Lower Limb Exoskeletons (LLEs) are wearable robotic systems that provide mechanical power to the user. Human-exoskeleton (HE) connections must guarantee the subsistence of the user’s natural behavior during the interaction, avoiding the exertion of undesired forces, i.e., the robot must be transparent. Since transparency is an essential feature of exoskeletons’ design, numerous works focus on its maximization, e.g., employing passive joints at the HE interfaces. Given the inherent complications of repeatedly prototyping and experimentally testing a device, modeling the exoskeleton and its physical interaction with the user emerges as an extremely valuable approach for assessing the design effects. This paper proposes a novel method to compare different exoskeleton configurations with a flexible simulation tool. This approach contemplates simulating the dynamics of the device, including its interaction with the wearer, to evaluate multiple connection mechanism designs along with the kinematics and actuation of the LLE. This evaluation is based on the minimization of the interaction wrenches through an optimization process that includes the impedance parameters at the interfaces as optimization variables and the similarity of the LLE’s joint variables trajectories with the motion of the wearer’s articulations. Exploratory tests are conducted using the Wearable Walker LLE in different configurations and measuring the interaction forces. Experimental data are then compared to the optimization outcomes, proving that the proposed method provides contact wrench estimations consistent with the collected measurements and previous outcomes from the literature.

Estimating the pose of objects through vision is essential to make robotic platforms interact with the environment. Yet, it presents many challenges, often related to the lack of flexibility and generalizability of state-of-the-art solutions. Diffusion models are a cutting-edge neural architecture transforming 2D and 3D computer vision, outlining remarkable performances in zero-shot novel-view synthesis. Such a use case is particularly intriguing for reconstructing 3D objects. However, localizing objects in unstructured environments is rather unexplored. To this end, this work presents Zero123-6D, the first work to demonstrate the utility of Diffusion Model-based novel-view-synthesizers in enhancing RGB 6D pose estimation at category-level, by integrating them with feature extraction techniques. Novel View Synthesis allows to obtain a coarse pose that is refined through an online optimization method introduced in this work to deal with intra-category geometric differences. In such a way, the outlined method shows reduction in data requirements, removal of the necessity of depth information in zero-shot category-level 6D pose estimation task, and increased performance, quantitatively demonstrated through experiments on the CO3D dataset.

Haptic interaction often requires stabilizing controllers for safety. The Time-Domain Passivity Approach guarantees passivity (then stability) by observing and dissipating energy generated from active elements in a network. The dissipating action is performed by a Passivity Controller, whose action is commanded to the physically limited robot actuators. Thus, the controller stabilizing action should be in turn limited in order to command displayable references to the actuators. This problem is rarely taken into account in the literature and when it is, the limitation is neither directly related to the actuator power limits, nor to the robot's current configuration. The limits of the currently adopted strategies leave room for improvement. In this paper, a new strategy to limit the Passivity Controller action is proposed taking into account both the physical limits of the actuators and the robot configuration. This new strategy is experimentally tested against the classical one based on the sampling time. In the experiment, a human interacts with a virtual wall in a Virtual Environment through a haptic interface. The wall induces an unstable behavior passivated with the two limitation strategies. The results clearly state the benefits introduced by the proposed strategy in two relevant cases.

Railways safety regulations require the drivers acting on a pedal to signal that they are awake and vigilant. This implies a noticeable biomechanical load on the driver. In this work, we propose an embedded computer-vision system that, using a single camera placed on the cockpit of a train, analyzes the driver's watchfulness by monitoring gaze and eyelid blinking. The proposed system provides a consensus to the control logic of the train, which replaces the action on the pedal. The system copes with the peculiar conditions of a train's cabin, such as variable illumination, the variability of the driver's face image and presence of more than one people in the cabin. At the same time, it accounts for the constraints posed by the international regulation (Safety Integrity Level IV) and customer specifications, which poses limitations on the hardware selection. The paper presents the design and evaluation of this system. The former includes the hardware selection and the algorithm development, whereas the latter includes preliminary tests for tuning the algorithm and final tests in real operating conditions for the evaluation of the system. The results show that the systems always correctly detects the driver's watchfulness and, importantly, it does not report false positives. As such, it can be used to avoid the driver's action on the pedal and reducing the biomechanical load.

This work addresses an automated system that supports the "Maintenance on Condition" paradigm. The system automatically processes auto-recorded video streams collected by a wayside camera capture device, and proceeds to a preliminary analysis in search for posture errors.We present and discuss a novel system that provides a proper identification of pantograph heads from video sources or image sequences and proceeds to recover the 3D asset from a single 2D image. The system exploits modern Deep Learning (DL) networks to extract a preliminary pantograph shape from the video sequence, then applies an optimization algorithm to estimate accurate position and orientation.A comparative and exhaustive analysis with few hundreds of samples shows the accuracy of the algorithm and the robustness to changes in illumination and other environmental conditions.

