Updated on 2022/05/26

写真a

 
SCHMITZ, Alexander
 
Affiliation
Faculty of Science and Engineering, Graduate School of Creative Science and Engineering
Job title
Associate Professor(without tenure)

Research Institute

  • 2020
    -
    2022

    理工学術院総合研究所   兼任研究員

Degree

  • Ph.D

Research Experience

  • 2017.04
    -
    Now

    Waseda University   Sugano Lab   Associate Professor

  • 2014.01
    -
    2017.03

    Waseda University   Sugano Lab   Assistant Professor

  • 2011.10
    -
    2013.12

    Waseda University   Sugano Lab (TWENDY-ONE team)   Postdoc (JSPS funded)

  • 2007.01
    -
    2011.04

    Italian Institute of Technology (IIT)   iCub team   PhD Student

  • 2000.04
    -
    2006.12

    TQS EDV-Software GesmbH   Workflow Systems   Software developer

 

Research Areas

  • Robotics and intelligent system

Papers

  • Variable In-Hand Manipulations for Tactile-Driven Robot Hand via CNN-LSTM.

    Satoshi Funabashi, Shun Ogasa, Tomoki Isobe, Tetsuya Ogata, Alexander Schmitz, Tito Pradhono Tomo, Shigeki Sugano

        9472 - 9479  2020

    DOI

  • Stable In-Grasp Manipulation with a Low-Cost Robot Hand by Using 3-Axis Tactile Sensors with a CNN.

    Satoshi Funabashi, Tomoki Isobe, Shun Ogasa, Tetsuya Ogata, Alexander Schmitz, Tito Pradhono Tomo, Shigeki Sugano

        9166 - 9173  2020

    DOI

  • Morphology-Specific Convolutional Neural Networks for Tactile Object Recognition with a Multi-Fingered Hand.

    Satoshi Funabashi, Gang Yan, Andreas Geier, Alexander Schmitz, Tetsuya Ogata, Shigeki Sugano

        57 - 63  2019  [Refereed]

    DOI

  • Morphology-Specific Stepwise Learning of In-Hand Manipulation with a Four-Fingered Hand

    Satoshi Funabashi, Alexander Schmitz, Shun Ogasa, Shigeki Sugano

    IEEE Transactions on Industrial Informatics    2019.01  [Refereed]

    DOI

  • An Adjustable Force Sensitive Sensor with an Electromagnet for a Soft, Distributed, Digital 3-Axis Skin Sensor

    Holgado, A.C, Alvarez Lopez, J.A, Schmitz, A, Tomo, T.P, Somlor, S, Jamone, L, Sugano, S

    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018)    2018

  • Object Recognition Through Active Sensing Using a Multi-Fingered Robot Hand with 3D Tactile Sensors

    Funabashi, S, Morikuni, S, Geier, A, Schmitz, A, Ogasa, S, Tomo, T.P, Somlor, S, Sugano. S

    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018)    2018

  • Large Range Impedance Shaping for Physical Human Robot Interaction Through Light Quantity Measurement Based Torque Regulation

    Wang, W, Wei, C, Suga, Y, Kuo, C, Schmitz, A, Sugano, S

    IEEE Robotics and Automation Letters   3 ( 1 ) 187 - 194  2018

    DOI

  • Evaluation of Series Clutch Actuators With a High Torque-to-Weight Ratio for Open-Loop Torque Control and Collision Safety

    Wang, Y, Schmitz, A, Kobayashi, K, Alvarez Lopez, J.A, Matsuo, Y, Sakamoto, Y, Sugano, S

    IEEE Robotics and Automation Letters (RA-L)   3 ( 1 ) 297 - 304  2018

    DOI

  • Covering a Robot Fingertip With uSkin: A Soft Electronic Skin With Distributed 3-Axis Force Sensitive Elements for Robot Hands

    Tomo, T.P, Schmitz, A, Wong, W.K, Kristanto, H, Somlor, S, Hwang, J, Jamone, L, Sugano, S

    IEEE Robotics and Automation Letters (RA-L)   3 ( 1 ) 124 - 131  2018

    DOI

  • A New Silicone Structure for uSkin - a Soft, Distributed, Digital 3-axis Skin Sensor - and its Integration on the Humanoid Robot iCub

    Tomo, T.P, Regoli, M, Schmitz, A, Natale, L, Kristanto, H, Somlor, S, Metta, G, Sugano, S

