Search

This paper presents an augmented reality application to assist with myoelectric prostheses control for people with limb amputations. For that, we use the low-cost Myo armband coupled with low-level signal processing methods specifically built to control filters’ levels and processing chain. In particular, we use deep learning techniques to process the signals and to accurately identify seven different hand gestures. From that, we have built an augmented reality projection of a hand based on AprilTag markers that displays the gesture identified by the deep learning techniques. With the aim to properly train the gesture recognition system, we have built our own dataset with nine subjects. This dataset was combined with one publicly available to work with the data of 24 subjects in total. Finally, three different deep learning architectures have been comparatively studied, achieving high accuracy values (being 95.56% the best one). This validates our hypothesis that it is possible to have an adaptive platform able to fast learn personalized hand/arm gestures while projecting a virtual hand in real-time. This can reduce the adaptation time to myoelectric prostheses and improve the acceptance levels. Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. This work has been partly supported by Grant PID2019-104818RB-I00 funded by MCIN/AEI/10.13039/501100011033 and by “ERDF A way of making Europe”; and by Generalitat Valenciana (CIGE/2021/136).

The Web is the main source of information for almost all human activities. Webpages are growing exponentially and becoming more sophisticated, presenting a serious challenge to search engines, recommender systems and Web directories. To organize this complex and vast content, webpage classification is the basic technique, usually based on textual analysis of HTML code. However, the visual appearance of a webpage plays an important role and can be a new alternative to distinguish between categories. In a previous paper, we implemented a Deep Learning model to classify webpages into certain categories using only screenshots, where the results demonstrated a very hard multi-class problem. In the present work, we address the same problem under a new approach, applying One vs. Rest strategy, using regularization techniques, redefining the prediction mechanism, and generating a more reliable dataset. Thus, we have obtained interesting improvements in accuracy and reduction of overfitting. Also, we have developed an online system for classifying webpages that can help designers, website owners, webmasters, and users in general.

Along the last decades, Robotics research has taken a major turn from laboratories to factories and ordinary real-world environments. Consequently, new issues to be overcome have arisen, specially when autonomous, dexterous robots are in place. In this paper, we present this evolution in the case of robot vision for manipulation through several robot developments, by analysing their challenges and proposed solutions. This overview highlights the need of using different techniques depending on the task at hand and the scenario to work in. This work was supported in part by the Ministerio de Economía y Competitividad under Grant DPI2015-69041-R, in part by Universitat Jaume I under Grant UJI-B2018-74, and in part by Generalitat Valenciana under Grant PROMETEO/2020/034 and GV/2020/051.

Over time, the field of robotics has provided solutions to automate routine tasks in different scenarios. In particular, libraries are awakening great interest in automated tasks since they are semi-structured environments where machines coexist with humans and several repetitive operations could be automatically performed. In addition, multirotor aerial vehicles have become very popular in many applications over the past decade, however autonomous flight in confined spaces still presents a number of challenges and the use of small drones has not been reported as an automated inventory device within libraries. This paper presents the UJI aerial librarian robot that leverages computer vision techniques to autonomously self-localize and navigate in a library for automated inventory and book localization. A control strategy to navigate along the library bookcases is presented by using visual markers for self-localization during a visual inspection of bookshelves. An image-based book recognition technique is described that combines computer vision techniques to detect the tags on the book spines, followed by an optical character recognizer (OCR) to convert the book code on the tags into text. These data can be used for library inventory. Misplaced books can be automatically detected, and a particular book can be located within the library. Our quadrotor robot was tested in a real library with promising results. The problems encountered and limitation of the system are discussed, along with its relation to similar applications, such as automated inventory in warehouses. Support for the research conducted at UJI Robotic Intelligence Laboratory is provided in part by the Ministerio de Economía y Competitividad (DPI2015-69041-R), by Universitat Jaume I (UJI-B2018-74), and by Generalitat Valenciana (PROMETEO/2020/034, GV/2020/051).

Over one billion people in the world live with some form of disability. This is incessantly increasing due to aging population and chronic diseases. Among the emerging social needs, rehabilitation services are the most required. However, they are scarce and expensive what considerably limits access to them. In this paper, we propose EVA, an augmented reality platform to engage and supervise rehabilitation sessions at home using low-cost sensors. It also stores the user’s statistics and allows therapists to tailor the exercise programs according to their performance. This system has been evaluated in both qualitative and quantitative ways obtaining very promising results. This work has been supported by the Spanish Government TIN2016-76515R Grant, supported with Feder funds. Edmanuel Cruz is funded by a Panamenian grant for Ph.D. studies IFARHU and SENACYT 270-2016-207. This work has also been supported by a Spanish grant for PhD studies ACIF/2017/243 and FPU16/00887. Thanks also to Nvidia for the generous donation of a Titan Xp and a Quadro P6000.

