Search

In the context of Industry 4.0, a paradigm shift from traditional industrial manipulators to Collaborative Robots (CRs) is ongoing, with the latter serving ever more closely humans as auxiliary tools in many production processes. In this scenario, continuous technological advancements offer new opportunities for further innovating robotics and other areas of next-generation industry. For example, 6G could play a prominent role due to its human-centric view of the industrial domains. In particular, its expected dependability features will pave the way for new applications exploiting highly effective Digital Twin (DT)- and eXtended Reality (XR)-based telepresence. In this work, a novel application for the above technologies allowing two distant users to collaborate in the programming of a CR is proposed. The approach encompasses demanding data flows (e.g., point cloud-based streaming of collaborating users and robotic environment), with network latency and bandwidth constraints. Results obtained by analyzing this approach from the viewpoint of network requirements in a setup designed to emulate 6G connectivity indicate that the expected performance of forthcoming mobile networks will make it fully feasible in principle.

Recent trends in the Digital Humanities – conceived as new modalities of collaborative, transdisciplinary and computational research and presentation – also strongly influence research approaches and presentation practices in museums. Indeed, ongoing projects in museums have considerably expanded digital access to data and information, documentation and visualization of ancient ruins and objects. In addition, 3D modelling and eXtended Reality opened up new avenues of interacting with a wider public through digital reconstructions that allow both objects and sites to be presented through visual narratives based on multidisciplinary scholarly research. The article illustrates the use of 3D digital reconstruction and virtual reality to re-contextualise standing statues of Sekhmet in the Temple of Ptah at Karnak, where they were found in 1818. Today, they are on display at Museo Egizio, Turin. The theoretical framework of the research and the operational workflow – based on the study of the available archaeological, textual, and pictorial data – is presented here.DOI: https://doi.org/10.20365/disegnarecon.31.2023.4

Having the Fifth Generation (5G) mobile communication system recently rolled out in many countries, the wireless community is now setting its eyes on the next era of Sixth Generation (6G). Inheriting from 5G its focus on industrial use cases, 6G is envisaged to become the infrastructural backbone of future intelligent industry. Especially, a combination of 6G and the emerging technologies of Digital Twins (DT) will give impetus to the next evolution of Industry 4.0 (I4.0) systems. This article provides a survey in the research area of 6G-empowered industrial DT system. With a novel vision of 6G industrial DT ecosystem, this survey discusses the ambitions and potential applications of industrial DT in the 6G era, identifying the emerging challenges as well as the key enabling technologies. The introduced ecosystem is supposed to bridge the gaps between humans, machines, and the data infrastructure, and therewith enable numerous novel application scenarios.

Abstract Monitoring road conditions, e.g., water build-up due to intense rainfall, plays a fundamental role in ensuring road safety while increasing resilience to the effects of climate change. Distributed cameras provide an easy and affordable alternative to instrumented weather stations, enabling diffused and capillary road monitoring. Here, we propose a deep learning-based solution to automatically detect wet road events in continuous video streams acquired by road-side surveillance cameras. Our contribution is two-fold: first, we employ a convolutional Long Short-Term Memory model (convLSTM) to detect subtle changes in the road appearance, introducing a novel temporally consistent data augmentation to increase robustness to outdoor illumination conditions. Second, we present a contrastive self-supervised framework that is uniquely tailored to surveillance camera networks. The proposed technique was validated on a large-scale dataset comprising roughly 2000 full day sequences (roughly 400K video frames, of which 300K unlabelled), acquired from several road-side cameras over a span of two years. Experimental results show the effectiveness of self-supervised and semi-supervised learning, increasing the frame classification performance (measured by the Area under the ROC curve) from 0.86 to 0.92. From the standpoint of event detection, we show that incorporating temporal features through a convLSTM model both improves the detection rate of wet road events (+ 10%) and reduces false positive alarms ( $$-$$ - 45%). The proposed techniques could benefit also other tasks related to weather analysis from road-side and vehicle-mounted cameras.

In this work we study the impact of noise on the training of object detection networks for the medical domain, and how it can be mitigated by improving the training procedure. Annotating large medical datasets for training data-hungry deep learning models is expensive and time consuming. Leveraging information that is already collected in clinical practice, in the form of text reports, bookmarks or lesion measurements would substantially reduce this cost. Obtaining precise lesion bounding boxes through automatic mining procedures, however, is difficult. We provide here a quantitative evaluation of the effect of bounding box coordinate noise on the performance of Faster R-CNN object detection networks for breast mass detection. Varying degrees of noise are simulated by randomly modifying the bounding boxes: in our experiments, bounding boxes could be enlarged up to six times the original size. The noise is injected in the CBIS-DDSM collection, a well curated public mammography dataset for which accurate lesion location is available. We show how, due to an imperfect matching between the ground truth and the network bounding box proposals, the noise is propagated during training and reduces the ability of the network to correctly classify lesions from background. When using the standard Intersection over Union criterion, the area under the FROC curve decreases by up to 9%. A novel matching criterion is proposed to improve tolerance to noise.

