This paper presents a study on key Human Factors considered in a Human-Robot Interaction (HRI) manufacturing scenario. We investigate user-perceived trust in collaborative robots, targeting crucial aspects such as acceptance, interaction fluency, cognitive workload, and usability. The experimental study is focused on a car door inspection and assembly task, where a human operator and a cobot operate side by side within a small shared workspace. The second link of the robot platform is equipped with 30 distributed proximity sensors that map the surrounding environment and detect nearby obstacles. Two distinct control strategies are evaluated for generating collision avoidance motions. The first strategy, Sensor Mounting (SM), leverages the sensors' mounting locations as control inputs to generate reactive avoidance motions, as described in [1]. The second approach, Whole-Body (WB), utilizes any point within the robot's geometric model, enabling both sensorized and non-sensorized links to respond to unpredictable events, as detailed in [2]. 24 subjects were involved in the experimental trials, performing assembly actions alongside a UR10e robot. Without prior knowledge of the control strategies employed, participants completed an online survey to rate their overall experience in both robot operating conditions (SM and WB). Results suggested that the WB proximity-aware controller did not compromise the system's perceived usability, trustworthiness, or efficiency. No statistically significant differences were observed among key subjective metrics (p > 0.05). Acceptance, usefulness, and satisfaction scores remained consistently high across both conditions. Finally, qualitative insights suggested users' preference for the WB control strategy, often described as more adaptive and responsive.

Tactile gesture recognition systems play a crucial role in Human-Robot Interaction (HRI) by enabling intuitive communication between humans and robots. The literature mainly addresses this problem by applying machine learning techniques to classify sequences of tactile images encoding the pressure distribution generated when executing the gestures. However, some gestures can be hard to differentiate based on the information provided by tactile images alone.In this paper, we present a simple yet effective way to improve the accuracy of a gesture recognition classifier. Our approach focuses solely on processing the tactile images used as input by the classifier. In particular, we propose to explicitly highlight the dynamics of the contact in the tactile image by computing the dense optical flow. This additional information makes it easier to distinguish between gestures that produce similar tactile images but exhibit different contact dynamics. We validate the proposed approach in a tactile gesture recognition task, showing that a classifier trained on tactile images augmented with optical flow information achieved a 9% improvement in gesture classification accuracy compared to one trained on standard tactile images.

Robots performing tasks in challenging environments must be supported by control or planning algorithms that exploit sensor feedback to effectively plan the robot’s actions. In this paper, we propose a reactive control law that simultaneously utilizes proximity and tactile feedback to perform a pick-and-place task in an unknown and cluttered environment. Specifically, the presented solution leverages proximity sensing obtained from distributed Time of Flight (ToF) sensors to avoid collision when this does not interfere with the pick-and-place task. Safety is guaranteed by a higher-priority task using tactile feedback that reduces contact forces when a collision occurs. Additionally, we compare the effectiveness of this control scheme with a collision detection and reaction scheme based solely on tactile sensing. Our results demonstrate that the proposed approach reduces the collisions with the environment and the task execution time of the pick-and-place operation.

Tactile data processing or classification is commonly performed using tactile images, i.e. two-dimensional representation of the applied contact. When tactile sensors cover the whole robot body, their relative spatial relations change depending on the robot posture. If the applied contact involves two adjacent links, the current relations among the tactile elements must be considered in order to generate a tactile image that preserves the contact shape. The goal of this paper is to propose a method for creating tactile images from pressure measurement acquired from a large area tactile system, where the relative displacement among the sensors fixed to different links change according to the robot posture. The proposed approach is experimentally validated using a Baxter robot equipped with distributed tactile sensors.