Railway line surveillance is important for providing safe and smooth travel of trains under effects of environmental or human-generated damages to the railway. This work presents a Structure from Motion pipeline specifically designed with the aim of supporting the monitoring operations of the railway infrastructure using a monocular camera mounted on the train's tractor. Within this work we developed a dynamical reconstruction instrument based on the mathematics of the projective geometry for handling the problem of localization, by triangulation techniques of points, lines, whole objects and of other known elements. Exploiting the a-priori knowledge of the scene structure (known track gauge) and the camera intrinsic parameters it is possible to reconstruct in metric dimension the trajectory of the train and the position of the detected object. The approach proposed here combines Computer Vision techniques to detect the significant elements and to classify a set of features with Bayesian filtering. Algorithms for this specific purposes have been developed in order to identify the rail track geometry, and a line-based approach has been adopted to assess the camera poses. Starting from these first estimates, a manifold Unscented Kalman Filter operates on the set of robustly matched features, fusing heterogeneous cues about the camera orientation and using RANSAC to find the best solution. Consequently, the detected objects can be triangulated and localized. An analysis using real captures is reported to prove the quality of the results obtained.

The shortage of specialist caused by the increased need for medical examinations has stimulated the application of robotics technologies to telemedicine. For some of the most common medical examinations such as ultrasonography and palpation, doctors exploit haptic feedback to formulate a diagnosis. This is especially true for palpation, where haptic feedback plays the biggest role. In this paper, we present a novel 3-Degrees-of-Freedom (DoFs) robotic interface which is designed to be integrated into a telepalpation system. In particular, this haptic interface is the master of a teleoperation loop in which the slave operates on the patient. Therefore, its design allows the doctor to explore the whole patient's abdomen while providing the doctor with a haptic feedback when in contact with the patient. A preliminary assessment of the interface is also presented: three participants were asked to detect the presence and the size of a sphere without visual clues. Results show that the interface is suitable for the application in remote palpation.

For a proactive and user-centered robotic assistance and communication, an assistive robot must make decisions about the level of assistance to be provided. Therefore, the robot must be aware of the preferences and the capabilities of the elderly. At the same time, relying on a sensing setup which is totally embedded in the assistive robot would increase its usability. In the framework of the RAMCIP project, a novel skills evaluation methodology has been developed to make the robot aware of the user's perceptual, cognitive and motor skills. This paper presents such a methodology and its preliminary evaluation. Based on a task analysis of the activities for which the robot provides assistance, the user's skills are given a score which is updated at different time scales based on the source of information. Highly reliable information is gathered from caregivers at a low rate by means of a graphical interface hosted by the robot. This information refers to standard medical examinations. Based on the modules for motion tracking, object and activity recognition, specific actions of ADL are selected to update motor skills score at a higher rate, which is typically twice per day. The two sources of information are then fused in a Kalman filter. Preliminary results on the illustrative example of arm precision show that the robot's sensing and cognitive capabilities suffice to obtain a state-of-the-art evaluation of the arm precision skill.

Teleoperation in robotic embodiments allows operators to perform and program manipulation tasks with better accuracy, dexterity, and visualization than what is possible with traditional human-robot interaction paradigms. However, the perception of cues (e.g., egocentric distances) relevant to task execution, is known to be distorted in virtual environments due to many factors, which can be grouped into technical, human, and methodological categories. This phenomenon becomes more pronounced in a low-cost/encumbrance setup, where the dynamic environment is captured with color and depth (RGB-D) cameras and presented in a virtual environment. In this paper, the effects of augmented reality (AR) are evaluated as a tool to deliver additional information, which helps in overcoming the differences in perception between telepresence and actual presence. The AR feedback is used to improve the embodiment illusion and to guide the operator during task execution. The AR setup, comprising an RGB-D camera and a head-mounted display, is integrated with the Baxter robot and evaluated by involving 22 participants in an experiment while they execute a pick-and-place task, taking into account their expertise in AR/virtual reality (VR) and gaming. The use of AR results in enhancing the accuracy and efficiency of the task performance, besides significantly reducing the effect of the differences in skillfulness between the participants. Furthermore, it is found that the sense of presence and embodiment for the participant is positively affected by different types of AR.

The introduction of teleoperated robots in scenarios in which human manipulation dexterity does not have to be limited by the teleoperation system is one of the greatest challenges in the field of telecontrol. In this paper we propose an approach for capturing and transferring human manupulative skills to a robotic manipulator that is able to supervise the teleoperation process by means of a proactive support that introduces elastic motion constraints around specific motion primitives. By exploiting not only information about motion, but also the relationships between the manipulator and the objects, in the form of affordances, the system is capable of assisting the human operator in order to improve the teleoperation task performances. We test the algorithm with a Microsoft Kinect RGBD sensor that allows human body pose tracking and the semi-humanoid Baxter Robot by Rethink Robotics as teleoperated platform.

