In the Industry 5.0 era, the focus shifts from basic automation to fostering collaboration between humans and robots. Trust is crucial in this new paradigm, enabling smooth interaction, especially for users with limited robotics knowledge. This study presents a novel framework that uses human hand gestures and voice commands to control robot movements, aiming to enhance trust, reduce cognitive workload, and minimize task execution time-key for efficient manufacturing. In automated systems, swift completion of micromanagement tasks is essential to prevent process disruption. To evaluate this framework, we devised a testbed scenario within an automated carbon fiber transportation and draping process, focusing on a maintenance task as the micromanagement challenge. Participants inspected the gripper, guided the robot along a defined path, and performed maintenance, such as attaching cables. Two conditions were tested: gestures and voice commands versus a smartPAD. The results showed that gestures and voice commands increased trust, lowered cognitive load, and shortened execution times, improving overall manufacturing efficiency.

Predicting human motion is vital for enhancing safety and efficiency in human-robot collaboration. Researchers have dedicated significant efforts to developing accurate human models, often involving optimization and task-specific information. However, regardless of complexity, all models come with uncertainties that robots need to recognize to make informed decisions. This paper examines the performance of two simple models using the Unscented Kalman Filter (UKF) to filter and predict future human poses. Moreover, a combined version of the models is implemented using an Interacting Multiple Model (IMM) estimator. The objective is to evaluate the algorithms' prediction accuracy and uncertainty across various human-robot interaction scenarios under different operating conditions. This analysis identifies suitable settings where the simple model can be effective and highlights situations where a more complex system might be necessary.

The programming complexity of industrial robots significantly limits their expansion in complex industrial applications. Consequently, research has focused extensively on the development of intuitive programming methods.This article proposes a framework for task-oriented programming introducing an intuitive and modular task structure. The framework provides an algorithm able to optimize the execution parameter of the tasks. A physical simulation environment allows accurate parameter optimization in a virtual environment providing feasible and safe results. Efficiency tests demonstrated the method’s effectiveness, and a comparison with genetic and Bayesian -based ones have been conducted.

Human-Robot collaborative transportation is a promising technology that combines the strength of humans and robots. The most common approaches rely on methodologies that exploit force-sensing. However, the drawbacks are multiple. First, the magnitude of force applied might be limited to avoid damages. Then, force measurements might be unidirectional according to the material properties; e.g., compression forces are not measurable for fabrics. This paper proposes an approach based on the estimation of the deformation state of the manipulated object from depth images. Specifically, the segmented depth image of the manipulated object are fed to a Convolutional Neural Network (CNN) model to estimate the current deformation status. Compared with the desired deformation, the current deformation status is used to generate the robot’s twist command. The methodology is proved in a mobile robot application, where carbon-fiber fabrics are transported. A comparison with the state-of-the-art is reported proving that the proposed method is more accurate and more repeatable.

Human-robot co-manipulation of large but lightweight elements made by soft materials, such as fabrics, composites, sheets of paper/cardboard, is a challenging operation that presents several relevant industrial applications. As the primary limit, the force applied on the material must be unidirectional (i.e., the user can only pull the element). Its magnitude needs to be limited to avoid damages to the material itself. This paper proposes using a 3D camera to track the deformation of soft materials for human-robot co-manipulation. Thanks to a Convolutional Neural Network (CNN), the acquired depth image is processed to estimate the element deformation. The output of the CNN is the feedback for the robot controller to track a given set-point of deformation. The set-point tracking will avoid excessive material deformation, enabling a vision-based robot manual guidance.

The paper introduces a robotic manipulation framework suitable for the execution of manipulation tasks. Based on the ROS platform, the framework provides advanced motion planning and control functionalities for robotic systems to guarantee a high level of autonomy during the execution of an action. The integrated motion planning module can handle multiple motion planners to generate collision-free trajectories for a given planning scene that can be dynamically uploaded. In the same way, the robot controllers can be changed online on the base of the robot behavior required by the action under execution. The motion control of the robotic system is fully demanded to the manipulation framework relieving the upper control layers from the management of low-level functionalities and the task geometrical information. The framework can be used downstream to a task planner or as a standalone library to simplify the robot programming in complex manipulation tasks.

Hand-eye calibration of laser profile sensors is the process of extracting the homogeneous transformation between the laser profile sensor frame and the end-effector frame of a robot in order to express the data extracted by the sensor in the robot’s global coordinate system. For laser profile scanners this is a challenging procedure, as they provide data only in two dimensions and state-of-the-art calibration procedures require the use of specialised calibration targets. This paper presents a novel method to extract the translation-part of the hand-eye calibration matrix with rotation-part known a priori in a target-agnostic way. Our methodology is applicable to any 2D image or 3D object as a calibration target and can also be performed in situ in the final application. The method is experimentally validated on a real robot-sensor setup with 2D and 3D targets.

