Ponència presentada en la 19th International Conference on Informatics in Control, Automation and Robotics. \n14-16 de juliol de 2022, Lisboa, Portugal.

Children with a diagnosis of Autism Spectrum Disorder (ASD) have serious difficulties in the development of their communicative and social skills. In recent years, robots have been tested in the therapy of autistic children as a promising tool for increasing their interest and motivation in the activities. In this paper we present the results of a pilot study with playful robot-child interaction developed for the therapy of diagnosed children aged between 3 and 5. The children were separated into an intervention and a control group. Their progress in development was measured before and after the intervention. Although the experience was unanimously considered as positive by parents and caregivers, we have found no significative differences between the intervention and control groups. Some observed trends demand more caution and additional studies for identifying not only the advantages but also the possible pitfalls of the use of robots in the therapy of autistic children.

RPN (Robotic Programming Network) is an initiative to bring existing remote robot laboratories to a new dimension, by adding the flexibility and power of writing ROS code in an Internet browser and running it in the remote robot with a single click. The code is executed in the robot server at full speed, i.e. without any communication delay, and the output of the process is returned back. Built upon Robot Web Tools, RPN works out-of-the-box in any ROS-based robot or simulator. This paper presents the core functionality of RPN in the context of a web-enabled ROS system, its possibilities for remote education and training, and some experimentation with simulators and real robots in which we have integrated the tool in a Moodle environment, creating some programming courses and make it open to researchers and students (http://robotprogramming.uji.es).

When applying service robotic tasks using sensor based control, a classical exponential decrease of the error is usually used in the control laws which can reduces the performance of the executed task. In fact, due to this choice, the convergence time greatly increases especially at the end of the process. To ameliorate the performance of such tasks, we present in this paper two new error regulation strategies to accelerate the service tasks execution. These propositions are compared with the classical one in the case of performing autonomous object's manipulation tasks using real-time visual servoing. The Model Based Tracking method is used to apply head servoing and grasping of different objects using Nao humanoid robot.

A practical solution for the development of real-world multi-robot applications is presented. It consists of a robot middleware (Player) and a multi-agent development environment (JADE). Such components provide off-the-shelf tools which allow a straightforward implementation of indoor localization and navigation tasks for a team of mobile robots. Such integration combines proven mobile robot algorithms with a distributed infrastructure, and extends the capabilities from a robot alone to a whole team of robots, thus allowing the development of cooperative applications. As a proof of concept, an auction-like goal assignment task is presented: the robot team is given a goal, and each robot proposes an estimated cost for achieving it, then the best proposal is selected. Most of the control flow is automated by the JADE standard interaction protocols. Experimental evaluation demonstrates the advantages of combining both frameworks, for a practical yet sound development of multi-robot applications.

In order to have an operative system with multiple robots each one with its own configuration, it is important to establish cooperative mechanisms that allow the robots with less sensory power to get helped from the robots with more sensory power. In this context, it is important that the cooperation is done in a way that allows each robot to take advantage of the particular resources of the other robots in the system. This paper presents an application where a group of robots must cooperate in order to safely navigate through an unknown environment. In this application, only one robot has a camera mounted on it and none of the other robots have any type of sensor. The robot with the camera calculates the optical flow values from the images that it gets from the camera, and from these values calculates the ldquotime to contactrdquo values that determine the time that the robot has before colliding with an obstacle in front of it. This information is shared among the team so that any robot can navigate without colliding with the obstacles.

Mobile robots are nowadays capable of navigating in a semi-structured environment, either alone or in formations. Dealing with mobile obstacles, e.g. persons, in everyday environments poses additional challenges which are being addressed by the research community. This paper presents an experiment with a set of robots -acting as a swarm- and one person. The aim of such robot-human squad is to explore an unmapped area indoors. The swarm is programmed such that obstacle avoidance, robot avoidance and human avoidance is combined with staying in the vicinity of the human and gradually proceeding towards the end point. The robots are provided with enough sensors to perform avoidance, and determine/estimate the distance to the human. Communication is one-way only, from robots to human. The aim of the experiment is to provide insights about the real problems of the multirobot system when dealing with a non-expert person in a cooperative exploration task.