Virtual Reality (VR) has increasingly attracted the attention of the computer animation community in search of more intuitive and effective alternatives to the current sophisticated user interfaces. Previous works in the literature already demonstrated the higher affordances offered by VR interaction, as well as the enhanced spatial understanding that arises thanks to the strong sense of immersion guaranteed by virtual environments. These factors have the potential to improve the animators' job, which is tremendously skill-intensive and time-consuming. The present paper explores the opportunities provided by VR-based interfaces for the generation of 3D animations via armature deformation. To the best of the authors' knowledge, for the first time a tool is presented which allows users to manage a complete pipeline supporting the above animation method, by letting them execute key tasks such as rigging, skinning and posing within a well-known animation suite using a customizable interface. Moreover, it is the first work to validate, in both objective and subjective terms, character animation performance in the above tasks and under realistic work conditions involving different user categories. In our experiments, task completion time was reduced by 26%, on average, while maintaining almost the same levels of accuracy and precision for both novice and experienced users.

Automatic event detection from images or wearable sensors is a fundamental step towards the development of advanced sport analytics and broadcasting software. However, the collection and annotation of large scale sport datasets is hindered by technical obstacles, cost of data acquisition and annotation, and commercial interests. In this paper, we present the Soccer Event Recognition (SoccER) data generator, which builds upon an existing, high quality open source game engine to enable synthetic data generation. The software generates detailed spatio-temporal data from simulated soccer games, along with fine-grained, automatically generated event ground truth. The SoccER software suite includes also a complete event detection system entirely developed and tested on a synthetic dataset including 500 min of game, and more than 1 million events. We close the paper by discussing avenues for future research in sports event recognition enabled by the use of synthetic data.

Intervention by First Responders (FRs) is essential in disaster response, and their preparation greatly benefits from continuous updates. However, the design of effective training experiences targeted to FRs can be very demanding from the viewpoint of a Training Provisioner (TP). Virtual Reality (VR) may have a key role to play in enhancing and facilitating this task. In fact, VR technology has already proven to be very helpful in the field of emergency training, as well as its use as a powerful design and mock-up tool in many other contexts. In this work, the application of VR as a mock-up tool supporting TPs in the arrangement and validation of a training experience, either real or virtual, is explored. In particular, a case study is considered concerning the training of an FR for hydro-geological risks. Within this context, the proposed approach is compared against dramaturgy prototyping, a method commonly used for the design of experiential courses. Results indicate that the adoption of a VR-based mock-up tool (VRMT) can provide TPs with good insights on the arrangement of the training and precious indications on how to actually map this information onto real-world exercises.

Swapping visual perspective in virtual reality (VR) provides a unique means for embodying different virtual bodies and for self-distancing. Moreover, this technology is a powerful tool for experiential learning and for simulating realistic scenarios, with broad potential in the training of soft skills. However, there is scarce knowledge on how perspective swapping in VR might benefit the training of soft skills such as those required in a job interview. This article investigates the impact of virtual body swapping on the self-assessment of verbal and nonverbal communication skills, emotional states, and embodiment in a simulated job interview context. Three main conditions were compared: a baseline condition in which the participants practiced a job interview from the first-person perspective of a virtual interviewee (no swap condition); an external point of view condition where, first, the participants answered questions from the interviewee perspective, but then swap visual perspective to re-experience their responses from a nonembodied point of view (out of body condition); and a condition in which, after answering questions from the interviewee perspective, the participants re-experienced their responses from the embodied perspective of the virtual recruiter (recruiter condition). The experimental results indicated that the effectiveness of the out of body and recruiter conditions was superior to the no swap condition to self-assess the communication styles used during a job interview. Moreover, all the conditions led to a high level of embodiment toward the interviewee avatar when seen from the first-person perspective; in the case of the recruiter condition, the participants also felt embodied in the recruiter avatar. No differences in emotional states were found among conditions, with all sharing a positive valence.

Motion capture systems provide an efficient and interactive solution for extracting information related to a human skeleton, which is often exploited to animate virtual characters. When the character cannot be assimilated to an anthropometric shape, the task to map motion capture data onto the armature to be animated could be extremely challenging. This paper presents two methodologies for the automatic mapping of a human skeleton onto virtual character armatures. Kinematics chains of the human skeleton are analyzed in order to map joints, bones and end-effectors onto an arbitrary shaped armatures. Both forward and inverse kinematics are considered. A prototype implementation has been developed by using the Microsoft Kinect as body tracking device. Results show that the proposed solution can already be used to animate truly different characters ranging from a Pixar-like lamp to different kinds of animals.

Advancements in input device and sensor technologies led to the evolution of the traditional human-machine interaction paradigm based on the mouse and keyboard. Touch-, gesture- and voice-based interfaces are integrated today in a variety of applications running on consumer devices (e.g., gaming consoles and smartphones). However, to allow existing applications running on desktop computers to utilize natural interaction, significant re-design and re-coding efforts may be required. In this paper, a framework designed to transparently add multi-modal interaction capabilities to applications to which users are accustomed is presented. Experimental observations confirmed the effectiveness of the proposed framework and led to a classification of those applications that could benefit more from the availability of natural interaction modalities.