Aimed at building autonomous service robots, reasoning, perception, and action should be properly integrated. In this paper, the depth cue has been analysed as an early stage given its importance for robotic tasks. So, from neuroscience findings, a hierarchical four-level dorsal architecture has been designed and implemented. Mainly, from a stereo image pair, a set of complex Gabor filters is applied for estimating an egocentric quantitative disparity map. This map leads to a quantitative depth scene representation that provides the raw input for a qualitative approach. So, the reasoning method infers the data required to make the right decision at any time. As it will be shown, the experimental results highlight the robust performance of the biologically inspired approach presented in this paper. This paper describes research done at UJI Robotic Intelligence Laboratory. Support for this laboratory was provided in part by Ministerio de Economía y Competitividad (DPI2015-69041-R) and by Universitat Jaume I.

Technological advances are being made to assist humans in performing ordinary tasks in everyday settings. A key issue is the interaction with objects of varying size, shape, and degree of mobility. Autonomous assistive robots must be provided with the ability to process visual data in real time so that they can react adequately for quickly adapting to changes in the environment. Reliable object detection and recognition is usually a necessary early step to achieve this goal. In spite of significant research achievements, this issue still remains a challenge when real-life scenarios are considered. In this article, we present a vision system for assistive robots that is able to detect and recognize objects from a visual input in ordinary environments in real time. The system computes color, motion, and shape cues, combining them in a probabilistic manner to accurately achieve object detection and recognition, taking some inspiration from vision science. In addition, with the purpose of processing the input visual data in real time, a graphical processing unit (GPU) has been employed. The presented approach has been implemented and evaluated on a humanoid robot torso located at realistic scenarios. For further experimental validation, a public image repository for object recognition has been used, allowing a quantitative comparison with respect to other state-of-the-art techniques when realworld scenes are considered. Finally, a temporal analysis of the performance is provided with respect to image resolution and the number of target objects in the scene.

Over one billion people in the world suffer from some form of disability. Nevertheless, according to the World Health Organization, people with disabilities are particularly vulnerable to deficiencies in services, such as health care, rehabilitation, support, and assistance. In this sense, recent technological developments can mitigate these deficiencies, offering less-expensive assistive systems to meet users&rsquo, needs. This paper reviews and summarizes the research efforts toward the development of these kinds of systems, focusing on two social groups: older adults and children with autism.

Rehabilitation is essential for disabled people to achieve the highest level of functional independence, reducing or preventing impairments. Nonetheless, this process can be long and expensive. This fact together with the ageing phenomenon has become a critical issue for both clinicians and patients. In this sense, technological solutions may be beneficial since they reduce the costs and increase the number of patients per caregiver, which makes them more accessible. In addition, they provide access to rehabilitation services for those facing physical, financial, and/or attitudinal barriers. This paper presents the state of the art of the assistive rehabilitation technologies for different recovery methods starting from in-person sessions to complementary at-home activities. This work was supported by the Spanish Government TIN2016-76515-R Grant, supported with FEDER funds.

Assistive robots are a category of robots that share their area of work and interact with humans [...]

The population ageing phenomenon leads to an unceasing need for home-based healthcare systems to continuously monitor the elderly’s cognitive and physical health. In this sense, physical activity may be beneficial in preserving cognition in elder life as well as in providing clinicians and therapists with the indicative of elderly’s health condition. Nevertheless, current systems fail to promote and monitor the elderly’s physical activity in their living environments. This paper is aimed at providing a socially assistive robot solution for this task. Since robot acceptance depends to a great extent on its robustness in performing tasks, we have focused on exercise recognition due to its great importance for both clinicians and elderly. For that, two different tasks were carried out. First, an image dataset for physical exercise recognition has been generated. Then, a comparative analysis of several deep learning techniques is presented. This paper reveals a great performance in the exercise recognition of CNN-LSTM with an exercise recognition accuracy of 99.87%. This work was supported in part by the Spanish Government under Grant TIN2016-76515-R, and in part by Feder Funds.

This paper describes the approach taken by the team from the Robotic Intelligence Laboratory at Jaume I University to the Amazon Robotics Challenge 2017. The goal of the challenge is to automate pick and place operations in unstructured environments, specifically the shelves in an Amazon warehouse. RobInLab's approach is based on a Baxter Research robot and a customized storage system. The system's modular architecture, based on ROS, allows communication between two computers, two Arduinos and the Baxter. It integrates 9 hardware components along with 10 different algorithms to accomplish the pick and stow tasks. We describe the main components and pipelines of the system, along with some experimental results.

