Humanoid Robotics

Socially perceptive robots: Challenges and concerns

by Christopher Edward Peters

Castellano, G., and Peters, C.
Commentary on the article: Sharkey, N., and Sharkey, A. "The crying shame of robot nannies: an ethical appraisal", Interaction Studies, John Benjamins Publishing Company, 11(2), pp. 201-207, John Benjamins Publishing Company, 2010 doi:10.1075/is.11.2.04cas

Social robots are those endowed with communication channels and abilities that take inspiration from human beings. The... more Social robots are those endowed with communication channels and abilities that take inspiration from human beings. The scope of such abilities should include those allowing a robot to understand people’s affective states and expressions, intentions, actions, and to interpret them based on contextual information. Childcare robots are an example of robots that could take advantage of the integration of these capabilities. This commentary conducts a technical appraisal of the notion of autonomous childcare robots, focusing on these social perceptive capabilities, reviewing some of the key challenges remaining to be investigated by the research community in this respect.

Linear State Feedback Controller Design for Bipedal Locomotion

by Safwan Choudhury

Graduate Course Submission

Bipedal locomotion is a highly active area of re- search within the field of humanoid robotics. Thus far, the most... more Bipedal locomotion is a highly active area of re- search within the field of humanoid robotics. Thus far, the most popular control strategy used to achieve walking in robots has been based on the Zero-Moment Point (ZMP) criterion. In order to achieve stable gait cycles for a humanoid robot, the walking control strategy must track a stable COM trajectory which keeps the ZMP location within the region of foot support. A simplified motion model for the walking robot is obtained by approximating the complex dynamics of the system as a 3D linear inverted pendulum (3D LIPM). This approximation provides a casual, linear time-invariant (LTI) system which can be controlled using linear techniques. It was determined that the state space model of the 3D LIPM is both controllable and observable. However, the system is inherently unstable due to poles in the right half plane. In order to stabilize the system, a linear state feedback system is designed. The final control strategy is implemented in simulation on a 14DOF lower body humanoid research platform which closely models the kinematic and dynamic parameters of a physical robot. It was determined that the linear control strategy utilizing state feedback was successful in keeping the ZMP within the region of foot support.

Towards expressive musical robots: a cross-modal framework for emotional gesture, voice and music

by Angelica Lim

Angelica Lim*, Tetsuya Ogata and Hiroshi G Okuno

EURASIP Journal on Audio, Speech, and Music Processing 2012, 2012:3 doi:10.1186/1687-4722-2012-3

It has been long speculated that expression of emotions from different modalities have the same underlying 'code',... more It has been long speculated that expression of emotions from different modalities have the same underlying 'code', whether it be a dance step, musical phrase, or tone of voice. This is the first attempt to implement this theory across three modalities, inspired by the polyvalence and repeatability of robotics. We propose a unifying framework to generate emotions across voice, gesture, and music, by representing emotional states as a 4-parameter tuple of speed, intensity, regularity, and extent (SIRE). Our results show that a simple 4-tuple can capture four emotions recognizable at greater than chance across gesture and voice, and at least two emotions across all three modalities. An application for multi-modal, expressive music robots is discussed.

Keywords: affective computing; gesture; entertainment robots.

Insieme ma soli di Sherry Turkle, un libro chiave sul meccanismo dell’auto inganno.

by Pietro Piro

Recensione critica a S. Turkle, Insieme ma soli. Perché ci aspettiamo sempre più dalla tecnologia e sempre meno dagli altri, Codice Edizioni, Torino 2012.