A great part of today's industries tends to invest on automatic machines that can replace or collaborate with humans in typical repetitive tasks. Despite their high motion and positioning precision, most of these robots operate blindly, causing the working system to be poorly robust to even slight changes of the working environment. A solution to such an issue might be to make the robots capable of readjusting their actions according to a perceptual feedback, in particular made of visual data. However in many application single camera systems lack of field-of-view, accuracy and precise 3D localization. In this work we propose a multi-camera framework for the visual servoing of a collaborative robot that has to manipulate untextured industrial pieces. The robot is supposed to recognize the object of interest and reach it with its end-effector. We adopt a multi-camera approach that overcomes typical issues related to single-camera schemes. The system contains an object recognition module that extends an already existing algorithm for 2D detection on images to approximate 3D localization in space. A final probabilistic recursive estimation process combines the measures provided by the different sensors in order to improve the target pose computation, considering all the possible uncertainty and disturbance sources that may interfer, thus making the system more robust and efficient.

The remote examination is becoming more and more important as the population is aging and experts lack as ever before. We propose a novel system which is suitable for remote examination and in particular for remote auscultation. The system is located at two sites, at the patient site a robot holds a stethoscope which is placed on the patient while an RGB-D sensor streams a video of the scene. At the doctor site, the doctor interacts with a haptic interface that allows s/he to move the stethoscope while receiving haptic feedback when the stethoscope is in contact with the patient and looking at the remote scene on a screen. The doctor listens to the noise from the stethoscope thanks to a diaphragm and a headset where the audio stream from the patient site is played. After presenting this novel system, we show its effectiveness by means of experiments that involve auscultation-like tasks. We show the usability of the system to place the stethoscope, the usability to hear correctly the noise of the heart as well as the overall quality of the streamed audio signal.

Kinesthetic teaching is a viable solution for programming robots in the execution of new tasks thanks to the human-mediated mapping between the task objectives and the robot joint space. Redundant designs and differences from human kinematics pose challenges in the efficient execution of the teaching task. In this work we employ vibrotactile feedback letting operators understand specific kinematic constraints such as reaching joint limits and singularities. The experimentation with a Baxter robot and a four-motor vibrotactile bracelet is reported showing the effectiveness of the proposed enhancement to the kinesthetic teaching task.

Nowadays robotics educational platforms play an important role in the development and testing of new robotic technologies. These systems offer at low cost the possibility to access and experiment basic robot functionalities. In this paper, we examined the KUKA youBot: an omnidirectional mobile platform equipped with a five DOFs (Degrees of Freedom) robotic arm. The current internal design of the control loops limits severely its performances.

This paper presents the MOTORE++ system, a Portable, mobile haptic interface with the unique feature of using its wheels to deploy rehabilitation exercises to users. MOTORE++ is a battery powered device, with hot swap batteries, capable to run autonomously for almost an hour. MOTORS++ is a technology shift enhancement improvement over the previous version. Its new electronic architecture allows several communication protocols (RS232, WiFi, Bluetooth) that provide link stability in all running scenarios. The device also implements a cutting edge computing architecture and a novel position sensor jointly developed with Anoto®to deliver precise sensor fusion and stability to the localization and force generation algorithms. In the present papers we will describe the relevant new features of the device, and we will review the major innovation with respect to the existing mobile haptic interfaces.

The use of drones in agriculture is becoming more and more popular. The paper presents a novel approach to distinguish between different field's plowing techniques by means of an RGB-D sensor. The presented system can be easily integrated in commercially available Unmanned Aerial Vehicles (UAVs). In order to successfully classify the plowing techniques, two different measurement algorithms have been developed. Experimental tests show that the proposed methodology is able to provide a good classification of the field's plowing depths.

The shortage of physicians afflicting developed countries encourages engineers and doctors to collaborate towards the development of telemedicine. In particular, robotic systems have the potential for helping doctors making examination. A very common examination that can be the goal of a robotic system is palpation. Most of the robotics systems that have been developed for palpation present interesting features such as integrating augmented reality environments or allowing for hand free interaction. In this paper we present a novel palpation system that allows us to perform virtual palpation of real objects by means of a haptic and an augmented reality feedback. This system features an encountered-type haptic interface in which the haptic feedback is calculated by a collision detection algorithm that is based on online recording of the surface to be touched. The system allows the users to remove their hand from the haptic interface end-effector that follows the user's hand thanks to the tracking performed by a Leap Motion. We show that the system provides a natural interaction during the contact-non contact switch, a suitable force during indentation, and it allows to discriminate objects within the body through the haptic channel.