The world’s population is ageing and, with that, new social issues arise, especially in terms of healthcare and daily activities. Despite the preference for human professional healthcare, the new socio-economic situation and the decrease in care personnel make necessary to give support to the process of caregiving. In this context, Robotics can be considered as a solution since it can provide healthcare support, help in performing daily tasks, and/or increase the feeling of autonomony and self management. This paper is an overview of the existing robotic technologies for elderly care, analysing their benefits for the elderly.

The paradigm shift of Robotics moving toward autonomous robots meeting human needs in real world settings requires developing robot interaction skills. So, a synergy of different disciplines is essential to achieve that goal. In particular, Human-Robot Interaction (HRI), the study of how humans interact with robots in daily environments, aims to endow robots with the necessary interactive abilities. In this context, efficient people detection and tracking is an imperative preliminary step to increase efficiency by selecting relevant parts of an image to be processed by other systems such as: gesture detection and recognition; face detection, recognition and tracking; understanding human activity, etc. In this paper, we propose to analyze the motion detection problem by providing a solution for a good environment adaptation of the robot system and real-time visual perception, including an accurate people/object distinction

A long-term goal in Robotics is developing autonomous systems able to assist and support human beings, especially in hazardous and/or repetitive tasks. So, these robotic systems will share their workspace with other robots, people or both of them, possibly having different goals and needs. This fact may result in a conflict that should be solved for properly achieving the intended goals. However, there is no a universal way to do it since different scenarios and behaviours lead to different kinds of conflicts. In addition, execution time is a critical issue in the Robotics field and has to be taken into account when a conflict resolution technique is developed. In this chapter we will discuss the state-of-the-art algorithms applied to several robotic tasks from assembly and disassembly in industrial settings to multi-robot cooperation through collision avoidance in unstructured, crowded environments. So, a deep analysis will highlight approach's applications and utilities, as well as their limitations.

The ability to grasp is a fundamental requirement for service robots in order to perform meaningful tasks in ordinary environments. However, its robustness can be compromised by the inaccuracy (or lack) of tactile and proprioceptive sensing, especially in the presence of unforeseen slippage. As a solution, vision can be instrumental in detecting grasp errors. In this paper, we present an RGB-D visual application for discerning the success or failure in robot grasping of unknown objects, when a poor proprioceptive information and/or a deformable gripper without tactile information is used. The proposed application is divided into two stages: the visual gripper detection and recognition, and the grasping assessment (i.e. checking whether a grasping error has occurred). For that, three different visual cues are combined: colour, depth and edges. This development is supported by the experimental results on the Hobbit robot which is provided with an elastically deformable gripper.

Based on the importance of relative disparity between objects for accurate hand-eye coordination, this paper presents a biological approach inspired by the cortical neural architecture. So, the motor information is coded in egocentric coordinates obtained from the allocentric representation of the space (in terms of disparity) generated from the egocentric representation of the visual information (image coordinates). In that way, the different aspects of the visuomotor coordination are integrated: an active vision system, composed of two vergent cameras; a module for the 2D binocular disparity estimation based on a local estimation of phase differences performed through a bank of Gabor filters; and a robotic actuator to perform the corresponding tasks (visually-guided reaching). The approach’s performance is evaluated through experiments on both simulated and real data.

Social activities are among the most striking of animal behaviours, providing knowledge about their intelligence, cognition and evolution. However, their observation in the field can be especially arduous. To address this, image processing methods have been developed. However, despite the extensively research on this topic, multiple object tracking still remains a very hard problem due to the wide variety of issues to be overcome (e.g. changes in illumination conditions, stopped colony member, occlusions, etc.). In this paper, we contribute a novel visual tracking application addressing the challenge of detecting and simultaneously tracking hundreds of animals in their habitat. For that, motion is used as primary cue. The system was validated in experiments with laboratory colonies of micro-robots and several example analysis of dewlap lizard’s behaviour.

On the way to autonomous robotic systems, key issues are object detection and recognition. In this paper, we aim at robustly detecting and recognizing different objects in real-life scenarios from a visual input when robot manipulation is the goal task. For that, and based on the human vision system performance, the system computes object's colour, motion and shape cues and combines them in a probabilistic manner to accurately achieve object identification and recognition task. More-over, a Graphical Processing Unit (GPU) is used to fulfill the requirement for real-time visual data processing. In addition, it has been implemented and tested on a robotic platform.

The ability of any robot to robustly detect and recognize people is a fundamental issue to allow safe Human-Robot Interactions. This ability allows the system to deal with situations that are not determined a priori, while safely performing its tasks. Some research has been carried out on this topic, although most of the proposed approaches restrict the systems autonomy, flexibility and/or performance time. In this paper, we present a visual application for human detection and recognition without limiting the systems capabilities.

