In the context of recent developments in logistics, the efficient and flexible deployment of autonomous robotic systems remains a significant challenge, particularly in semi-structured, flexible environments, typically encountered in small residences, warehouses, or medium-sized industrial facilities, where there is minimal potential for infrastructural and/or procedural enhancements to facilitate robotic automation. Such environments pose a significant problem to automated solutions, since the environment is flexible and partially unknown, cluttered and human-center. This paper presents a modular architecture for autonomous robotic logistics designed to enhance operational efficiency through adaptive control, real-time decision-making, and IoT integration. The proposed system employs a hierarchical architecture that separates high-level task planning from lowlevel motion control, facilitating scalability and simplifying task management. The architecture supports multiple autonomous robots capable of dynamic task allocation, path planning, and predictive control to improve reliability and minimise task execution time. This work contributes to the development of a novel class of robotic logistics systems that are capable of operating in semi-structured environments. These systems are distinguished by their ability to combine the advantages of traditional large-scale automation solutions with the flexibility and cost-effectiveness of small-scale robotic systems.

Industry 5.0 improves human-machine collaboration by integrating Artificial Intelligence (AI) and Extended Reality (XR) into industrial environments. This paper presents a structured Reference Architecture for a system that addresses industrial environments within the Industry 5.0 paradigm, iteratively refined based on evolving business and technical requirements. Designed for scalability, interoperability, and flexibility, it enables seamless interaction between XR applications, AI-powered decision support tools, and industrial systems. The architecture incorporates an enterprise architecture perspective that addresses industry-driven use cases and user scenarios from six pilot applications. Key components, including XR applications, AI recognition models, digital twins (DTs), and an orchestration hub, are outlined. The business layer is built on user stories that reflect real-world industrial needs from various sectors, and future directions for extending the architecture within Industry 5.0 ecosystems are discussed.

As food safety is undergoing through significant challenges due to recent food scandals, and the consumers demands for products of higher quality is increasing, the need for better knowledge of the food production processes and adoption of data sharing practices in the product and supply chain management are emerging. To address those issues, data sharing platforms have been introduced as essential tools for creating high value from data with secure and mutually beneficial multi-partner data sharing fascilitation. Blockchain technology, through its inhereted distributed nature can help to build trust mechanisms to enhance transparency and security dimension of food chains. In this work we propose a novel security mechanism for proper authentication and authorization when accessing resources through an agrifood data platform. Our proposed methodology aims to deliver sophisticated backbone service capabilities that will enable trusted, secure, automated, robust and controlled data transactions for food certification to all food sector businesses that demand easy, fast, and actionable access to variegating food safety data from multiple devices and in various settings.

Artificial Intelligence (AI) advances are pushing the boundaries across research domains with AI-driven solutions in healthcare claiming a significant share. A key objective of these studies concerns the timely prediction of various pathological conditions. Sepsis is a life-threatening syndrome and one of the main causes of death in intensive care unit (ICU) patients. As it becomes a major health problem worldwide, sepsis early prediction could assist healthcare professionals towards making informed clinical decisions, and thereby, significantly reducing the sepsis' morbidity and mortality. A notable body of literature involving the use of AI for sepsis prediction exists. However, to the best of our knowledge, only a handful of studies focus on performing a systematic review of the AI enabled solutions for sepsis prediction in ICUs. In this context, the present paper aims to identify knowledge gaps, stimulate interest and yield motivations for future research. Moreover, to discuss ethical and explainability aspects and associated challenges. The literature search was conducted between February 2023 and April 2023 and considered eligible articles published within the last five years.