This work investigates the use of a highly immersive telepresence system for industrial robotics. A Robot Operating System integrated framework is presented where a remote robot is controlled through operator's movements and muscle contractions captured with a wearable device. An augmented 3D visual feedback is sent to the user providing the remote environment scenario from the robot's point of view and additional information pertaining to the task execution. The system proposed, using robot mounted RGB-D camera, identifies known objects and relates their pose to robot arm pose and to targets relevant to the task execution. The system is preliminary validated during a pick-and-place task using a Baxter robot. The experiment shows the practicability and the effectiveness of the proposed approach.

Wearable motion tracking systems represent a breakthrough in ecological motion tracking. Their effectiveness has been proved in many fields, from performance assessment to human-robot interaction. Most of the approaches are based on the exploitation of optimal probabilistic filtering of inertial motion units (IMUs) signals, ranging from linear Kalman Filters (KF) to Particle filters (PF). Since most of the models are highly nonlinear, filters such as Extended Kalman Filter (EKF) and Unscented Kalman Filter (UKF) are typically used. These approaches cause all the variables of the models to be correlated each other. Probabilistic Graphical Models (PGM) are a framework for probabilistic reasoning that allows to explicitly declare the actual dependencies among variables. In this paper we propose a novel algorithm for motion tracking with IMUs based on PGM. The model is compared to the state of the art UKF algorithm in tracking the human upper limb. The results show that the proposed approach perform a slightly better compared to the UKF.

Learning to hand-write is a complex task and is fundamental for the development of a correct language reasoning and understanding. This work presents a multimodal system that focuses on the learning of handwriting movements. The system is thought for children usage providing engaging graphics and novel feedback technologies to accelerate the learning process. The main characteristic of the system architecture is its scalability in hardware and software components so that it is possible to employ it in any domestic setup.

In the robot programming by demonstration (PbD) framework, the high-level representation of a skill in a series of action units gives an intuitive method to program and instruct robot behaviors. In this context we present a ROS (Robot Operating System) integrated architecture for learning households manipulation tasks by one observation. The user is observed during the execution of everyday tasks, every action is analyzed and its effect is translated into changes in the environment state. During the observation a strip-like map of the task is built and stored as a sequence of actions. From the map obtained the task can be performed. A planner robustly adapts the execution both to different environment initial conditions and to possible faults, occurring during the operations. We test the capability of the chosen approach to autonomously learn and robustly perform complex tasks, such as setting up and clearing a table in a real kitchen-like environment.

This paper presents a health economic system for motor recovery in patients with the commonest cause of death in some countries, stroke. The system is based on immersive, real-time motion capture (MOCA) available for private use and at the bedside. An interactive virtual reality (VR) interface designed with auditory and visual feedback. It consists on two scenarios and a 3D character that follows the user's arm movements by using the first and third person view metaphors of interaction. Two easy and enjoyable games are proposed for each scenario. The system is designed to be adapted to several tasks with different index of difficulty (ID) for gradual motor recovery in patients with stroke. The experiments carried out on eight healthy neurologically interact volunteers have shown that our system is suitable to be used at home on training programs, giving good references for future applications on stroke arm recovery.

The present paper discusses a framework for creating flexible rehabilitation exercises on a mobile haptic interface. The approach is based on a combination of high level interactive scripting with a flexible real-time haptic control algorithm. The control problem has been decomposed into primitives such that the real-time issues are managed at low level on the mobile system, while a high level control can interact with the user through powerful and flexible scripting. The control architecture is flexible enough to operate haptic rendering on wireless mobile devices. Overall the system allows to create a large variety of rehabilitation exercises that can all share the same methodology for their parametrization and assessment. The rationale of the design and the implementation of the different control level will be provided. Design experiments, based on a rehabilitation game scenario will also be discussed.

The future of working machines winks to semi autonomy and latest technological aids to improve the quality of operations as well as the easiness of specific tasks execution. This field can take great advantage of latest human-machine interface (HMI) technologies that has been applied in the last years in field like virtual environments and robotics. The present paper discusses a novel approach for interactive operation of working machines. The approach combines traditional controls with visual/vision and haptic interactions. A wearable projection system has been introduced with the purpose of describing a wide set of localized commands recognized by the system's vision module. A preliminary setup has been developed using a simplified demonstration platform. A test session applied to a manipulation robot is presented to evaluate the performance of the proposed solutions in terms of task effectiveness, neglect tolerance, interaction effort and usability of the human-machine interface.

In this work we present a method to produce a model of human motion based on an expansion in functions series. The model is thought to reproduce the learned movements generalizing them to different conditions. We will show, with an example, how the proposed method is capable to produce the model from a reduced set of examples preserving the relevant features of the demonstrations while guaranteeing constraints at boundaries.

The Body Extender is a whole-body exoskeleton designed to operate in unknown and difficult environments, for instance in disaster areas. The Body Extender allows the wearing operator to increase its force while maintaining a high level of perception.