Cognitive impaired population face with innumerable problems in their daily life. Surprisingly, they are not provided with any help to perform those tasks for which they have difficulties. As a consequence, it is necessary to develop systems that allow those people to live independently and autonomously. Living in a technological era, people could take advantage of the available technology, being provided with some solutions to their needs. This paper presents a platform that assists users with remembering where their possessions are. Mainly, an object recognition process together with an intelligent scheduling applications are integrated in an Ambient Assisted Living (AAL) environment.

One of the main goals of Robotics research is to help human beings in their daily tasks. However, physical interaction in everyday human scenarios requires robot systems endowed with rich sensory-motor skills and multisensory feedback that enables them to exhibit levels of adaptability high enough to achieve their goals. In this context, vision plays a main role since it provides rich information about the state of the environment. Although it is an active research area, there are still some challenging issues to be solved. Among them, the research presented in this paper addresses the object recognition for manipulation tasks in unstructured environments from a visual input. We have designed a mechanism that provides a background model covering the whole system’s peripersonal space such that the objects of interest can be always identified without any information about the system. Different objects and scene conditions have been considered to assess approach’s performance by showing robust object recognition in all the cases.

On the way to autonomous service robots, spatial reasoning plays a main role since it properly deals with problems involving uncertainty. In particular, we are interested in knowing people’s pose to avoid collisions. With that aim, in this paper, we present a qualitative acceleration model for robotic applications including representation, reasoning and a practical application.

On the way to autonomous robots able to perceive all the surrounding space, this paper focuses on visual object recognition in real scenarios where those objects can be occluded, modify their appearance due to a viewpoint changed or different illumination conditions, etc. In this paper, we aim at robustly detecting and recognizing different objects in real-life scenarios from a visual input. For that, we present an appoach to properly build a peripersonal background model such that the target objects are always detected and recognized without any a-priori knowledge about the robotic system. Several objects and different scene conditions have been used to evaluate the method’s performance by providing successful object detection and recognition in all the cases, as shown in the experimental section.

The way to autonomous robotic systems leads to deal with acting and interacting with real-life scenarios. Focusing on human-robot interaction, one of the first issues to be solved concerns safety since systems are becoming larger and more sophisticated and the damage caused can be considerable. So, robotic systems must exhibit levels of adaptability high enough to achieve their goals by guaranteeing the safety of all their surrounding elements, especially when they are human beings. With that aim, we propose a visual application that provides the system with information about all-embracing activity and, consequently, with the ability of safe interacting with human beings.

On the way to autonomous robots, perception is a key point. Among all the perception senses, vision is undoubtedly the most important for the information it can provide. However, it is not easy to identify what is seen from the provided visual input. On this regard, inspired by humans, we have studied motion as a primary cue. Particularly, we present a computational solution for motion detection, object location and tracking from images captured by perspective and fisheye cameras. The proposed approach has been validated with an extensive set of experiments and applications using different testbeds of real environments with real and/or virtual targets.

Motion detection plays a fundamental role in any object tracking or video surveillance algorithm, to the extent that nearly all such algorithms start with motion detection. Actually, the reliability with which potential foreground objects in movement can be identified, directly impacts on the efficiency and performance level achievable by subsequent processing stages of tracking or object recognition. However, detecting regions of change in images of the same scene is not a straightforward task since it does not only depend on the features of the foreground elements, but also on the characteristics of the background such as, for instance, the presence of vacillating elements. So, in this chapter, we have focused on the motion detection problem in the basic case, i.e., when all background elements are motionless. The goal is to solve different issues referred to the use of different imaging sensors, the adaptation to different environments, different motion speed, the shape changes of the targets, or some uncontrolled dynamic factors such as, for instance, gradual/sudden illumination changes. So, first, a brief overview of previous related approaches is presented by analyzing factors which can make the system fail. Then, we propose a motion segmentation algorithm that successfully deals with all the arisen problems. Finally, performance evaluation, analysis, and discussion are carried out.

In qualitative spatial and temporal reasoning we can distinguish between comparing and naming magnitudes. In particular, naming qualitative models allow humans to express spatio-temporal concepts such as “That horse is really fast”. In colloquial terms, naming concepts are called relative. In this paper we present a general framework to solve the representation magnitude and a general algorithm to solve the basic step of inference process of qualitative models based on intervals. The general method is based on the definition of two algorithms: the qualitative sum and the qualitative difference.

In this chapter, we will introduce some of the concepts and techniques of Computer Vision that are used throughout this book. This description does not represent an exhaustive introduction into the Computer Vision field, but it is addressed to clarify those terms to a reader unfamiliar with them.