This paper describes how the use of panoramic cameras can dramatically simplify safety issues for a robot arm moving in close proximity to human beings, since they can simultaneously observe a 360° field of view. We present in this context an approach to visual servoing in which both the manipulator as well as any other moving object are tracked. Reliability and robustness are enhanced by adaptative background modelling and global illumination change detection.

A practical solution based on multi-agent protocols for the development of real-world multi-robot applications is presented. FIPA standard protocols implemented by the JADE library provide the standard functionality for a number of tasks. Robot behaviors are built upon the player middleware. Such components provide off-the-shelf tools which allow a straightforward implementation of indoor localization and navigation tasks for a team of mobile robots. Such integration combines proven mobile robot algorithms with a distributed infrastructure, and extends the capabilities from a robot alone to a whole team of robots, thus allowing the development of cooperative applications. As a proof of concept, an auction-like goal assignment task is presented: the robot team is given a goal, and each robot proposes an estimated cost for achieving it, then the best proposal is selected. Most of the control flow is automated by the standard interaction protocols. Experimental evaluation demonstrates the advantages of combining both frameworks, for a practical yet sound development of multi-robot applications.

In robotics, the manipulation ofa prioriunknown objects involves several steps and problems that must be carefully considered and solved by proper planning and control algorithms. For example, once suitable contact points have been computed, the control system should be able to track them in the approach phase, i.e., while the relative position/orientation of the object and the gripper of the robotic system change due to the approaching movement of the robot toward the object. This correspondence paper proposes a practical method for the tracking of grasp points in image space that is based on transferring previously computed grasp points from an initial image to subsequent ones and on the analysis of the new grasp configuration. Three different options are proposed for this transference. Experimental results show the interesting practical performance of the general procedure.

Within the context of tele-laboratories for education the use of the Internet as communication media permits any researcher/student to perform remote experiments in a simple and reliable manner. Moreover, this situation introduces many interesting issues like network protocols for Internet robots, the effects of variable bandwidth and time-delays on telerobotics, etc. In this paper we present a comparative analysis of using several Internet transport protocols when performing a remote experiment within the UJI Industrial Telelaboratory. TCP, UDP, Trinomial and TEAR protocols are analyzed using the NS2 simulator. 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. These ideas are the basis for the definition of the SNRTP (simple network robot transport protocol).

In this paper, we present a novel boosted robot vision control algorithm. The method utilizes on-line boosting to produce a strong vision-based robot control starting from two weak algorithms. The notion of weak and strong algorithms has been presented in the context of robot vision control, in presence of uncertainty in the measurement process. Appropriate probabilistic error functions are defined for the weak algorithm to evaluate their suitability in the task. An on-line boosting algorithm is employed to derive a final strong algorithm starting from two weak algorithms. This strong one has superior performance both in image and Cartesian spaces. Experiments justify this claim.

The field of visual servoing is now widely accepted as a modern, consolidated discipline for vision-based real-time robot control. Though experimental setups have become affordable, theoretical and practical issues arise, which advise the use of simulation systems prior to real execution. This paper presents an object-oriented, cross-platform, network-ready environment for visual servoing simulations. With flexibility and extensibility as the main design goals, tasks can be defined either for cameras attached to moving Cartesian frames, or serial link manipulators. In order to provide fast feedback to the user, it includes real-time 3D rendering of the simulated scene. Task parameters and visual features can be freely chosen, and new features can be easily added to the framework. Output data is logged to disk files, which can be analyzed by any popular mathematical package. The simulator is built upon an agent-based framework, which makes possible the distribution across multiple networked computers. Moreover, it can be securely downloaded from a Web server and automatically installed in a computer, running either Windows, Linux or Mac OS X operating systems. This simulator is now a valuable tool in our research lab, and it has been extensively used by the students of a recent online course on visual servoing

