Papers by Francisco Martín Rico
arXiv (Cornell University), Sep 15, 2022
Self-localization is a fundamental capability that mobile robot navigation systems integrate to m... more Self-localization is a fundamental capability that mobile robot navigation systems integrate to move from one point to another using a map. Thus, any enhancement in localization accuracy is crucial to perform delicate dexterity tasks. This paper describes a new location that maintains several populations of particles using the Monte Carlo Localization (MCL) algorithm, always choosing the best one as the system's output. As novelties, our work includes a multi-scale match matching algorithm to create new MCL populations and a metric to determine the most reliable. It also contributes the state of the art implementations, enhancing recovery times from erroneous estimates or unknown initial positions. The proposed method is evaluated in ROS2 in a module fully integrated with Nav2 and compared with the current state-of-the-art Adaptive ACML solution, obtaining good accuracy/recovery times.
2014 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), 2014
This paper describes the development of a low cost robotic platform named MYRABot+, which is able... more This paper describes the development of a low cost robotic platform named MYRABot+, which is able to make the required tasks in order to assist a human in a domestic environment. We also believe that the best way to measure its performance and validate its behavior is taking part in a robotic challenge. This robotic platform explicitly uses low cost components, making it an accessible platform in monetary terms. In addition, we have designed a component-oriented software architecture that allows an easy implementation of simple HRI tasks. We demonstrate the feasibility of this proposal by taking part in the competition RoCKIn@home. There we show the basic abilities needed to work in a house environment, such as selflocalization, navigation, human dialog, and object manipulation. Our goal is to be able to evaluate and to compare it with other robotic platforms.
Multimedia Tools and Applications, 2022
Facing human activity-aware navigation with a cognitive architecture raises several difficulties ... more Facing human activity-aware navigation with a cognitive architecture raises several difficulties integrating the components and orchestrating behaviors and skills to perform social tasks. In a real-world scenario, the navigation system should not only consider individuals like obstacles. It is necessary to offer particular and dynamic people representation to enhance the HRI experience. The robot’s behaviors must be modified by humans, directly or indirectly. In this paper, we integrate our human representation framework in a cognitive architecture to allow that people who interact with the robot could modify its behavior, not only with the interaction but also with their culture or the social context. The human representation framework represents and distributes the proxemic zones’ information in a standard way, through a cost map. We have evaluated the influence of the decision-making system in human-aware navigation and how a local planner may be decisive in this navigation. The ...
As robotic systems spread, cybersecurity emerges as major concern. Currently most research autono... more As robotic systems spread, cybersecurity emerges as major concern. Currently most research autonomous systems are built using the ROS framework, along with other commercial software. ROS is a distributed framework where nodes publish information that other nodes consume. This model simplifies data communication but poses a major threat because a malicious process could easily interfere the communications, read private messages or even supersede nodes. In this paper we propose that ROS communications should be encrypted. We also measure how encryption affects its performance. We have used 3DES cyphering algorithm and we have evaluated the performance of the system, both from the computing and the communications point of view. Preliminary results show that symmetric ciphers using private keys impose significant delays.
Using HPC as a Competitive Advantage in an International Robotics Challenge
Using information from RGBD sensors requires huge amount of processing. To use these sensors impr... more Using information from RGBD sensors requires huge amount of processing. To use these sensors improves the robustness of algorithms for object perception, self-localization and, in general, all the capabilities to be performed by a robot to improve its autonomy. In most cases, these algorithms are not computationally feasible using single-thread implementations. This paper describes two multi thread strategies proposed for self localize a mobile robot in a known environment using information from a RGBD sensor. The experiments will show the benefits obtained when different numbers of threads are compared, using different approaches: a pool of threads and creation/destruction scheme. The work has been carried out on a Kobuki mobile robot in the environment of the RoCKiN competition, similar to RoboCup@home.
RESUMEN Los últimos años se está detectando una bajada significativa en la matrículación de alumn... more RESUMEN Los últimos años se está detectando una bajada significativa en la matrículación de alumnos en las ingenierías en los países desarrollados. Esto nos ha hecho plantearnos la necesidad de fomentar las vocaciones científico-técnicas, para lo que hemos decidido aprovechar nuestra experiencia en el campo de la robótica. En concreto hemos organizado un campeonato de construcción de robots que denominamos RoboCampeones y que describimos en esta comunicación.