Most haptic devices share two main limits: they are grounded and they have limited workspace. A possible solution is to create haptic interfaces by combining mobile robots and standard grounded force-feedback devices, the so called Mobile Haptic Interfaces (MHIs). However, MHIs are characterized by dynamical limitations due to performance of the employed devices. This paper focuses on basic design issues and presents a novel (prototype) Mobile Haptics Platform that employs the coordination of numerically controlled wheel torques to render forces to a user handle placed on the top of the device. The interface, consisting in a small omni-directional robot, is link-less, fully portable and it has been designed to support home-rehabilitation exercises. In the present paper we shall review relevant choices concerning the functional aspects and the control design. In particular a specific embedded sensor fusion was implemented to allow the device to move on a desk without drifting. The sensor fusion algorithm has been optimized to provide users with a quality force feedback while ensuring accurate position tracking. The two requirements are in contrast each other and a specific variant of the Extended Kalman Filter (EKF) was required to allow the device working.

The present paper introduces a novel type of haptic interface which is fully portable and employs only onboard sensors and electronics to solve accurate localization and force feedback generation. The device offers 2DOF force control while sliding on a plane and maintaining its orientation comfortable for the user. The device generates force feedback information without any intermediate link between the motion wheels and the grasping handle. The device has been designed for application in neuro-rehabilitation protocols and it adopts specific mechanical, electrical and control solutions in order to cope with patient requirements. The paper describes the mechanical and electronic solutions as well as the most relevant features of control implementation issues that were addressed in the system design.

The present work describes the design of a Sailing simulator that includes fundamental interaction stimuli and environmental phenomena such as wind and sea conditions, vessel and sails configuration, and actions performed by drivers on real maneuvers. The behavior of the simulator takes into account most of the static and dynamic effects caused by the wind, the pilots and the sea. The motion based simulator is operated by means of levers that control all maneuvers in the ship. Simulator feedbacks include audio, visual as well as inertial cues. An interactive simulation of the dynamics of the vehicle and of the environment physics is integrated into the interactive motion based sailing simulator in order to allow real time use within application. All mathematical components have been integrated in a parametric way giving the possibility to choose among differents boats and sails types. Several environmental effects such as wind control, can be interactively controlled by a remote operator while the boat is navigating into a virtual scenario. In the following the main feature of the simulator system will be described together with the relevant activities performed to create the real-time model of the simulator. Some experimental results will also be provided.

We analyze the impact of the delay between the sensors and the visualization on the performance at a catching task in virtual environment. Testers have been asked to interact with a virtual environment displayed on a 2D screen in front of them, catching, with the virtual hand, virtual balls falling from the top of the screen. Two thresholds have been inferred: a behavioral threshold delay beyond which the behavioral organization is sensibly affected and a performance threshold delay beyond which task performance begins to worsen. We found a drop in performance when the total delay is over 70-80 ms, yet without significant changes in the organization of successful catches. Although the presence of a threshold on behavior is still to be further investigated, these two thresholds give a practical indication for the design and the validation of virtual reality based training systems. This is especially important in the context of training human skills in virtual environment: in particular to assess the quality of a training platform simulating the three ball cascade juggling pattern.

In this paper we describe two concrete applications of visibility to robotics. Both applications are related to the situation in which a robot is in a known environment, of which a map is given. The basic concept on the basis of our contributions is that of mathematical visibility. The visibility polygon of a point or of an edge can be used in different robot tasks, i.e. obstacle avoidance, path planning and localization. The strength of visibility is that different information can be extracted directly from the map through an offline operation. Furthermore the computation of the visibility polygon of a point can be applied instead of the classical methods used for the sensor reading simulation based on ray casting techniques.

This paper presents a novel use of sensor sytem for human gait recognition evolution to be employed in virtual environments exploration. The system allows free human motion inside a virtual environment employing human gait recognition. Experimental sessions have been organized in order to acquire acceleration data related to walking and running of several subjects. We present an algorithm that recognizes a person gait in real-time. The recognized motion can be used to enhance the presence of the user in the virtual environment. A simple scenario has been developed to assess the system functionality. The experiments carried out show that our system is suitable to classify human motion, count steps and, moreover, can be used both in virtual and augmented reality (VR) environments for an improved interaction.

While control theory for bilateral teleoperation systems under constant time communication delay is well developed, the research on time-varying communication delay systems is still ongoing. Most wave-based approaches proposed in literature to deal with time-varying delay appear too conservative resulting in high degradation from the constant time delay case. We have already proposed a bilateral control scheme with energy balance monitoring over packet switched communication networks. In the previous work, we dealt with a simplify situation where the time-varying was in the communication channel from master to the slave. However, we did not implement and test the system with a more complex scenario in which the delay was in both communication paths. The paper presents a complete bilateral teleoperation control scheme to compensate nonlinearity introduced by an Internet like communication channel. The system implements intelligent strategies to maintain the system passivity while it deals with position drift compensation, packets loss and blackouts management. Experimental results using the proposed control scheme are shown.