    IEEE Robotics and Automation Letters (RA-L)   3 ( 3 ) 2584 - 2591  2018

    DOI

  • A Wearable Three-Axis Tactile Sensor for Human Fingertips

    Kristanto, H, Sathe, P, Schmitz, A, Tomo, T. P, Somlor, S, Sugano, S

    IEEE Robotics and Automation Letters (RA-L)   3 ( 4 ) 4313 - 4320  2018

    DOI

  • Development of a capacitive-type 6-axis force-torque sensor

    S. Somlor, A. Schmitz, H. Jinsun, T. P. Tomo, S. Sugano

    Proceedings of IEEE Sensors   2017-   1 - 3  2017.12

     View Summary

    Force sensing is a crucial task for robots, especially when end effectors such as fingers and hands need to interact with unknown environments
    to sense such forces, a force-torque (F/T) sensor is an essential component. In this paper, we propose a small-sized 6-axis F/T sensor with a novel arrangement of 12 transducers using the force transducer we have previously developed. The copper beryllium used in our sensor reduces hysteresis in each transducer. Additionally, the sensor provides digital output via I2C bus to reduce the susceptibility to noise, and reduce the number of required wires. Sensor characteristics such as its sensitivity, signal-to-noise ratio, linearity, and hysteresis are determined. More importantly, we showed that our sensor can detect and measure the 6-axis F/T.

    DOI

  • Exploiting the slip behavior of friction based clutches for safer adjustable torque limiters

    Yushi Wang, Alexander Schmitz, Kento Kobayashi, Javier Alejandro Alvarez Lopez, Wei Wang, Yuki Matsuo, Yoshihiro Sakamoto, Shigeki Sugano

    IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM     1346 - 1351  2017.08

     View Summary

    Torque limiters are a proven way to enhance the safety in robots. To further increase the safety, adjustable torque limits depending on the task and the joint configuration (joint angles, velocity, acceleration) would be preferable. Friction clutches can be used as adjustable torque limiters (ATL). In contact free motion the ATL can be set with torque limits higher than the required torque, thereby not influencing the position tracking performance. At an impact, the torque is intrinsically limited, enhancing the safety. Furthermore, depending on the implementation, friction clutches have another relevant property. They can have different torque limits for static and kinetic friction: When the static torque limit is exceeded (as it would be the case in an incidental contact situation), the clutch starts slipping, and the torque output automatically decreases, thereby reducing the forces in a quasi-static contact, as defined in ISO/TS 15066:2016. The current paper implements and profiles an ATL, which exhibits a kinetic torque limit of only 50.4% of the static torque limit at 10rpm. This ensures both an adjustable torque limit fitting to the task requirement and a lower but not zero torque after impact for enhanced safety. Impact experiments validate the safety benefits outlined above.

    DOI

  • Low-cost 3-axis soft tactile sensors for the human-friendly robot Vizzy

    Tiago Paulino, Pedro Ribeiro, Miguel Neto, Susana Cardoso, Alexander Schmitz, Jose Santos-Victor, Alexandre Bernardino, Lorenzo Jamone

    Proceedings - IEEE International Conference on Robotics and Automation     966 - 971  2017.07

     View Summary

    In this paper we present a low-cost and easy to fabricate 3-axis tactile sensor based on magnetic technology. The sensor consists in a small magnet immersed in a silicone body with an Hall-effect sensor placed below to detect changes in the magnetic field caused by displacements of the magnet, generated by an external force applied to the silicone body. The use of a 3-axis Hall-effect sensor allows to detect the three components of the force vector, and the proposed design assures high sensitivity, low hysteresis and good repeatability of the measurement: notably, the minimum sensed force is about 0.007N. All components are cheap and easy to retrieve and to assemble
    the fabrication process is described in detail and it can be easily replicated by other researchers. Sensors with different geometries have been fabricated, calibrated and successfully integrated in the hand of the human-friendly robot Vizzy. In addition to the sensor characterization and validation, real world experiments of object manipulation are reported, showing proper detection of both normal and shear forces.

    DOI

  • Bioinspired Ciliary Force Sensor for Robotic Platforms

    Pedro Ribeiro, Mohammed Asadullah Khan, Ahmed Alfadhel, J�rgen Kosel, Fernando Franco, Susana Cardoso, Alexandre Bernardino, Alexander Schmitz, Jos� Santos-Victor, Lorenzo Jamone

    IEEE Robotics and Automation Letters   2 ( 2 ) 971 - 976  2017.04

     View Summary

    The detection of small forces is of great interest in any robotic application that involves interaction with the environment (e.g., objects manipulation, physical human-robot interaction, minimally invasive surgery), since it allows the robot to detect the contacts early on and to act accordingly. In this letter, we present a sensor design inspired by the ciliary structure frequently found in nature, consisting of an array of permanently magnetized cylinders (cilia) patterned over a giant magnetoresistance sensor (GMR). When these cylinders are deformed in shape due to applied forces, the stray magnetic field variation will change the GMR sensor resistivity, thus enabling the electrical measurement of the applied force. In this letter, we present two 3 mm � 3 mm prototypes composed of an array of five cilia with 1 mm of height and 120 and 200 μm of diameter for each prototype. A minimum force of 333 μ N was measured. A simulation model for determining the magnetized cylinders average stray magnetic field is also presented.