Elderly and mobility impaired people need special attention during bathing activities, since these tasks are demanding in body flexibility. Our aim is to build an assistive robotic bathing system, in order to increase the independence and safety of this procedure. Towards this end, the expertise of professional carers for bathing sequences and appropriate motions have to be adopted, in order to achieve natural, physical human - robot interaction. In this paper a Navigation Function (NF) approach is proposed in order to reproduce the way an expert clinical carer executes the bathing activities by means of construction repulsive potential fields ("virtual obstacles") for an assistive bath robot. The produced vector field, constructed based on the demonstration procedure, is used for real-time motion behavior planning tasks, which exploits the visual information from Depth sensors and the advantages of the NF approach, to estimate the reference pose for the end- effector of the assistive robotic system. The proposed method guarantees globally asymptotic convergence to the learned from demonstration washing motion, within the deformable and moving body-part limits, while in addition, restricted areas on the body surface are avoided. The proposed method is evaluated using real experimental data, obtained from human subjects during pouring water task demonstration.

This paper presents a novel system for automatic early detection of wild forest-fire using optical and thermal cameras at ground station and mounted on Unmanned Aerial Systems (UAS). The proposed system can detect and identify forest fires threats in real-time, and at the same time it is capable to notify the interested parties and authorities by providing alerts and important information (e.g. specific location, environmental conditions, etc.). Early recognition and detection of forest fires is a very challenging problem. Numerous potential sources of error leads to an increased rate of false positives (false alarms). The proposed system addresses them by exploiting the complementarities between thermal and optical cameras located at a panoramic static ground location together with the same type of cameras mounted onboard a (or potentially more) UAS. Also, the system is equipped with sensors to monitor and take into account the environmental conditions for the on the fly threat assessment. All data are fused together for an automated risk assessment. The proposed system has been integrated and it is ready for experimental testing and validation in close-to-operational conditions in field fire experiments with controlled safety conditions carry out in Pano Platres forest in Cyprus.

In this work, we present a novel framework for on-line human gait stability prediction of the elderly users of an intelligent robotic rollator using Long Short Term Memory (LSTM) networks, fusing multimodal RGB-D and Laser Range Finder (LRF) data from non-wearable sensors. A Deep Learning (DL) based approach is used for the upper body pose estimation. The detected pose is used for estimating the body Center of Mass (CoM) using Unscented Kalman Filter (UKF). An Augmented Gait State Estimation framework exploits the LRF data to estimate the legs' positions and the respective gait phase. These estimates are the inputs of an encoder-decoder sequence to sequence model which predicts the gait stability state as Safe or Fall Risk walking. It is validated with data from real patients, by exploring different network architectures, hyperparameter settings and by comparing the proposed method with other baselines. The presented LSTM-based human gait stability predictor is shown to provide robust predictions of the human stability state, and thus has the potential to be integrated into a general user-adaptive control architecture as a fall-risk alarm.

In this paper we describe a control strategy for a user-adaptive human-robot system for an intelligent robotic Mobility Assistive Device (MAD)using raw data from a single laser-range-finder (LRF)mounted on the MAD and scanning the walking area. The proposed control architecture consists of three modules. In the first module, a previously proposed methodology (termed IMM-PDA-PF)delivers the augmented human state estimation of the user by providing robust leg tracking and on-line estimation of the human gait phases. This information is processed at the next module for providing the pathological gait parametrization and characterization, by computing specific gait parameters for each gait cycle. These gait parameters form the feature vector that classifies the user in a certain class related to risk of fall. Those are of particular significance to the system, since the gait parameters and the respective class are used in the third module, i.e. the human-robot formation controller, in order to adapt the desired formation of the human-robot system, by selecting the appropriate control variables. The experimental evaluation comprises gait data from real patients, and demonstrates the stability of the human-robot formation control, indicating the importance of incorporating an on-line gait characterization of the user, using non-wearable and non-invasive methods, in the context of a robotic MAD.

Tracking human gait accurately and robustly constitutes a key factor for a smart robotic walker, aiming to provide assistance to patients with different mobility impairment. A context-aware assistive robot needs constant knowledge of the user's kinematic state to assess the gait status and adjust its movement properly to provide optimal assistance. In this work, we experimentally validate the performance of two gait tracking algorithms using data from elderly patients; the first algorithm employs a Kalman Filter (KF), while the second one tracks the user legs separately using two probabilistically associated Particle Filters (PFs). The algorithms are compared according to their accuracy and robustness, using data captured from real experiments, where elderly subjects performed specific walking scenarios with physical assistance from a prototype Robotic Rollator. Sensorial data were provided by a laser rangefinder mounted on the robotic platform recording the movement of the user's legs. The accuracy of the proposed algorithms is analysed and validated with respect to ground truth data provided by a Motion Capture system tracking a set of visual markers worn by the patients. The robustness of the two tracking algorithms is also analysed comparatively in a complex maneuvering scenario. Current experimental findings demonstrate the superior performance of the PFs in difficult cases of occlusions and clutter, where KF tracking often fails.