Any teleoperation system involving two distant devices is affected by communication delay due to the physical gap between the devices. Several approaches based on wave variables have already been proposed to deal with time-varying delay. However, these approaches are too conservative resulting in high degradation from the constant time delay case. In this paper, we propose a new control scheme for bilateral teleoperation under time-varying communication delay entirely developed in the wave variables domain. The proposed method minimizes the performance degradation from the constant time delay case. Experimental results show the validity of the proposed scheme.

The present paper deals with a system architecture and a digital format to support the acquisition, storage and transfer of human skills. Virtual environments and haptic interfaces will be addressed as target platforms for the capturing and rendering of skills. There are several methodologies for approaching definition and modelling of skills, and the present work will focus on a specific approach that merges evidences from human sciences with present approaches in intelligent robotics and machine learning. This work presents a supporting tool that enables researchers to model, analyse and control the skill transfer process. In addition this work will provide an overview of a skill transfer framework, and information related to the models of skill representation that are being employed.

Fixed-Base Exoskeleton applications have increased rapidly in the last few years, evidently as part of promising rehabilitation robotic programs of the robotics worldwide community, where in particular Human-Robot-Interaction (HRI) plays an important role in its design and control because they are tightly coupled to human-limbs. Exoskeletons embrace HRI as well as technological and theoretical challenges towards real and effective rehabilitation. In this realm, some questions arise, to name a few, what is the relationship between the exchanged energy between human and exoskeleton? How can we assess rehabilitation factors under HRI philosophy? This paper attempts to establish answers to these questions, which can be embodied into rehabilitation HRI using a Light-Exoskeleton. A compliant haptic guidance scheme for human arm subject to minimum-jerk-trajectories criterion is proposed. Preliminary experimental results provide further insight of a haptic guidance scheme taking into account decisive factors into the HRI such as human pose, haptic guidance control, reaching and tracking tasks, the complexity of the virtual environment, and muscles activity.

A recent trend in virtual environments aims at making the user free of devices or limitations in its motion, at the benefit of immersiveness and interactivity. This work introduces an interaction paradigm that goes beyond motion based interaction, by making use of measured real forces exerted by the user in free space. The sensation of touch with virtual object is obtained by vibrotactile stimulation combining virtual contact information with measured forces. In this way the user has an additional dimension of interactivity at the benefit of immersivity, without incurring in the reduction of sense of presence introduced by grounded haptic interfaces. This paradigm is presented and discussed in particular in the context of a boxing training simulation, as one of the possible application scenarios.

In this paper, we propose a real time 3D gesture recognition system that relies on the state based approach. The novelty of this work is the introduction of probabilistic neural networks (PNNs) to characterize the uncertain boundaries of each state. The 3D gestures are modeled as a sequence of states in a configuration space; the number of states and their spatial parameters are calculated by dynamic k-means clustering on the training data of the gesture without temporal information. Gesture recognition is performed using a simple Finite State Machine (FSM), where, each state transition depends only on the output of its corresponding PNN and optionally on its time restrictions (minimum and maximum time permitted in the state). If a recognizer reaches its final state, then it could be said that a gesture is recognized. The approach is illustrated with the implementation of a real time system that recognizes the semantic meaning of seven basic gestures of the Indian Dance, the description of the system and the technologies used, it will be described in detail in the paper.

Haptic interaction with virtual objects is typically tool mediated, or in alternative it constraints userpsilas body in someway, like it happens in exoskeletons that cannot be totally transparent. Encounter type haptic interfaces aim at hands free haptic interaction, that is more natural and can be applied in contexts in which the user moves in the space around the interface. This paper presents a system that allows a palm based haptic interaction in a large workspace using the principle of encountered haptics. The system is evaluated in a surface exploration task and compared against the same task performed with a standard haptic interface. In this type of task this type of interface is better suited, providing a smoother feedback to the hand during the movement over the surface.

This work presents a study of performance improvement of unskilled people to drawn simple sketches. We have assisted the unskilled people when drawn using a haptic interface which acts as a virtual guide taking advantage of its force feedback capabilities. In the first part of the study, an application has been developed to extract fixed templates from image files; the application extract the principal edges in the images to build output trajectories (templates) that are used by haptic interface controller, after that, the user can "fill" the virtual templates with the assistance of the force feedback capabilities of the interface. Based on the obtained results for fixed templates, a second application was developed; the user can generate interactive templates indicating where he/she desires to put a geometrical template (circle, line or arc) inside the haptic interface's workplace; once that the position of the template is defined, the interface shows its position graphically and then user can fill it assisted by the haptic interface force feedback.