We present an agent-based framework for the development of distributed applications for a team of heterogenous mobile robots. The main goal is to ease the development of cooperative tasks among teams of robots. The proposed architecture must have not only the capacity to allow the team of robots to accomplish such tasks, but also it must have tools and features that allow programmers to develop complex applications in a reasonable time. Agent-based development platforms are used for this purpose, integrating the necessary capabilities for developing distributed applications, and managing the communications among all the components. To demonstrate the advantages of the proposed framework, two real applications, remote vision and robot following, are presented. Both of them consist of a set of agents, and run actually in real robot systems, demonstrating that distributed systems do not add significant overhead to real-time tasks.

Visual control tasks demand very fast processing and transfer of huge amounts of data - live video images. Nowadays, computers and communication systems have become powerful enough to allow more flexible implementations of visual control tasks, enlarging the field of application to embrace networked systems, e.g. cooperative robots or mobile manipulators. In such setups, video grabbing, vision processing, and control might be located in different platforms across the network. This paper presents a cross-platform, networked implementation of visual control tasks based on software agents and video streaming technologies. This implementation consists of free, off-the-shelf, software components, resulting in a transparent system whose configuration can be adapted to existing hardware in very different ways, without any modification in the source code. We present several configurations which span onboard and offboard camera setups, and we experimentally determine the control loop delay of a real system, to test the feasibility of the proposed approach.

The visual tracking of grasp points is an essential operation for the execution of an approaching movement of a robot arm to an object: the grasp points are used as features for the definition of the control law. This work describes a strategy for tracking grasps on planar objects based on the use of a homography. In particular, the homography is used for transferring (translating) a grasp from a view of an object to a second one, providing in this way a correspondence in the second view. The grasp tracking procedure combines the search of a new grasp with the translation and the evaluation of that grasp between object views. Results of the proposed grasp tracking strategy are shown in case of grasps computed for a two-finger and a three-finger gripper.

The positioning of a gripper with respect to an object is one of the basic steps involved in the manipulation of that object. In particular, in a grasping task the fingers of the gripper should be placed at a set of selected grasp points belonging to the object. In this paper, a two-finger gripper and a stereo pair of cameras mounted in an eye-in-hand configuration are considered for this task. A visual servoing control system is proposed for the guidance of the positioning movement in which the grasp points are tracked in image space and used as input features for the control law. This tracking is based on the use of an invariant description of the grasp with respect to the object. The control law is restricted to control the degrees of freedom that produce movements that respect the invariance required by the grasp tracking.

In this article, a robot formation control strategy based on a vision-based follow-the-leader scenario is proposed, with emphasize on its reliability. On the one hand, perception is enhanced by the control of a motorized zoom. On the other hand, bidirectional and non-oblivious (Suzuki, I and Yamashita, M, 1996) control is implemented, with an odometry-based fault detection of vision-based information and a leader path-planning strategy to improve its visibility. After introduction of the control strategy, extensive experimental results are presented.

Obstacle detection and collision avoidance capabilities are the cornerstone of service robotic manipulators, i.e., robots that can work safely in human environments. Though algorithms and methods for collision avoidance already exist, they usually rely on complete CAD models of the environment. Such model are difficult to obtain from dynamic environments involving persons moving in unpredictable ways, thus reactive behaviors based on real-time sensing seems to be a more appropriate solution. This paper presents a prototype of the sensing skin for a robot arm. Rings of sensors are arranged around the robot links, each ring consisting of several infrared range sensors, which can detect objects in a distance range of between 4 and 30 cm, with less influence on the color of reflected obstacles. The resulting array of sensor measurements is fed up into a reinforcement learning scheme whose outputs are motion command for the robot joints. The system is intended to learn in an autonomous way the motions to avoid collisions with surrounding objects in real-time.