Il libro della psicologa del MIT di Boston Sherry Turkle, Insieme ma soli. Perché ci aspettiamo sempre più dalla... more Il libro della psicologa del MIT di Boston Sherry Turkle, Insieme ma soli. Perché ci aspettiamo sempre più dalla tecnologia e sempre meno dagli altri, ha il merito di riuscire a far luce sull’intimità del rapporto uomo-robot. Tuttavia, ci troviamo di fronte ad un libro drammatico. In cosa consiste questo dramma? L’uomo che vive nelle società del cosiddetto benessere avanzato si trova di fronte ad un bivio: o cambiare la propria realtà oppure, costruirsene un’artificiale dove vivere assecondando i propri desideri, perlopiù inconsci. L’autrice ci dimostra, senza troppi moralismi, che proprio dove l’organizzazione del lavoro assorbe maggiori energie, le persone sono spinte potentemente verso un mondo virtuale dove realizzare i propri bisogni più intimi. Analizzando questo libro nella sua portata più ampia, mi pare che faccia da calco al reale e non da carta, e che non sia stato scritto per indicarci la via d’uscita per una realtà (che appare, per chi ha ancora occhi collegati a un cuore umano, di una tristezza disarmante) quanto piuttosto, per avvertirci dell’eventualità di una futura espropriazione da parte della logica dei robot e preparare il terreno per nuove e imprevedibili relazioni di dominio.

Evaluation of Machine Learning Methods on a Swinging Humanoid

by Jessica Meyer

Not published

We show that, given a specific task, a variety of machine learning algorithms can be applied. The approaches are... more We show that, given a specific task, a variety of machine learning algorithms can be applied. The approaches are evaluated in terms of performance in a simulated environment and applicability to a real-world task. We argue that no approach performs optimally in all aspects considered.

Design and development of five-fingered hands for a humanoid emotion expression robot

by Maria Chiara Carrozza

International Journal of Humanoid Robotics (IJHR) 2007

Among social infrastructure technologies, Robot Technology (RT) is expected to play an important role in solving the... more Among social infrastructure technologies, Robot Technology (RT) is expected to play an important role in solving the problems of the aging society. New generations of personal robots are expected to be capable of assisting humans in a variety of contexts and thus of interacting and communicating with them effectively and even in a friendly and natural way. Expressing human-like emotions is an important capability to this aim. The objectives of this work are the design and development of two five-fingered robotic hands for a humanoid upper body able to generate and express emotions. The specific design goals have been grasping and expression of emotions through hand gestures, as a complement to facial expression of emotions. The paper presents the design process of the robotic hands, named RCH-1 (Robocasa Hand No. 1), starting from the requirements deriving from their use in grasping and gestures. The resulting robotic hands are described in detail, together with the hand sensory systems. Experimental trials are then presented, aimed at assessing the hand performance and at validating their effectiveness in grasping and emotion expression, when mounted on the emotion expression humanoid robot WE-4R (Waseda Eye No. 4 Refined).

iros2011ws

by Claire Dune

A sensorless torque control for Antagonistic Driven Compliant Joints

by Maria Chiara Carrozza

Mechatronics - 20 : 355:367 (2010)

Antagonistic Driven Compliant Joints (ADCJs) are object of great interest in current robotics research, rep- resenting... more Antagonistic Driven Compliant Joints (ADCJs) are object of great interest in current robotics research, rep- resenting one of the most widely applied solutions to develop human-like and safe joints for human- robot interaction. Providing the joint with ‘‘actively” adjustable hardware compliance, ADCJs have two distinctive features: (1) the joint is powered by two independent ‘‘actuation units” and (2) each actuation unit works as a non-linear elastic element with an adjustable resting position. This paper proposes a sens- orless torque control strategy suitable for ADCJs actuated robots. This method is based on two steps: (1) off-line characterization of the elasticity of the actuation units, defined by the force–elongation curve and (2) online estimation of the force exerted by each actuation unit, through a direct measure of the joint angle, and of the ‘‘resting position” of each actuation unit. The proposed force estimation method can be used to develop two independent force controllers, which can be then combined to regulate the result- ing joint torque, with no need of additional torque sensors. The performance of the proposed torque con- trol was evaluated over the shoulder and the elbow ADCJs of the 2-link 2-DOFs planar robotic arm NEURARM. The method proved to work effectively, achieving good performances on the test platform, and represents a suitable alternative to state-of-the-art sensor-based torque controls.