Adapting ROS Logs to Facilitate Transparency and Accountability in Service Robotics
Advances in Intelligent Systems and Computing, 2019
Understanding why a particular robot behavior was triggered is a cornerstone for having human-acc... more Understanding why a particular robot behavior was triggered is a cornerstone for having human-acceptable social robots. Thus, every robot action should be explained in order to audit, recognize, and control expected and unexpected behaviors using usual sources of information provided by robot software components. Enabling intelligibility goes through a correct translation of system logs. This paper presents an initial approach for arranging low-level knowledge extracted from logs available in the de facto standard for service robotics ROS in order to be useful for developers and regulators.
Applied Sciences, 2021
Virtual desktops in cloud scenarios play a significant role in higher education. Nowadays, the id... more Virtual desktops in cloud scenarios play a significant role in higher education. Nowadays, the idea of moving laboratories to the cloud seems mandatory and it is necessary to maintain students’ commitment in this new scenario. This paper aims at two targets, customizing a Virtual Desktop platform for delivering the laboratories of a programming course in a Computer Science Bachelor Degree and empirically apply the technology acceptance model and the system usability scale to a set of students that use it. Results obtained in this paper provide insights about the direct effect between the perceived ease of use, perceived usefulness, and attitude to technology following the technology acceptance model (TAM) as well as a comprehensive analysis of the system usability scale (SUS) of our platform.
Sensors, 2020
Socially assistive robots have been used in the care of elderly or dependent people, particularly... more Socially assistive robots have been used in the care of elderly or dependent people, particularly with patients suffering from neurological diseases, like autism and dementia. There are some proposals, but there are no standardized mechanisms for assessing a particular robot’s suitability for specific therapy. This paper reports the evaluation of an acceptance test for assistive robots applied to people with dementia. The proposed test focuses on evaluating the suitability of a robot during therapy sessions. The test measures the rejection of the robot by the patient based on observational data. This test would recommend what kind of robot and what functionalities can be used in therapy. The novelty of this approach is the formalization of a specific validation process that only considers the reaction of the person to whom the robot is applied, and may be used more effectively than existing tests, which may not be adequate for evaluating assistance robots. The test’s feasibility was...
Integrated Computer-Aided Engineering, 2020
Cognitive architectures allow robots to perform their operations by drawing on a process that aim... more Cognitive architectures allow robots to perform their operations by drawing on a process that aims to simulate human reasoning. This paper presents an integrated semantic artificial memory system in cognitive architecture based on symbolic reasoning and a connective representation of the knowledge. This memory system attempts to simulate how humans learn to distinguish instances of particular objects within their class using a convolutional network to detect the relevant elements of an image. We use a vector with the extracted features to learn to discriminate an instance of another element from the same class. A novel feature of our approach is its autonomous learning process during the operation of the robot, integrating a deep learning embedding with a statistical classifier. The usefulness and robustness of this method are demonstrated by applying it to a social robot that learns to differentiate people. Finally, experiments are carried out to validate our approach, comparing the detection results with several alternative methods.
Frontiers in Neurorobotics, 2019
Tracking people has many applications, such as security or safe use of robots. Many onboard syste... more Tracking people has many applications, such as security or safe use of robots. Many onboard systems are based on Laser Imaging Detection and Ranging (LIDAR) sensors. Tracking peoples' legs using only information from a 2D LIDAR scanner in a mobile robot is a challenging problem because many legs can be present in an indoor environment, there are frequent occlusions and self-occlusions, many items in the environment such as table legs or columns could resemble legs as a result of the limited information provided by two-dimensional LIDAR usually mounted at knee height in mobile robots, etc. On the other hand, LIDAR sensors are affordable in terms of the acquisition price and processing requirements. In this article, we describe a tool named PeTra based on an off-line trained full Convolutional Neural Network capable of tracking pairs of legs in a cluttered environment. We describe the characteristics of the system proposed and evaluate its accuracy using a dataset from a public repository. Results show that PeTra provides better accuracy than Leg Detector (LD), the standard solution for Robot Operating System (ROS)-based robots.