In the last years, there is a greater interest in systems of multiple autonomous robots for the accomplishment of cooperative tasks. This fact has motivated the implementation of a distributed architecture for a team of heterogeneous mobile robots. Such architecture must have the capacity to allow to the team of robots the accomplishment of cooperative tasks; the proposed solution consist of a multiagent system for the implementation of this distributed architecture. Also, two practical applications of cooperative tasks with the created architecture are sketched: cooperative navigation and localization and cooperative visual servoing.

The main goal of this paper, is the study of image-based stereo visual servoing. A pair of cameras is mounted on the end-effector of the manipulator arm. The visual features are the pair of images of an unknown object. The developed control laws use either the raw image points, or the estimated 3D coordinates. The experimental setup is challenging: large rotations are involved, images are noisy, and cameras are coarsely calibrated. In this setup, the trajectory of the end-effector differs notably, sometimes leading the arm near its joint range limits. Experimental results demonstrate that using pixel coordinates is disadvantageous, compared with 3D coordinates estimated from the same pixel data.

Most visual servoing applications are concerned with geometrically modeled objects. In this paper, the problem of controlling a motion by visual servoing around an unknown object with a stereovision system is addressed. The main goal is to move the end-effector around the object in order to observe several viewpoints of the object for other tasks, e.g. inspection or grasping. The present work uses the well-known image-based visual servoing approach with a point, but the importance of the relationship between the end-effector and camera frames is clarified and emphasized. This relationship is needed for properly stacking the Jacobians or interaction matrices of each camera. A comparison with a visual servoing approach with a direct stacking of the Jacobians is presented. The centroid of a region, obtained by color segmentation, is used to move around the observed object. Experiments are developed on a PA-10 robot connected to a real time stereovision system, with two cameras mounted on the end-effector. Experimental results demonstrate the importance of a proper definition of the stacked Jacobians, to avoid undesired motions in the servoing task. Particularly, when turning around an unknown object, undesired motions on roll angle of the stereovision system can be avoided.

Neither of the classical visual servoing approaches, position-based or image-based methods, are completely satisfactory. This paper presents a different approach with some advantages of both, i.e., the trajectory of the camera motion is predictable and the image features remain in the field of view of the camera. Our new approach is based on the computation of the pose of the object from the image, thus an appropriate calibration of the camera and a geometric model of the object are required. Experimental results on a real robotic platform are presented.

This paper presents a state identification approach which eliminates ambiguities caused by sensing and uncertainty. In manipulation tasks, the identification of contact states based on force and position sensing is affected by ambiguities. The approach uses recurrent neural networks to learn an internal representation of the finite state automata defined by the sensor patterns. The technique is demonstrated using a simulated learning task. State identification is combined with other techniques in a sensor-based learning architecture for robotic manipulation. Results are presented for simulated tasks. The system is able to manage ambiguous states which previously were impossible to learn.

Robots are extremely difficult to program in uncertain environments. Sensors are required to get feedback and detect the actual world state. In order to adapt to new situations, robots must be able to learn from examples or from their own experience. Learning can be accelerated if the available a priori task knowledge is used. The proposed sensor-based architecture combines learning with programmed modules. The correspondence between qualitative states and actions is learnt. Programming is used to decrease the complexity of the learning task. Numerical and qualitative processing are integrated in a suitable scheme for a wide range of robot tasks. Examples for a real insertion task are provided, where force sensing and the relative position are sufficient to successfully learn the task. The solution is thus valid for any other target location.

A novel approach based on the use of force sensors for motion in contact with uncertainty in task planning is presented. A neural network monitors the force signals measured by a sensor mounted in the robot wrist. This network is able to learn without need of a teacher the different contact states of the system. The method is intended to work properly in complex real-world situations, for which a geometric analytical model may not be feasible, or too difficult. In this paper the authors study the two-dimensional peg-in-hole problem and a real example of a complex insertion task in a flexible manufacturing system.