Here we give context to the Special Issue on “Detection and Tracking of Targets in Forward-Looking InfraRed (FLIR) Imagery” in Sensors. We start with an introduction to the role of infrared images in today’s vision-based applications, by outlining the specific challenges that characterize detection and tracking in FLIR images. We then illustrate why selected papers have been chosen to represent the domain of interest, by summarizing their main contributions to the state-of-the-art. Lastly, we sum up the main evidence found, and we underline some of the aspects that are worthy of further investigation in future research activities.

In this article we present the Phygital Game project, a mixed-reality game platform in which children can play with or against a robot. The project was developed by adopting a human-centered design approach, characterized by the engagement of both children and parents in the design process, and situating the game platform in a real context—an educational center for children. We report the results of both the preliminary studies and the final testing session, which focused on the evaluation of usability factors. By providing a detailed description of the process and the results, this work aims at sharing the findings and the lessons learned about both the implications of adopting a human-centered approach across the whole design process and the specific challenges of developing a mixed-reality playground.

Service robots are playing an increasingly relevant role in society. Humanoid robots, especially those equipped with social skills, could be used to address a number of people’s daily needs. Knowing how these robots are perceived and potentially accepted by ordinary users when used in common tasks and what the benefits brought are in terms, e.g., of tasks’ effectiveness, is becoming of primary importance. This paper specifically focuses on receptionist scenarios, which can be regarded as a good benchmark for social robotics applications given their implications on human-robot interaction. Precisely, the goal of this paper is to investigate how robots used as direction-giving systems can be perceived by human users and can impact on their wayfinding performance. A comparative analysis is performed, considering both solutions from the literature and new implementations which use different types of interfaces to ask for and give directions (voice, in-the-air arm pointing gestures, route tracing) and various embodiments (physical robot, virtual agent, interactive audio-map). Experimental results showed a marked preference for a physical robot-based system showing directions on a map over solutions using gestures, as well as a positive effect of embodiment and social behaviors. Moreover, in the comparison, physical robots were generally preferred to virtual agents.

Blockchain is receiving increasing attention from academy and industry, since it is considered a breakthrough technology that could bring huge benefits to many different sectors. In 2017, Gartner positioned blockchain close to the peak of inflated expectations, acknowledging the enthusiasm for this technology that is now largely discussed by media. In this scenario, the risk to adopt it in the wake of enthusiasm, without objectively judging its actual added value is rather high. Insurance is one the sectors that, among others, started to carefully investigate the possibilities of blockchain. For this specific sector, however, the hype cycle shows that the technology is still in the innovation trigger phase, meaning that the spectrum of possible applications has not been fully explored yet. Insurers, as with many other companies not necessarily active only in the financial sector, are currently requested to make a hard decision, that is, whether to adopt blockchain or not, and they will only know if they were right in 3–5 years. The objective of this paper is to support actors involved in this decision process by illustrating what a blockchain is, analyzing its advantages and disadvantages, as well as discussing several use cases taken from the insurance sector, which could easily be extended to other domains.

Telemedicine scenarios include today in-hospital care management, remote teleconsulting, collaborative diagnosis and emergency situations handling. Different types of information need to be accessed by means of etherogeneous client devices in different communication environments in order to enable high quality continuous sanitary assistance delivery wherever and whenever needed. In this paper, a Web-based telemedicine architecture based on Java, XML and XSL technologies is presented. By providing dynamic content delivery services and Java based client applications for medical data consultation and modification, the system enables effective access to an Electronic Patient Record based standard database by means of any device equipped with a Web browser, such as traditional Personal Computers and workstation as well as modern Personal Digital Assistants. The effectiveness of the proposed architecture has been evaluated in different scenarios, experiencing fixed and mobile clinical data transmissions over Local Area Networks, wireless LANs and wide coverage telecommunication network including GSM and GPRS.

Abstract When moving in generic indoor environments, robotic platforms generally rely solely on information provided by onboard sensors to determine their position and orientation. However, the lack of absolute references often leads to the introduction of severe drifts in estimates computed, making autonomous operations really hard to accomplish. This paper proposes a solution to alleviate the impact of the above issues by combining two vision-based pose estimation techniques working on relative and absolute coordinate systems, respectively. In particular, the unknown ground features in the images that are captured by the vertical camera of a mobile platform are processed by a vision-based odometry algorithm, which is capable of estimating the relative frame-to-frame movements. Then, errors accumulated in the above step are corrected using artificial markers displaced at known positions in the environment. The markers are framed from time to time, which allows the robot to maintain the drifts bounded by additionally providing it with the navigation commands needed for autonomous flight. Accuracy and robustness of the designed technique are demonstrated using an off-the-shelf quadrotor via extensive experimental tests.

Sensors are becoming ubiquitous in all areas of science, technology, and society. In this Special Issue on “Sensors for Entertainment”, developments in progress and the current state of application scenarios for sensors in the field of entertainment is explored.