When designing a user-friendly Mobility Assistive Device (MAD) for mobility constrained people, it is important to take into account the diverse spectrum of disabilities, which results to completely different needs to be covered by the MAD for each specific user. An intelligent adaptive behavior is necessary. In this work we present experimental results, using an in house developed methodology for assessing the gait of users with different mobility status while interacting with a robotic MAD. We use data from a laser scanner, mounted on the MAD to track the legs using Particle Filters and Probabilistic Data Association (PDA-PF). The legs' states are fed to an HMM-based pathological gait cycle recognition system to compute in real-time the gait parameters that are crucial for the mobility status characterization of the user. We aim to show that a gait assessment system would be an important feedback for an intelligent MAD. Thus, we use this system to compare the gaits of the subjects using two different control settings of the MAD and we experimentally validate the ability of our system to recognize the impact of the control designs on the users' walking performance. The results demonstrate that a generic control scheme does not meet every patient's needs, and therefore, an Adaptive Context-Aware MAD (ACA MAD), that can understand the specific needs of the user, is important for enhancing the human-robot physical interaction.

Elderly people have particular needs in performing bathing activities, since these tasks require body flexibility. Our aim is to build an assistive robotic bath system, in order to increase the independence and safety of this procedure. Towards this end, the expertise of professional carers for bathing sequences and appropriate motions has to be adopted, in order to achieve natural, physical human - robot interaction. In this paper, a real-time end-effector motion planning method for an assistive bath robot, using on-line Point-Cloud information, is proposed. The visual feedback obtained from Kinect depth sensor is employed to adapt suitable washing paths to the user's body part motion and deformable surface. We make use of a navigation function-based controller, with guarantied globally uniformly asymptotic stability, and bijective transformations for the adaptation of the paths. Experiments were conducted with a rigid rectangular object for validation purposes, while a female subject took part to the experiment in order to evaluate and demonstrate the basic concepts of the proposed methodology.

For a robotic walker designed to assist mobility constrained people, it is important to take into account the different spectrum of pathological walking patterns, which result into completely different needs to be covered for each specific user. For a deployable intelligent assistant robot it is necessary to have a precise gait analysis system, providing real-time monitoring of the user and extracting specific gait parameters, which are associated with the rehabilitation progress and the risk of fall. In this paper, we present a completely non-invasive framework for the on-line analysis of pathological human gait and the recognition of specific gait phases and events. The performance of this gait analysis system is assessed, in particular, as related to the estimation of double support phases, which are typically difficult to extract reliably, especially when applying non-wearable and non-intrusive technologies. Furthermore, the duration of double support phases constitutes an important gait parameter and a critical indicator in pathological gait patterns. The performance of this framework is assessed using real data collected from an ensemble of elderly persons with different pathologies. The estimated gait parameters are experimentally validated using ground truth data provided by a Motion Capture system. The results obtained and presented in this paper demonstrate that the proposed human data analysis (modeling, learning and inference) framework has the potential to support efficient detection and classification of specific walking pathologies, as needed to empower a cognitive robotic mobility-assistance device with user-adaptive and context-aware functionalities.

The precise analysis of a patient's or an elderly person's walking pattern is very important for an effective intelligent active mobility assistance robot. This walking pattern can be described by a cyclic motion, which can be modeled using the consecutive gait phases. In this paper, we present a completely non-invasive framework for analyzing and recognizing a pathological human walking gait pattern. Our framework utilizes a laser range finder sensor to detect and track the human legs, and an appropriately synthesized Hidden Markov Model (HMM) for state estimation, and recognition of the gait patterns. We demonstrate the applicability of this setup using real data, collected from an ensemble of different elderly persons with a number of pathologies. The results presented in this paper demonstrate that the proposed human data analysis scheme has the potential to provide the necessary methodological (modeling, inference, and learning) framework for a cognitive behavior-based robot control system. More specifically, the proposed framework has the potential to be used for the classification of specific walking pathologies, which is needed for the development of a context-aware robot mobility assistant.