This paper deals with the problem of estimating the pose of tactile elements (i.e. taxels) composing a robotic skin covering the whole body of a robot. This problem arises when a robot skin technology has to be integrated into an already existing robotic platform. To date, the integration process is done by hand and it is not possible to predict where the sensor will be placed on the robot body. This paper presents a novel approach based on a RGB-D camera and exploiting the motion capabilities of the robot for activating the skin sensors. The method uses the measurements of the camera to reconstruct the unknown robot body outer shape and to compute how the area can be touched by the robot. The taxels responses and the related contact centroids are used for estimating the position of the sensors. Our method is based on few assumptions and is a step towards a calibration procedure that can be executed autonomously by a robot. Experiments performed on the Baxter robotic platform demonstrate the effectiveness of the presented approach obtaining an average position error less than 2mm.

This paper deals with the problem of using the tactile feedback generated by a robotic skin for discriminating a human hand touch from a generic contact. Humans understand collaboration intentions through different sensing modalities such as vision, hearing and touch. Among them, a physical interaction is mainly used for demonstrating or correcting a kind of motion and is usually started by touching with the hands the other human body. Until recently, it was difficult to perform the same in human-robot cooperation due to the lack of large-scale tactile systems functionally similar to a human skin. Our approach consists in transforming measurements of sensors distributed on the robot body into a convenient 2D representation of the contact shape, i.e., a contact image, then applying image classification techniques in order to discriminate a human touch from unexpected collisions. Experiments have been performed on a robotic skin composed of 768 pressure sensors integrated on a Baxter robot forearm. More than 1800 contact images have been generated from 43 different persons for training and testing two machine learning algorithms: Bag of Visual Words and Convolutional Neural Networks. The experimental results show that both approaches are valid, obtaining a classification accuracy higher than 96%.

This paper presents a novel approach for recognizing a human hand touch by processing pressure measurements generated by a robotic skin. Physical cooperation among humans is mainly based on the sense of touch and usually starts with hand contacts. If a robot can distinguish a human touch from a generic contact, the human-robot cooperation can be more natural and effective. The proposed approach consists in transforming the sensor pressure measurements distributed on the robot surface into a convenient 2D representation of the contact shape, i.e., a contact image. The image-based representation of contacts allows facing the problem of human touch classification by applying machine learning methods already developed for image classification. The experiments have been performed using a robotic skin, composed of 768 tactile elements, placed on a Baxter robot forearm. The contact classification has been performed using a Convolutional Neural Network obtaining an accuracy higher than 97% experimentally validating the proposed approach.

In this paper a novel multi-modal tactile sensor is presented, featuring a matrix of capacitive pressure sensors, a microphone for acoustic measurements and proximity and ambient light sensor. The sensor is fully embedded and can be easily integrated at mechanical and electrical levels with industrial grippers. Tactile sensing design has been put on the same level of additional requirements, usually overlooked in tactile sensor research, such as the mechanical interface, cable harness and robustness against continuous and repetitive operations, just to name but a few. The performances of the different sensing modalities have been assessed in a test rig for tactile sensors. Experiments have been performed in order to show the capabilities of the sensor for implementing tactile based industrial gripper control and tactile based fabric classification.

Within the past decade, extensive research has been done on large-scale tactile sensing, as a result of which, a large variety of robot skins have been developed. These robot skins are different in various aspects: the sensing modality, interconnectivity of the sensors, modularity, the communication network, etc. This variety limits portability of software among these robot skins. In this article, a middleware is proposed that is capable of interacting in principle with any robot skin, through the use of simple drivers. Primarily, the middleware acquires data in real-time and provides its applications with those data in an abstract structure. As a result, the portability of algorithms implemented for large-scale tactile data processing is greatly increased among various available and future robot skins.

This article discusses a real-time networking infrastructure for a large-scale tactile sensing system to be used with humanoid robots. In such a system, real-time networking issues are of the utmost importance. Stemming from previous work, a theoretical model is presented and experimentally validated. Tests show real-time performance in a network of distributed computational nodes, each one in charge of managing part of the tactile system.

Tactile sensing is considered a key technology for implementing complex robot interaction tasks. The contribution of this article is two-fold: (i) we propose a general-purpose algorithm for the reconstruction of deformation and force distributions for capacitance-based skin-like systems; (ii) real-time performance can be tuned according to available computational resources, which leads to an any-time formulation. Experiments (both in simulation and with real robot skin) provide a quantitative analysis of results.