The present work analyzes the effects on learning and cognitive processes when augmenting user feedback by means of the force feedback devices. Different haptic devices have been employed to test three different cognitive processes: feature and shape recognition, trajectory learning and co-writing. In order to assess the effectiveness of the haptic feedback we compared in the three test cases the force feedback with alternate methods of displaying feedback (acoustic and visual stimuli), as a result we found that information provided by haptic interfaces complements the one which is achieved by vision and audio and, if integrated helps to improve specific kind of performances. After reviewing the three different test cases and the achieved result we will try to provide some indications on how to exploit haptic feedback to improve gesture performance in skill training application.

In this paper the design and construction of a novel wireless Dataglove based on new flexible goniometric sensor technology is described. The device is characterized by a low cost and rugged construction and no requires calibration before its use. Indeed, the sensors used are purely goniometric, so they are not sensible to dimensions of the user's hand. The Dataglove can measure the angular displacement of the fingers hand using 11 sensors, each sensor has a resolution of 0.2 degrees, with 3 degree of accuracy in the worst case. The communication between the Dataglove and its computer Host is carried out using a 2,4 gigahertz wireless Bluetooth radio protocol, in a guaranteed range up to 10 meters with a refresh rate of 100 Hz.

Achieving realistic rendering of thin and spatially sharp objects (needles, for example) is an important open problem in computer haptics. Intrinsic mechanical properties of users, such as limb inertia, as well as mechanical and bandwidth limitations in haptic interfaces make this a very challenging problem. A successful rendering algorithm should also provide stable contact with a haptic virtual object. Here, perceptual illusions have been used to overcome some of these limitations to render objects with perceived sharp features. The feasibility of the approach was tested using a haptics-to-vision matching task. Results suggest that lateral-force-based illusory shapes can be used to render sharp objects, while also providing stable contact during virtual object exploration

Since their first usage simulators have been employed in training staff in civil aeronautics and in military fields to improve driving skills without compromising safety of people and machines. The system proposed in this paper is suited to transfer this activity into the industrial field, in particular an innovative fork-lift simulator is presented. Actually most frequent causes of accident with fork-lifts are wrong manoeuvres accomplished by drivers. This simulator aims to improve skills in driving and handling materials using a fork-lift. The system can reply inertial feedback on the operator and allows the user to control all the tasks of a fork-lift as driving and handling materials. The paper presents an overall view of the system including Stewart platform, supporting structure, physical based model, wash-out filter, system architecture and a video system mounted on board of the moving platform

The present paper describes the conceptual and technical design of a new multimodal device named Haptic Desktop System (HDS). Haptic Desktop System is an integrated system, which merges haptic functionalities, and VDT systems into one. Specific care has been given to HDS design for enhancing and improving human-computer interaction from the following points of view: esthetical, ergonomic and functional. In order to improve the quality of the interaction, the HDS fully integrates proprioceptive, visual, audio and haptic functionalities, into a desk while minimizing the visual interference of the physical components. In the proposed approach classic input devices (i.e. keyboard and mouse) have been replaced by new features integrated within audio and haptic. Such features allow commanding and rendering natural force stimuli in such a way that they are completely coherent and co-located with respect to the visual information. The new features of the HDS are designed for reducing considerably the mental load required to the users during interaction operations. In the present paper the design guidelines and the achieved results are reported.

One of the principal guidelines in the design of haptic devices is to provide a suitable mechanical design that can improve control performance and the force-feedback fidelity. Unfortunately these guidelines may conflict with other design objectives (reflected mass, balancing, dexterity) as well as with specifications given by users and applications. For haptic interfaces based on tendon driven actuation it is highly important to achieve an accurate model of friction losses in the transmission system, in order to be able to compensate for them through an active control. In this paper it is reported a method for modeling and control complex tendon transmissions used for driving haptic devices and robots. The presented approach can operate in realtime with very low complexity; it is applicable to all kinds of serial manipulators and provides enough flexibility to allow identification of parameters and modeling of distributed friction phenomena all along the transmission. The approach has been implemented and tested on a 4 DOF exoskeleton system, the PERCRO L-EXOS.

A 2-DOF force-feedback joystick was employed to simulate the force response of a manual gearshift of car during drive. The control law is based on an hybrid model. A state machine determines the active state of the system, according to the simulation, and changes the parameters of the dynamical model. The operator can move the gearshift lever whether such a movement would be allowed in an actual transmission under similar circumstances. The obtained performance was compared to the experimental data, measured on a real car. The simulated and experimental results match satisfactorily and the joystick gives a realistic feel of an actual manual transmission.