Design and Development of a Novel Robotic Platform for Neuro-Robotics Applications: the NEURobotics ARM (NEURARM)

by Maria Chiara Carrozza

Advanced Robotics 22 (2008) 3–37

This paper presents the NEURARM, a novel robotic platform specifically designed for performing joint experiments... more This paper presents the NEURARM, a novel robotic platform specifically designed for performing joint experiments between neuroscience and robotics. The NEURARM replicates the main functions and char- acteristics of the human arm during the execution of planar movements for reaching and catching a moving object. The NEURARM is a 2-d.o.f. planar robotic platform actuated by means of four linear hydraulic actuators and four cables integrated in agonist–antagonist configuration. The first version of a non-linear spring that will be integrated in series with the actuator has been developed and tested. The main compo- nents of the sensory system are four tension sensors on the cables, two angle sensors in the joints, and linear potentiometers and pressure sensors on the pistons. The paper presents the design methodology, the devel- oped components and system, and the experimental characterization of the NEURARM. The available data demonstrate qualitatively that the design is appropriate, that the NEURARM is able to replicate the required maximum kinematics performance and that real joint experiments with neuroscientists can start.
 Koninklijke Brill NV, Leiden and The Robotics Society of Japan, 2008

Description, Characterization and Assessment of a BioInspired Shoulder Joint-First Link Robot for NeuroRobotic Applications

by Maria Chiara Carrozza

Biomedical Robotics and Biomechatronics, 2006. BioRob 2006. The First IEEE/RAS-EMBS International Conference on

The development of innovative exoskeletons for the upper limb requires a strong collaboration between robotics and... more The development of innovative exoskeletons for the upper limb requires a strong collaboration between robotics and neuroscience. The robotic system will be deeply coupled to the human user and the exoskeleton design should be based on the human model in terms of biomechanics, and control and learning strategies. This paper presents the preliminary results of the design process of the Neurobotics exoskeleton (NEUROexos). A bioinspired three joints-three links robotic arm is under development for implementing bioinspired control strategies and for obtaining a human-like robotic arm to be used for assessing active exoskeletons in fully safe conditions. In particular, this paper presents the shoulder joint-first link prototype, the selected actuation system, the actuator modelling and identification, and the experimental evaluation of the prototype capability to replicate the human shoulder kinematics during the execution of a catching task

On the realization of a novel anthropomorphic hand for humanoid robotics: RoboCasa Hand#

by Maria Chiara Carrozza

Opinions and attitudes toward humanoid robots in the Middle East

by Nikolaos Mavridis

Co-authored with: Nikolaos Mavridis, Marina-Selini Katsaiti, Silvia Naef, Abdullah Falasi, Abdulrahman Nuaimi, Hamdan Araifi & Ahmed Kitbi, published in Springer Journal "AI & Society", http://www.springerlink.com/content/c16684w802318xx8/

Robotics is expected to boom in the near future, moving massively beyond traditional application areas, and extending... more Robotics is expected to boom in the near future, moving massively beyond traditional application areas, and extending to all parts of the globe. Thus, in order to enable effective international customization of robot designs, and in order to facilitate their smoother harmonious introduction to everyday life, it is important to study the opinions and attitudes toward robots in different regions of the world. Although there exists a small body of research covering the US, EU, and Asia, there is almost no research regarding attitudes toward robots in the Middle East, a region with its own marked cultural idiosyncrasies. Therefore, we brought Ibn Sina, an Arabic-language conversational android robot to Dubai’s Gitex, one of the most important exhibitions in the region, and performed a questionnaire-based empirical study with 355 subjects from 38 countries, which had seen the robot interacting, and most of which had also interacted directly with it. Many interesting findings are presented: First, a statistically significant ordering of preferred application areas for robots overall was found, as well as strong effects of the region of origin on the preferred applications. Furthermore, strong religion, age, and education effects were observed. Overall, the results together with a theoretical discussion of possible causes provide interesting insights on cultural acceptance of robots in this richly complex region, which potentially have strong implications to their wider deployment in the future in specific settings.