Cognitive processing, Jan 6, 2018
Generation of autonomous behavior for robots is a general unsolved problem. Users perceive robots... more Generation of autonomous behavior for robots is a general unsolved problem. Users perceive robots as repetitive tools that do not respond to dynamic situations. This research deals with the generation of natural behaviors in assistive service robots for dynamic domestic environments, particularly, a motivational-oriented cognitive architecture to generate more natural behaviors in autonomous robots. The proposed architecture, called HiMoP, is based on three elements: a Hierarchy of needs to define robot drives; a set of Motivational variables connected to robot needs; and a Pool of finite-state machines to run robot behaviors. The first element is inspired in Alderfer's hierarchy of needs, which specifies the variables defined in the motivational component. The pool of finite-state machine implements the available robot actions, and those actions are dynamically selected taking into account the motivational variables and the external stimuli. Thus, the robot is able to exhibit d...
Journal of Physical Agents (JoPha), 2007
In this paper we present our software framework for robotic applications, jde-neoc. This is the s... more In this paper we present our software framework for robotic applications, jde-neoc. This is the second implementation of our cognitive behavior-based architecture JDE, and it is aimed to overcome some of the limitations observed in three years using the rst one. jdeneoc uses schemas as the basic component of robot applications, which are combined in dynamic hierarchies to unfold the global behavior. Each schema is built separatedly into a plugin and dynamically linked to the framework when needed. It keeps its own graphical user interface. Some tools like a hierarchy oscilloscope and a 3D sensors-and-motors GUI have been created and added to the framework.
Analysis and Evaluation of a Low-Cost Robotic Arm for @Home Competitions
Advances in Intelligent Systems and Computing, 2015
This paper reviews the design design, construction and performance of an affordable robotic arm o... more This paper reviews the design design, construction and performance of an affordable robotic arm of four degrees of freedom based on an Arduino controller in a home-like environment. This paper describes the kinematic design of our 4 DOF arm and the physical restrictions that this design imposes. We have also proposed two types of end-effectors to address two types of manipulation tasks: to grasp objects and to push different light switches. The arm was on board of the MYRABot platform and both were evaluated in the RoCKIn competition. This competition involves grasping and manipulation tasks that are described in the paper as well. Comments on the results of the competition and their implication in further improvement of the robot are also described in the paper.
A robotic platform for domestic applications
During the last years, robots are leaving industrial or research environments and sharing the sam... more During the last years, robots are leaving industrial or research environments and sharing the same space with humans. This paper describes a robotic platform and its behavior architecture created to develop the necessary skills to help a human being in its own environment. This mobile robot is equipped with one robotic arm with 7 degrees of freedom and a RGBD depth camera as main sensor. The software behavior architecture developed for this robot can develop complex behaviors in a simple way, providing real-time features with low computational consumption. This architecture will be validated in a public robot competition called RoCKIn@home.
2006 IEEE 3rd Latin American Robotics Symposium, 2006
Communications are the basis for the collaborative activities in the TeamChaos 4-legged team. In ... more Communications are the basis for the collaborative activities in the TeamChaos 4-legged team. In this paper we present the communications architecture developed both to let teammates communicate, and to easy the debugging of robot behaviors from external computers. Details of its implementation on the aiBo robots are also given. Using this infrastructure we describe a protocol for role exchange named Switch! that we have created. We also describe the use of both the communication architecture, and the Switch! protocol in the passing challenge of the 2006 edition of the RoboCup.
robotica-urjc.es
Resumen En la liga de 4 patas de la Robocup, equipos de 4 robots AIBO autónomos se enfrentan entr... more Resumen En la liga de 4 patas de la Robocup, equipos de 4 robots AIBO autónomos se enfrentan entre sı en partidos de fútbol. El objetivo de esta competición es presentar un entorno desafiante en que se han de resolver varios problemas relacionados con la robótica. En particular, ...
Una de las aplicaciones habituales dentro de los sistemas multi-robot es la percepción distribuid... more Una de las aplicaciones habituales dentro de los sistemas multi-robot es la percepción distribuida. Este mecanismo de cooperación permite que cada robot sea capaz de modelar su entorno, más allá de lo que percibe a través de sus propios sensores, apoyándose en las observaciones de otros robots del equipo. Las técnicas probabilísticas de fusión sensorial pueden emplearse para combinar percepciones de varios robots y obtener unaúnica estimación global. En este artículo se presentan dos aproximaciones al problema de la percepción distribuida de la pelota dentro del escenario de la RoboCup. * Los resultados de este trabajo han sido parcialmente financiados por los proyectos COCOGROM del Ministerio de Educación y Ciencia (ref.
Uploads
Papers by Francisco Martín Rico