Collaborative robots in manufacturing offer significant potential for developing synergies between the skills of the workforce and the capabilities of the robots, increasing efficiency and reducing the psycho-physical effort required from workers. One of the main barriers to the adoption of these systems is the workers' lack of trust in robots, which can negatively affect both performance and well-being. To address this issue, a precise monitoring phase must be conducted with sensors and algorithms that enable data fusion from different sources. Nevertheless, in an operative context, the presence of cumbersome setups to monitor both workers and cobots can slow down performance and create bias and unsatisfactory working conditions. For this reason, this work proposes a framework that describes the transition from an integrated Human Digital Twin toward a lighter monitoring setup, exploiting the potential of Machine Learning algorithms during the operative phase to reduce the number of required sensors. In fact, while extensive data is valuable during the design phase of collaborative workstations, the operational phase should minimize sensor use, leveraging pre-gathered data to train Machine Learning networks for estimating missing quantities. To achieve such a level of data quality in the pre-deployment and design phases, we introduce an algorithm for real-time alignment of body poses estimated by different Motion Capture technologies. This method provides accurate, occlusion-robust body pose estimation while also solving the drifting phenomena that affect inertial measurement units. Consequently, the proposed approach establishes a robust foundation for enhancing Human-Robot Collaboration by ensuring precise and reliable real-time body pose estimation, a crucial step for advancing safety and efficiency in the manufacturing field.

This paper presents Hi-ROS (Human Interaction in ROS), an open source framework focused on real-time accurate assessment of human motion. The system offers a series of tools to track multiple people in real-time by exploiting a calibrated camera network. No assumptions are made about the typology or number of cameras, nor about the body pose estimation algorithm used to extract the 3D poses of the people in the scene. The tools provided by Hi-ROS include a Skeleton Tracker to ensure temporal consistency of the detected poses, a Skeleton Merger to fuse the tracks from multiple cameras, thus limiting flickering phenomena, a Skeleton Optimizer to ensure limb length consistency, and a Skeleton Filter to perform real-time smoothing of the detected joint trajectories. Accuracy, tracking robustness, and real-time performance of the proposed system were evaluated on a public dataset, containing both single-person and multi-person sequences with up to 4 people interacting. The results obtained using different subsets of the proposed tools show how the complete Hi-ROS pipeline provides accurate and reliable estimates also in challenging scenarios, with a reduction of the RMSE of up to 27 % with respect to a pure tracking approach. This work aims to push forward the development of unobtrusive human–robot interaction applications, multi-person automated posture analyses, rehabilitation performance assessments, and any possible application enabled by real-time accurate assessment of human motion via markerless motion capture.

Research on wearable robotic devices is fostered by the need to assist and restore human locomotion, which is essential for most daily life activities. Despite a continuous technological advancement, many challenges are to be faced before establishing the use of these devices as part of the rehabilitation process. A main concern is how to actively engage the users and monitor how they are affected by the exoskeleton. Basic analyses, such as measuring walking speed, must be extended to include analysis on balance, brain activity, and evaluation of neuromechanical effects. This scenario requires the use of different distributed sensor devices that must be carefully synchronized. This work describes the architecture we implemented to extend the capabilities of the H2 exoskeleton. As a proof of the architecture validity, we show the online estimation of users' muscle forces through the acquisition of electromyographic signals, that drive neuromusculoskeletal models. The proposed framework, built upon the Robot Operating System (ROS), aims to be reusable for a wide range of setups, including different exoskeletons and sensors.

With this work we introduce a novel methodology for the simulation of walking of a humanoid robot. Motion capture technology is used to calibrate the dynamics engine internal parameters and validate the simulated motor task. Results showed the calibrated contact model allows predicting dynamically consistent ground reaction forces and producing realistic whole-body kinematics.

The inclusion of robotic systems in physiotherapy allows developing new solutions for the rehabilitation and support of disabled people. Our research addresses the core problem for the advancement of such applications: the availability of a human machine interface offering intuitive control of robotic devices. In this paper we present an EMG-driven model of the human lower limb based on that previously developed by Lloyd et al. We then introduce a set of enhancements that allow reducing time and memory requirements and provide real-time performances for the control of a lower limb powered orthosis.

The next generation of tools for rehabilitation robotics requires advanced human-robot interfaces able to activate the device as soon as patient's motion intention is raised. This paper investigated the suitability of Support Vector Machine (SVM) classifiers for identification of locomotion intentions from surface electromyography (sEMG) data. A phase-dependent approach, based on foot contact and foot push off events, was employed in order to contextualize muscle activation signals. Good accuracy is demonstrated on experimental data from three healthy subjects. Classification has also been tested for different subsets of EMG features and muscles, aiming to identify a minimal setup required for the control of an EMG-based exoskeleton for rehabilitation purposes.

Abstract Next generation e‐learning platforms will support cooperative use of geographically distributed educational resources as an aggregated environment, thus enabling a more effective knowledge exchange. Sharing this goal, our research activity addresses the definition and implementation of a service‐based infrastructure for content distribution and multimedia streaming. The proposed architecture provides enough flexibility, extensibility, and scalability to cope with the ever‐increasing heterogeneity and mobility of edge devices. In this paper, we initially illustrate the general objectives and requirements in the development of an e‐learning oriented application for multimedia content discovery, access, and distribution in a virtual community. Architectural considerations have motivated the use of Grid technologies as they provide access to resources and services of different administrative domains in a transparent, seamless, and secure way. The Grid‐based architecture has been endowed with a number of services including discovery and streaming of multimedia objects, multimedia content update, quality of service (QoS) management, and support for user authentication and authorization. A multimedia application based on the architecture is described and evaluated on a multi‐domain network. Copyright © 2005 John Wiley & Sons, Ltd.