Humanoid Robot Whole Body Motion Generation Using Human Gait

by Saeid Mokaram

Saeid Mokaram; Khairulmizam S.; Abd.Rahman Ramli; , "Humanoid Robot Whole Body Motion Generation Using Human Gait" IEEE GOLD Affinity Colloquium - 6th May 2010

Using parallel architectures for humanoid robots

by Giuseppe Carbone

Identification of humanoid robots dynamics using floating-base motion dynamics

by Gentiane Venture

The IbnSina Center: An augmented reality theater with intelligent robotic and virtual characters

by Nikolaos Mavridis

Co-authored with: N. Mavridis, D. Hanson., published in Proccedings of IEEE "Robot and Human Interactive Communication, 2009. RO-MAN 2009. The 18th IEEE International Symposium on", http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=5326148

Although numerous early attempts towards the use of robotics in conjunction with virtual characters in order to create... more Although numerous early attempts towards the use of robotics in conjunction with virtual characters in order to create augmented reality theater and interactive performances have taken place, the state of the art is still in an initial stage on the pathway towards the full exploitation of the technological as well as creative and artistic potentialities that exist. Here we will present the IbnSina Center, a novel augmented reality interactive theatre installation, named after the famous polymath of the 10th century, known as Avicenna in the West. The installation consists of a ten-meter stage, multiple stage sensors, a screen, a pseudo-3D holograph transparency, and a seating area for the audience. The stage is populated by a custom-designed humanlike humanoid robot (the ldquoIbnSinardquo robot) and by humans and other entities. The screen and the holograph can display static and moving images, virtual environments as well as online virtual worlds populated by characters, or a windowed / blended mix of the above. The robotic and virtual characters can be autonomous, partially-autonomous, puppetteered, scripted, or real-time-controlled by imitation of human body movements (embodied telepresence). Furthermore, multiple modes of participation of distant humans can be supported: not only through videoconference, but also through control of robots and/or virtual characters. The IbnSina center serves as a platform for multiple purposes: artistic, research as well as educational; and most importantly, the centrality of a progressive character such as IbnSina catalyzes the reconnection of the wider region of the UAE to a past during which scientific inquiry and the arts had flourished; and thus, enables the creation of a future for the region which will emphasize such cultural values.

Transforming IbnSina into an Advanced Multilingual Interactive Android Robot

by Nikolaos Mavridis

Co-authored with: Mavridis, N. AlDhaheri, A. AlDhaheri, L. Khanii, M. AlDarmaki, N., published in IEEE "Proceedings of the 2011 GCC Conference", http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=5752467

IbnSina is the world's first Arabic-language conversational android robot, and is also part of an interactive theatre... more IbnSina is the world's first Arabic-language conversational android robot, and is also part of an interactive theatre with multiple possibilities for human teleparticipation. In this paper, we describe extensions carried out to IbnSina's software architecture in order to enrich its capabilities in multiple ways, so that it can become an exciting educational / persuasive robot in the future. The main axis for extension were: access to online (Wikipedia) and stored (Koran database) content for dialogue generation, basic multilingual capability exploration (English and Arabic, also utilizing Google Translate), basic read-aloud-text capability (through OCR), and systematization of motor control (with higher-level API for real-time lip syncing, eye blinking, natural looking random face movements, and interpolation between facial expressions including an affective state subsystem). With such capabilities, IbnSina becomes closer to an attractive robot that can find real-world application in malls, schools, as a receptionist etc.