For an effective intelligent active mobility assistance robot, the walking pattern of a patient or an elderly person has to be analyzed precisely. A well-known fact is that the walking patterns are gaits, that is, cyclic patterns with several consecutive phases. These cyclic motions can be modeled using the consecutive gait phases. In this paper, we present a completely non-invasive framework for analyzing a normal human walking gait pattern. Our framework utilizes a laser range finder sensor to collect the data, a combination of filters to preprocess these data, and an appropriately synthesized Hidden Markov Model (HMM) for state estimation, and recognition of the gait data. We demonstrate the applicability of this setup using real data, collected from an ensemble of different persons. The results presented in this paper demonstrate that the proposed human data analysis scheme has the potential to provide the necessary methodological (modeling, inference, and learning) framework for a cognitive behavior-based robot control system. More specifically, the proposed framework has the potential to be used for the recognition of abnormal gait patterns and the subsequent classification of specific walking pathologies, which is needed for the development of a context-aware robot mobility assistant.

In this paper we present a polynomial navigation function (NF) for a sphere world that can be constructed almost locally, with partial knowledge of the environment. The presented navigation function is C2and as a result the computational complexity is very low, while the construction uses local knowledge and information. Moreover, an almost locally computable diffeomorphism between convex obstacles and spheres is presented, allowing the NF scheme to be used in a workspace populated by convex obstacles. Our approach is not strictly local in the epsiv sense, i.e., the field around a point is not influenced only by an e region around the point, but rather it is local in the sense that the NF around each obstacle is influenced only by the obstacle and the adjacent obstacles. In particular, we require, in the vicinity of an obstacle, the distance between the obstacle and the adjacent obstacles. Simulations are presented to verify this approach.

We present a methodology to steer the end effector of a robotic manipulator, which is constrained in terms of joint rates, on the surface within the workspace. We develop controllers for stabilizing the end effector to a point, and for tracking a trajectory on this surface, while respecting the input constraints. We show that the resulting closed loop system is uniformly asymptotically stable and we verify our analytical development with computer simulations.

In this paper we present a new navigation function for a sphere world that can be computed locally with limited knowledge of the environment. By requiring smooth and not analytic NF, the effect of each obstacle is exactly nullified outside a sensing zone around the obstacle (the only required parameter is the width of the sensing zone). This allows the computation of the navigation function using information from a single obstacle each time. We present simulations to verify the validity of this approach.

In this paper we present a methodology to drive the end effector of a robotic manipulator across the surface of an object in the workspace, and at the same time the manipulator can apply a force to the object, through its end-effector. Three typical tasks are considered, namely stabilization of the end effector over the object's surface and applying a specific force on it, motion planning and eventually trajectory tracking of the end effector across the object's surface. The proposed controllers utilize navigation functions and are based on the belt zone vector fields concept. The derived dynamic controllers are realized using an integrator backstepping methodology. The derived feedback based controllers guarantee global convergence and collision avoidance. The closed form solution provides fast feedback rendering the methodology particularly suitable for implementation on real time systems. The properties of the proposed methodology are verified through non-trivial computer simulations.

In this paper we present a methodology that drives and stabilizes a robotic agent moving in a three dimensional environment, to a 2-dimensional manifold embedded in the workspace. Once the agent reaches the manifold, depending on the application, it performs a motion planning or a trajectory tracking task. Appropriately constructed belt-zone vector fields guarantee that the agent will not depart the 2-D manifold proximity area, while carrying out the motion planning or trajectory tracking task. The derived closed form feedback control law guarantees global convergence and collision avoidance. The properties of the proposed algorithm are verified through non-trivial computer simulations.