This paper focuses on the role of real-time operation support in mobile robot control architectures for service applications. We show that a control architecture with integrated real-time features ensures better performance in terms of accuracy in navigation and reactivity to external events, compared with an architecture where no provision for real-time has been made. We argue that proper consideration to real-time operation should be given in order to ensure safe, dependable robot operation in human-inhabited environments. Along the paper, we describe features of YARA, a software framework improving dependability of mobile robot architectures by virtue of its support for real-time operation.

We investigate the effectiveness of several types of virtual fixtures in a robot programming by demonstration interface. We show that while all types of virtual fixtures examined yield a significant reduction in the number of errors in tight tolerance peg-in-hole tasks, color and sound fixtures generally outperform a tactile fixture in terms of both execution time of successful trials and error rate. We have found also that when users perceive that the task is very difficult but the system is providing some help by means of a virtual fixture, they tend to spend more time trying to achieve a successful task execution. Thus, for difficult tasks the benefits of virtual fixturing are better reflected in a reduction of the error rate than in a decreased execution time. We conjecture that these trends are related to the limitations of currently available interfaces for human-robot interaction through virtual environments and to the different strategies adopted by the users to cope with such limitations in high-accuracy tasks.

Distributed telerobotic applications exploiting Internet-related technologies, such as virtual laboratories and on-line robots, require effective techniques for timely delivery of sensory data to remote clients. In these systems, there is a need to distribute increasing quantities of sensory data to a potentially large number of clients during system operation. In this paper, we describe and evaluate three implementations of a sensory data distribution subsystem in the context of a CORBA-based framework for telerobotic applications. Experimental results show that solutions exploiting CORBA services and based on the event channel paradigm represent a viable alternative to ad-hoc solutions. The overhead associated to CORBA services becomes less significant with larger message size. Moreover, these services ensure portability, extensibility, reduction in programming complexity, and improved scalability when the number of clients increases.

Probabilistic path planning driven by a potential field is a well established technique and has been successfully exploited to solve complex problems arising in a variety of domains. However, planners implementing this approach are rather inefficient in dealing with certain types of local minima occurring in the potential field, especially those characterized by deep or large attraction basins. In this paper, we present a potential field planner combining "smart" escape motions from local minima with parallel computation to improve overall performance. The results obtained show significant improvement in planning time, along with remarkable reduction in standard deviation. A performance comparison on a benchmark problem of the potential field planner and an existing, state-of-the-art planner is also included. Our investigation confirms the effectiveness of potential field as heuristic to solve difficult path planning problems.

The technological developments in distributed systems have led to new telerobotic applications, such as virtual laboratories and remote maintenance of complex equipment. These applications must satisfy both the general requirements of distributed computing, e.g. location transparency and interoperability, and the domain-specific requirements of reconfigurability, guaranteed performance, real-time operation, and cooperation among robots and sensory systems. In this paper, we describe a software framework for distributed telerobotic systems exploiting advanced CORBA features, including Asynchronous Method Invocation and real-time priorities. The framework allows development of portable multithreaded client-server applications supporting concurrent and preemptable actions in the target robot system, and has been evaluated in a laboratory setup including a robot manipulator and two cameras accessible by multiple clients.

Randomized motion planners are greatly affected by the efficiency and robustness of algorithms for collision checking of robot configurations. A number of powerful collision detection algorithms are currently available to the research community although their relative capabilities and performance cannot be easily compared due to the many factors involved. We have experimentally evaluated collision detection packages within the context of motion planning for rigid and articulated robots in 3D workspaces. Artificial and realistic problems have been chosen as benchmarks to assess package behavior with different object models. Reported experimental results should help the user in choosing the appropriate collision detection package. In this paper we also present the framework we exploited in our planner to allow pluggable distance computation functions and keep the code simple and easy to maintain.

This paper presents a motion planning algorithm capable of exploiting the experience gained in previous path computations in the same static workspace. The algorithm takes advantage of a parallel approach to speed up computation and compile a graph retaining useful knowledge about the environment. Experimental results assess the performance improvement of the experience-based planner over the parallel implementation of a well-known probabilistic motion planning algorithm.

Due to the high number of sensors managed and need to perform complex reasoning activities, real-time control systems of autonomous robots exhibit a high potential for overload, i.e., real-time tasks missing their deadlines. In these systems overload should be regarded as a likely occurrence and hence managed accordingly. In this paper we illustrate a novel scheduling technique for adaptation of soft real-time load to available computational capacity in the context of autonomous robot control architectures. The technique is based on rate modulation of a set of periodic tasks in a range of admissible rates. The technique is shown to be easily computable and several variations in implementation are reviewed within the paper.

Describes a real-time library providing facilities useful in the design of robot control architectures. The library supports structured creation of reactive and deliberative modules, dynamic modification of relevant real-time parameters, generation of timing fault handlers, measurement and monitoring of execution times. This support enables adaptation of the rate of computation of real-time modules to the rate of change of the external world, and hence better tuning of robot behavior to the world uncertainty and dynamics. The real-time library has been put to work by designing a hybrid control architecture for a robot performing a kitting task. In the prototype experiment described in the paper, a Puma 560 robot manipulator is fed with parts by a small mobile robot. The control architecture governing Puma operations dynamically allocates computational resources to reactive and deliberative modules, according to the task level priorities.