Many motion base simulators have been developed in the last thirty years for many different types of vehicles. In order to make a simulation more realistic, linear accelerations and angular rates are exerted on the pilot by moving the platform on which the mock-up vehicle is located. This has to be accomplished without driving the simulator out of its workspace. The software component that is in charge of this is commonly referred to as washout filter. Washout filters have been widely investigated in the past, mainly in the field of flight simulators. We present a washout filter designed for a motorcycle simulator. The solution is preliminary and follows, as a reference point, techniques previously adopted for large aircraft simulators. Differences between motorcycle and aircraft simulation are analyzed and a preliminary customized solution is proposed. The washout filter to be used to drive a motorcycle simulator currently being built at PERCRO, has been tested off-line showing good results and will soon be tested on real riders.

Many motion based simulators have been developed for many different types of vehicles. In order to make a simulation more realistic, linear accelerations and angular rates are exerted on the pilot by moving the platform on which the mock-up vehicle is located. This has to be accomplished without driving the simulator out of its work-space. The software component that is in charge of this is commonly referred to as the washout filter. Washout filters have been widely investigated in the past, mainly in the field of flight simulators. We present a washout filter designed for a motorcycle simulator. The solution is preliminary and follows, as a reference point, techniques previously adopted for large aircraft simulators. Differences between motorcycle and aircraft simulation are analyzed and a preliminary customized solution is proposed. The washout filter, which will be used to drive a motorcycle simulator, currently being built at PERCRO, has been tested off-line showing good results and will soon be tested on real riders.

Intention tremor severely compromises everyday life tasks in patients suffering with multiple sclerosis or Parkinson's disease. The paper reports the current achievements in the analysis of subjects' movements. The trajectories produced by patients affected by tremor are investigated. Indexing procedures for the evaluation of the tremor which is present in the trajectories are proposed. Such indexes should be sensitive to tremor while they are not to ordinary movements. The properties of the indexes have been verified both with analytical considerations and with numerical tests. An experimental setup has been realized for the analysis of tremor on patients affected by multiple sclerosis tremor. The data collected within this experiment have been compared with expected results. Furthermore the indexing procedure has been applied for the evaluation of a filtering system. The case of handwriting has been chosen as the reference task for the evaluation of achieved results. The results of clinical tests are presented. Finally the applicability of the index-based procedures to the control of filtering systems is discussed. The control architectures in the case of force-feedback less interfaces as well as haptic interfaces are presented and discussed.

The hand force feedback system is an anthropomorphic haptic interface for the replication of the forces arising during grasping and fine manipulation operations. It is composed of four independent finger dorsal exoskeletons which wrap up four fingers of the human hand (the little finger is excluded). Each finger possesses three electrically actuated DOF placed in correspondence with the human finger flexion axes and a passive DOF allowing finger abduction movements. Each exoskeleton finger has three points of attachment to the operator's finger (two for the thumb) at the middle of the phalanges. Mechanical fixtures guarantee that just a force perpendicular to the finger and in its sagittal plane is exchanged at each point of attachment. Such force component is sensed and it is actively controlled in feedback. The paper illustrates the design and testing of the controller for the thumb exoskeleton. First the mechanical system is analyzed and the features which influence the controller design, such as the presence of unidirectional tendon transmission, are modeled. Then haptic controllers, i.e. feedback controllers aiming at improving the performance of the device when used as a haptic interface for virtual environments or telemanipulation, are designed and tested experimentally. Finally the experimental results are discussed.

Haptic interfaces have ordinarily been used as tools in the exploration of virtual environments as well as masters in teleoperation systems. In these systems the haptic interfaces have been commonly employed only to reproduce and simulate contact experience with a simulated or remote environment. This use is good enough for the realization of high quality simulators such as VETIR. All actions in simulators are generated by a precise set of rules which determine the correct feedback stimuli to be presented to the operator. In the article, haptic interfaces are presented as stand alone systems having their own and independent control. Consequently we explore the control capabilities and we identify a new extended interaction paradigm which provides to the machine the capability of interpreting the human actions and organizing a new high level feedback. The paper introduces a general structure for such a type of systems called reactive systems. A large set of interactive systems, such as tutors, trainers as well as technological aids for rehabilitation can be easily realized with the presented architecture.

We present an immersive virtual environment (VE) including visual, auditory and haptic feedbacks, which has been designed specifically to help to recover or improve the motor dexterity of the arm and hand in patients affected by disorders of motor coordination. The realization of an effective haptic feedback on the human arm and hand is the most critical issue for such application. Innovative approaches have been followed for the monitoring of upper limb movements; the replication of forces on the human hand, the real time simulation of interactions between user upper limb and virtual objects, including the simulation of stable grasps; and the accurate synchronization of the various sensory feedbacks. The rehabilitation exercises, which have already been implemented and tested on healthy subjects are described. The major technical solutions adopted are discussed.

This paper presents a new control model, ideal for teleoperation, which takes into account the problems arising with heavily delayed communicating systems. This is done with the help of a general purpose neural network and a specific dedicated training structure which is able to train the network and to minimize the network errors due to convergence problems. The principal aim of this model is to give more stability to the data flux reducing the uncertainties due to a variable delay present in the communication support.