In this paper, the description of a sensorized glove that has been developed to perform experiments in robot-based manipulation of clothes and objects is reported. The glove embeds a capacitive tactile sensing technology that has been designed in the past few years. The glove is used to provide an estimate of the expected tactile feedback related to involved forces and contact areas during common manipulation tasks. This information will be used in order to design a robot gripper for cloth manipulation.

This paper describes automated procedures for the design and deployment of artificial skin for humanoid robots. This problem is challenging under different perspectives: on the one hand, different robots are characterized by different shapes, thereby requiring a high degree of skin customization; on the other hand, it is necessary to define optimal criteria specifying how the skin must be placed on robot parts. This paper addresses the problem of optimally covering robot parts with tactile sensors, discussing possible solutions with reference to a specific artificial skin technology for robots, which has been developed in the past few years. Results show that it is possible to automate the majority of the required steps, with promising results in view of a future complete automation of the process.

The problem of "providing robots with the sense of touch" is fundamental in order to develop the next generations of robots capable of interacting with humans in different contexts: in daily housekeeping activities, as working partners or as caregivers, just to name a few.

This article introduces an extension of the original Parallel Force-Position control framework based on the use of tactile maps. Whole body skin systems for humanoid robots are considered a fundamental feature to improve contact interaction tasks by means of large scale tactile feedback. Stemming from previous work [1], the article describes how it is possible to extend the Parallel Force-Position control paradigm with the use of tactile maps, i.e., computational representation structures encoding the position of tactile elements located on the robot body surface. Furthermore, tactile maps are used to encode specific local features of contact trajectories, such as the desired exerted force at the contact point and the desired velocity. Results in simulation validate the approach.

This paper deals with the problem of estimating the position of tactile elements (i.e. taxels) that are mounted on a robot body part. This problem arises with the adoption of tactile systems with a large number of sensors, and it is particularly critical in those cases in which the system is made of flexible material that is deployed on a curved surface. In this scenario the location of each taxel is partially unknown and difficult to determine manually. Placing the device is in fact an inaccurate procedure that is affected by displacements in both position and orientation. Our approach is based on the idea that it is possible to automatically infer the position of the taxels by measuring the interaction forces exchanged between the sensorized part and the environment. The location of the contact is estimated through force/torque (F/T) measures gathered by a sensor mounted on the kinematic chain of the robot. Our method requires few hypotheses and can be effectively implemented on a real platform, as demonstrated by the experiments with the iCub humanoid robot.

Summary form only given. Scaled technologies continue to exhibit variability, driven by both random process effects and systematic structural effects. Process and design rule actions can be taken to reduce, or even eliminate, sources of systematic variability. Random variability is more difficult to combat, but architectural decisions can be made to limit the device sensitivity to specific random effects. A review of several current sources of technology variability is presented, and the impacts to the overall technology offering are assessed.

This paper describes an algorithm, which has been specifically designed to solve the problem of multirobot-controlled frequency coverage (MRCFC), in which a team of robots are requested to repeatedly visit a set of predefined locations of the environment according to a specified frequency distribution. The algorithm has low requirements in terms of computational power, does not require inter-robot communication, and can even be implemented on memoryless robots. Moreover, it has proven to be statistically complete as well as easily implementable on real, marketable robot swarms for real-world applications.

Even though the sense of touch is crucial for humans, most humanoid robots lack tactile sensing. While a large number of sensing technologies exist, it is not trivial to incorporate them into a robot. We have developed a compliant “skin” for humanoids that integrates a distributed pressure sensor based on capacitive technology. The skin is modular and can be deployed on nonflat surfaces. Each module scans locally a limited number of tactile-sensing elements and sends the data through a serial bus. This is a critical advantage as it reduces the number of wires. The resulting system is compact and has been successfully integrated into three different humanoid robots. We have performed tests that show that the sensor has favorable characteristics and implemented algorithms to compensate the hysteresis and drift of the sensor. Experiments with the humanoid robot iCub prove that the sensors can be used to grasp unmodeled, fragile objects.