The paper introduce a robotics software control architecture suitable for the development of complete robotic industrial applications. The architecture fuse the state-of-the-art software technologies in a single standalone platform to provide an easy integration between all the software components necessary to control a robotic application, i.e. PLC logic, robot motion program. The main goal is to provide an architecture as much as possible hardware agnostic to develop easily portable software.

In this paper we propose the use of a dynamic model in which the effects of temperature on friction are considered to develop a virtual force sensor for industrial robot manipulators. The estimation of the inertial parameters and of the friction model are explained. The effectiveness of the virtual force sensor has been proven in a polishing task. In fact, the interaction forces between the robot and the environment has been measured both with the virtual force sensor and a common load cell. Moreover, the advantages provided by considering the temperature dependency are highlighted.

The identification of the dynamic model of a robotic manipulator represents a fundamental step for designing high performance model-based controllers. Despite the huge number of works presented on this topic, the symbolic dynamic model reduction (i.e., the identification of the set of parameters observable through the measure of joint torques and positions) still remain a challenging task, characterized from tailored solutions, adapted from time to time to specific families of mechanisms. The work here presented, introduces an automatic and analytical reduction of the dynamic model, based on a multi-dimensional Fourier series decomposition of the dynamic equations. The procedure enables to obtain symbolically the base dynamic parameters (BP) starting from a given kinematic structure. The Fourier based model reduction can be applied indifferently both to open- and closed-chain kinematics. A simulated example shows the effectiveness of the proposed algorithm.

Robot dynamics is commonly modeled as a linear function of the robot kinematic state from a set of dynamic parametersintomotortorques. Baseparameters(i.e.thesetoftheoreticallydemonstratedlinearly-independent parameters) can be reduced to a subset of “essential” parameters by eliminating those that are negligible with respect to their contribution in motor torques. However, generic trajectories, if not properly defined, couple thecontributionofsuchessentialparametersintothemotortorques,actuallyreducingtheestimationaccuracy of the dynamics parameters. The work presented here introduces an index for evaluating correlation influence among essential parameters along an executed trajectory. Such index is then exploited for an optimal search of excitatory patterns consistent with the kinematical coupling constraints. The method is experimentally compared with the results achievable by one of the most popular IRs dynamic calibration method.

Notwithstanding the research on dynamic modelling of Industrial Robots (IRs hereafter) covers the last three decades, improvements are necessary to enable IRs adoption in technological tasks where high dynamics or interaction with environment is needed, e.g. deburring, milling, laser cutting etc. Indeed, this class of applications displays even more the necessity of high-accuracy tracking especially in workspace sub-regions, while common IR dynamic calibration methods often span the workspace at large (in term of positions and high velocities) resulting in an averagely fitting models. Open issues are therefore on the applicability/scalability of standard methods in workspace sub-regions and on the metrics used for the calibration performance evaluation. The paper proposes an algorithm designed to high-accuracy local dynamic identification, comparing it with the results achievable by a common IRs dynamic calibration method and by the same method scaled to a workspace sub-region. In addition, unlike from standard, the here reported experimental comparison is made by evaluating the torque prediction error for IRs robot moving along path programmed by standard/commercial IR motion planner and not along path belonging to the same template-class of trajectory used in identification phase.

Model-based control are affected by the accuracy of dynamic calibration. For industrial robots, identification techniques predominantly involve rigid body models linearized on a set of minimal lumped parameters that are estimated along excitatory trajectories made by suitable/optimal path. Although the physical meaning of the estimated lumped models is often lost (e.g. negative inertia values), these methodologies get remarkably results when well-conditioned trajectories are applied. Nonetheless, such trajectories have usually to span the workspace at large, resulting in an averagely fitting model. In many technological tasks, instead, the region of dynamics applications is limited, and generation of trajectories in such workspace sub-region results in different specialized models that should increase the predictability of local behavior. Besides this consideration, the paper presents a genetic-based selection of trajectories in constrained sub-region. The methodology places under optimization paths generated by a commercial industrial robot interpolator, and the genes (i.e. the degrees-of-freedom) of the evolutionary algorithms corresponds to a finite set of few via-points and velocities, just like standard motion programming of industrial robots. Remarkably, experiments demonstrate that this algorithm design feature allows a good matching of foreseen current and the actual measured in different task conditions.