telerobotics within the network robotics context, such as variable bandwidth and time-delays. Some of these aspects have been treated in the literature from the control point of view. Moreover, only a little work is related to the way Internet protocols can help to minimize the effect of delay and bandwidth fluctuation on network robotics. In this paper, we present the capabilities of TCP, UDP, TCP Las Vegas, TEAR, and Trinomial protocols, when performing a remote experiment within a network robotics application, the UJI Industrial Telelaboratory. Comparative analysis is presented through simulations within the NS2 platform. Results show how these protocols perform in two significant situations within the network robotics context, using heterogeneous wired networks: (1) an asymmetric network when controlling the system through a ADSL connection, and (2) a symmetric network using the system on Campus. Conclusions show a set of characteristics the authors of this paper consider very important when designing an End-to-End Congestion Control transport protocol for Internet Telerobotics.

Open laboratory for robotics education

Laboratories are key components in the learning process of applied matters. The laboratory enables students to acquire methodologies, work habitude, knowledge on equipment operation and experience, in conditions as near as possible to their future professional activity. The evolution of communication and information technologies opens new possibilities in educational methods. The purpose of this paper is to present a Web based system for the implementation of a robotics laboratory with didactic finalities. The laboratory is to be accessible indifferently and simultaneously, in situ or via Internet. The system presented aims at providing access to the laboratory at any time, from everywhere, without space problems, paying special attention to safety requirements. For these reasons we call it an Open laboratory.

A recurrent neural network approach for 3D vision-based force estimation

Robotic-assisted minimally invasive surgery has demonstrated its benefits in comparison with traditional procedures. However, one of the major drawbacks of current robotic system approaches is the lack of force feedback. Apart from space restrictions, the main problems of using force sensors are their high cost and the biocompatibility. In this work a proposal based on Vision Based Force Measurement is presented, in which the deformation mapping of the tissue is obtained using the ℓ2 - Regularized Optimization class, and the force is estimated via a recurrent neural network that has as inputs the kinematic variables and the deformation mapping. Moreover, the capability of RNN for predicting time series is used in order to deal with tool occlusions. The highlights of this proposal, according to the results, are: knowledge of material properties are not necessary, there is no need of adding extra sensors and a good trade-off between accuracy and efficiency has been achieved.

Augmented reality to assist teleoperation working with reduced visual conditions

Teleoperation in harsh environments has to tackle the problem of working with images of poor quality, as the visual feedback means for the human operator. This paper describes a procedure for image augmentation, based on the models of the scene elements, which are built from the images acquired in a previous phase, before the execution of the task, when the visual environment conditions are still good enough.