This paper deals with the problem of calibrating a large number of tactile elements (i.e., taxels) organized in a skin sensor system after fixing them to a robot body part. This problem has not received much attention in literature because of the lack of large-scale skin sensor systems. The proposed approach is based on a controlled compliance motion with respect to external objects whose pose is known, which allows a robot to determine the location of its own taxels. The major contribution of this work is the formulation of the skin calibration problem as a maximum-likelihood mapping problem in a 6D space, where both the position and the orientation of each taxel are recovered. An effective calibration process is envisaged that, given a compliance control law that assures prolonged contact maintenance between a given body part and an external object, returns a maximum-likelihood estimate of detected taxel poses. Simulations validate the approach.

In this paper a framework for representing tactile information in robots is discussed. Control models exploiting tactile sensing are fundamental in social Human-Robot interaction tasks. Difficulties arising in rendering the sense of touch in robots are at different levels: both representation and computational issues must be considered. A layered system is proposed, which is inspired from tactile sensing in humans for building artificial somatosensory maps in robots. Experiments in simulation are used to validate the approach.

In this paper a framework for representing tactile information in robots is discussed. Control models exploiting tactile sensing are fundamental in social Human-Robot interaction tasks. Difficulties arising in rendering the sense of touch in robots are at different levels: both representation and computational issues must be considered. A layered system is proposed, which is inspired from tactile sensing in humans for building artificial somatosensory maps in robots. Experiments in simulation are used to validate the approach.

This paper describes a framework for representing physical interaction tasks using tactile feedback. Although contact feedback has been widely exploited to control interaction with objects, the direct use of tactile information in designing and representing physical interaction rules has not received comparable attention in the literature. The missing link between algorithms implementing models of interaction and frameworks providing tactile information is one of the possible reasons. The major contribution of the paper is a working method to build a map of tactile sensors attached to a robot body and a control law using such a map to tune physical interaction with an external object. Experiments are used to validate the approach.

This DOI is not currently attached to any metadata records. DOIs can’t actually ever be deleted (they’re persistent), but sometimes our members create DOIs in error. We do have a process to approximate deletion which we follow only in rare cases where the DOI has been genuinely created in error, and most crucially, if the DOI has never been published anywhere online or in print and never otherwise distributed to or communicated with anyone (authors, readers, reviewers, etc.

Eye motion strategies in animals and humans have the goal of optimizing visual perception, therefore, the study of eye motions plays an important role in the design of humanoid robot eye systems. Saccades and smooth pursuit in humans and primates are a significant class of ocular motions, which obey the so called Listing's Law, stating that admissible eye's orientations have always zero torsion during motion. In this paper we present a model of the eye plant proving that Listing's Law implementation is strongly related with the geometry of the eye and its actuation system (extraocular muscles). The proposed model has been used to provide the guidelines for the design of a tendon driven humanoid robot eye. Experimental tests, presented in this paper, validate the model by performing a quantitative comparison of the performance of the robot eye with physiological data measured in humans and primates during saccades.

This paper presents a model for a tendon driven robot eye designed to emulate the actual saccadic and smooth pursuit movements performed by human eyes. Physiological saccadic motions obey the so called Listing's law which constrains the admissible eye's angular velocities. The paper discusses conditions making possible to implement the Listing's law on a purely mechanical basis, i.e. without active control

The problem of grasping and manipulating rigid objects using a multifingered robotic system is dealt with. A hierarchical two-level closed-loop trajectory tracking control strategy is presented in order to achieve the manipulation task, together with a complimentary force control, for object grasping, which makes use of a formulation of grasping forces decomposition.