The IbnSina interactive theater: Where humans, robots and virtual characters meet

by Nikolaos Mavridis

Co-authored with: Mavridis, N. and Hanson, D., published in Proceedings of the IEEE "Robot and Human Interactive Communication, 2009. RO-MAN 2009. The 18th IEEE International Symposium on", http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=5326144

Although numerous early attempts towards the use of robotics in conjunction with virtual characters in order to create... more Although numerous early attempts towards the use of robotics in conjunction with virtual characters in order to create augmented reality theater and interactive performances have taken place, the state of the art is still in an initial stage on the pathway towards the full exploitation of the technological as well as creative and artistic potentialities that exist. Here we will present the IbnSina center, a novel augmented reality interactive theatre installation, named after the famous polymath of the 10th century, known as Avicenna in the west. The installation consists of a ten-meter stage, multiple stage sensors, a screen, a pseudo-3D holograph transparency, and a seating area for the audience. The stage is populated by a custom-designed humanlike humanoid robot (the ldquoIbnSinardquo robot) and by humans and other entities. The screen and the holograph can display static and moving images, virtual environments as well as online virtual worlds populated by characters, or a windowed/blended mix of the above. The robotic and virtual characters can be autonomous, partially-autonomous, puppetteered, scripted, or real-time-controlled by imitation of human body movements (embodied telepresence). Furthermore, multiple modes of participation of distant humans can be supported: not only through videoconference, but also through control of robots and/or virtual characters. The IbnSina center serves as a platform for multiple purposes: artistic, research as well as educational; and most importantly, the centrality of a progressive character such as IbnSina catalyzes the reconnection of the wider region of the UAE to a past during which scientific inquiry and the arts had flourished; and thus, enables the creation of a future for the region which will emphasize such cultural values.

Android tele-operation through Brain-Computer Interfacing: A real-world demo with non-expert users

by Nikolaos Mavridis

Co-authored with: Christoforou, C. Machado, E.L., Spanoudis, G., published in Proceedings of the International Symposium on Robotics and Intelligent Sensors, Nagoya, IRIS 2010, program available at:
http://ns1.ohka.cs.is.nagoya-u.ac.jp/~iris_admin/IRIS2010_files/IRIS2010%20Detailed%20Program.pdf

Towards our vision of natural robotic tele-presence by thought, a real-world system which was demonstrated in public... more Towards our vision of natural robotic tele-presence by thought, a real-world system which was demonstrated in public with non-expert users is presented. The system consists of an EEG-based brain computer interface module (BCI), located in Cyprus, and relying on machine learning methods for recognizing brain patterns and translating them into control commands. The BCI module is controlling Ibn Sina, an android robot which is located 1400 miles away in the United Arab Emirates, in real-time, through an IP connection. Visual feedback from the robot is provided through a video link to the users. Previously untrained human users operated the system in multiple occasions (during public demos). We describe the demonstrations, as well as the structure of our system, and report quantitative measures of our system’s performance. This is up to our knowledge the first time that non-expert humans have controlled a remote android through thought during a public demonstration.

Steps towards Affordable Android Telepresence

by Nikolaos Mavridis

Co-authored with: N. Mavridis, A. Tsamakos et al., Published In Proceedings of the IEEE Human-Robot Interaction HRI2011 Conference Social Robotic Telepresence Workshop, http://www.aass.oru.se/~ali/hri2011ws/schedule.html

An important motivation for achieving effective embodied robotic telepresence comes not only from application areas... more An important motivation for achieving effective embodied robotic telepresence comes not only from application areas where the robot will be teleoperated all of the time, but also, as we shall argue, in cases where the current state of the art of autonomous AI can cater for a significant percentage of the operating time of the robot, but is not yet good enough to support the application alone. The main motivation for the system presented here comes from such cases where adjustable and sliding autonomy can be applied, and more specifically towards applications of androids in shopping malls, as receptionists, tutor robots etc. In the system presented in this paper, the arms, neck, facial expressions, eyes, lips and voice of the Ibn Sina android robot are controlled on the basis of the body movements and voice of a remote operator, while the operator is experiencing the world through the eyes and ears of the robot, fed to a head-mounted display and headphones. The system is the first android telepresence system using very-low cost operator interface equipment (kinect and webcam) while supporting arm, neck, and expression control. We present a set of generic requirements, followed by an extensive description of our system architecture, video demonstrations of actual operation, a discussion, and multiple interesting extensions.