Presents the first prototype of the DIST-Hand dextrous gripper. DIST-Hand is a 4-fingered tendon driven device with 16 degrees of freedom, designed for experiments in the area of grasping control, and tele-manipulation. The current version of the gripper is lightweight and can be easily installed on the various existing robots. The paper outlines the kinematic and structural characteristics of the hand. Furthermore, some general methodological issues addressed during the design phase are discussed.

AMADEUS is a dexterous subsea robot hand incorporating force and slip contact sensing, using fluid-filled tentacles for fingers. Hydraulic pressure variations in each of three flexible tubes (bellows) in each finger create a bending moment, and consequent motion or increase in contact force during grasping. Such fingers have inherent passive compliance, no moving parts, and are naturally depth pressure-compensated, making them ideal for reliable use in the deep ocean. In addition to the mechanical design, development of the hand has also been considered for closed loop finger position and force control, coordinated finger motion for grasping, force and slip sensor development/signal processing, and reactive world modelling/planning for supervisory "blind grasping". Initially, the application focus is for marine science tasks, but broader roles in offshore oil and gas, salvage, and military use are foreseen. Phase I of the project has been completed, with the construction of a first prototype. This paper summarizes the developments in Phase I. Further details for each area of investigation are referenced.

This paper presents the prototype of the DIST robotic hand developed at the Graal-Lab of the University of Genova. In the current version, the hand is formed by a palm supporting four fingers. Each finger has four rotational degrees of freedom, and is equipped with custom built position sensors using Hall-effect transducers. The actuation of each finger is done using six tendons driven by five computer controlled DC motors. A kinematic analysis has been performed using simulation tools, with the goal of building a mechanism with size and mobility similar to those of human hand.

A two layered hierarchical architecture is considered as the fundamental scheme for the closed loop control of robots in operational space. By considering different kinds of information transfer from the outer to the inner controllers, it is shown that the architecture can take into account a wide class of control schemes, then the analysis of their stability and robustness properties can be performed in a unified framework. Then on this basis some general results concerning such properties are given.

In this work we propose a Lyapunov based design of velocity observers and the controller for stable trajectory tracking by a robotic manipulator. It is shown how the proposed design is exponentially stable over a finite domain, and, in the high gain approximation, exponentially stable in the large domain. Moreover, the design proposed leads naturally to a reduced order observer structure, with considerable implementation advantages.

A class of coordinate transformations is introduced in order to derive the dynamic equation of a constrained manipulator on the constraining manifold. A theorem of existence is given, and some practical computational guidelines, based on the analytic knowledge of the equation of the constraining manifold, are outlined in order to compute the transformation off-line. If the analytic equations of the constraining manifold are inaccurate, the planned motion will not belong to the true manifold. It is then shown how the desired trajectories, both in the transformed domain and in the joint space domain, may be modified online to force a motion that belongs to the true manifold.>

This paper deals with the problem of the vision-based feedback control of an eye-head system. Movements of the visual sensors are controlled in order to gather optimal measurements, in relation to the kinematic structure of the system and the task that is currently being executed. In more explicit biological terms, it is the problem of, given a particular sensor, how to use movement to ameliorate perception. In particular it is proved that movements can essentially be guided by the achievement of the minimum cost function related with the sensitivity of the transformation from world to camera coordinates. This allows one to define proper control objectives, for the coordinated eye-head movements; it also formally motivates some relevant aspects of the biological vision like fixation, vergence and eye-head compensation.>

The problem of grasping rigid objects using robot hands is addressed. In particular, a representation of the space of the internal forces is given. Within this framework, an algorithm is proposed for the determination of feasible grasp and manipulation forces. sufficient conditions for the solution of this problem of coordinated manipulation are given.>

Learning control algorithms rely on offline estimates of generalized position, velocity, and acceleration errors. This problem is addressed in the framework of the spectral analysis of singular descriptor systems, and a class of robust estimates is introduced. The use of these estimators in the implementation of learning control algorithms has been tested on a prototype manipulator, and experimental results are reported. It is concluded that iterative learning control can be successfully implemented on real manipulators provided that robust estimators for velocity and acceleration are given.>