    DOI

  • Wayang robot with gamelan music pattern recognition

    Tito Pradhono Tomo, Alexander Schmitz, Guillermo Enriquez, Shuji Hashimoto, Shigeki Sugano

    Journal of Robotics and Mechatronics   29 ( 1 ) 137 - 145  2017.02

     View Summary

    This paper proposes a way to protect endangered wayang puppet theater, an intangible cultural heritage from Indonesia, by turning a robot into a puppeteer successor. We developed a seven degrees-offreedom (DOF) manipulator to actuate the sticks attached to the wayang puppet body and hands. The robot can imitate 8 distinct human puppeteer’smanipulations. Furthermore, we developed a gamelan music pattern recognition, towards a robot that can perform based on the gamelan music. In the offline experiment, we extracted energy (time domain), spectral rolloff, 13 Mel-frequency cepstral coefficients (MFCCs), and the harmonic ratio from 5 s long clips, every 0.025 s, with a window length of 1 s, for a total of 2576 features. Two classifiers (3 layers feed-forward neural network (FNN) and multi-class Support Vector Machine (SVM)) were compared. The SVMclassifier outperformed the FNN classifier with a recognition rate of 96.4%for identifying the three different gamelan music patterns.

    DOI

  • A Wearable Sensor for Fingertips That Can Measure 3-Axis Force

    KRISTANTO Harris, TOMO Tito Pradhono, SCHMITZ Alexander, WEI Chang, HUANG Yifan, KUO Chia Hao, SUGANO Shigeki

    The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)   2017   1A1 - O03  2017

     View Summary

    <p>This paper proposes a wearable device mounted on a human fingertip which measures the 3-axis force on the fingertip (both normal and shear forces) exerted while grasping or touching. The device consists of two Hall-Effect sensors attached on both sides of the fingertip to measure the finger pad deformation caused by external forces on the palmar side of the finger. The experiments in this paper proved that the device can measure both normal force and shear force. The recorded forces could be used for example to record the forces that human exert while manipulating objects.</p>

    DOI CiNii

  • Development of a Small-sized Capacitive 6-axis Force/Torque Sensor with a New Arrangement

    HWANG Jinsun, SOMLOR Sophon, SCHMITZ Alexander, TOMO Tito Pradhono, SUGANO Shigeki

    The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)   2017   1A1 - N03  2017

     View Summary

    <p>Force sensing is a crucial task for robots, especially when the end effectors such as fingers and hands need to interact with an unknown environment. In order to sense such forces, a force/torque sensor is an essential component. Many available force/torque sensors are based on strain gauges, but other sensing principles are also possible. Capacitive sensors have the advantage of the availability of small sized chips for sensor readout and digitization. Therefore, in this paper, we propose a small-sized 6-axis force-torque sensor using a novel arrangement of 12 unit of the transducers based on the capacitive force transducer we have previously developed. The copper beryllium used in our sensor acts as a capacitive transducer. The transducer has a hard limit which makes the sensor robust to overload. Additionally, this sensor provides digital output via I2C bus to reduce the susceptibility to noise, and reduce the number of required wires.</p>

    DOI CiNii

  • Design & Implementation of an Emergency Stop Function for On-Power Clutch Based Adjustable Torque Limiters

    Wang, Y, Schmitz, A, Alvarez Lopez, J.A, Kobayashi, K, Sugano, S

    IEEE/SICE International Symposium on System Integration (SII 2017)    2017

    DOI

  • Non-verbal Cues and Expressiveness; Motion Planning and Navigation in Human-Centered Environments

    Moondeep Shrestha, Ayano Kobayashi, Tomoya Onishi, Hayato Yanagawa, Yuta Yokoyama, Erika Uno, Alexander Schmitz, Mitsuhiro Kamezaki, Shigeki Sugano

    Proceedings of 2016 IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN2016)    2016.08  [Refereed]

  • Communicating Directional Intent in Robot Navigation using Projection and Display Indicators

    Moondeep Shrestha, Ayano Kobayashi, Tomoya Onishi, Hayato Yanagawa, Yuta Yokoyama, Erika Uno, Alexander Schmitz, Mitsuhiro Kamezaki, Shigeki Sugano

    Proceedings of 2016 IEEE International Symposium on Robot and Human Interactive Communication, (RO-MAN2016)     415 - 416  2016.08  [Refereed]

  • Design and Characterization of a Three-Axis Hall Effect-Based Soft Skin Sensor

    Tito Pradhono Tomo, Sophon Somlor, Alexander Schmitz, Lorenzo Jamone, Weijie Huang, Harris Kristanto, Shigeki Sugano

    SENSORS   16 ( 4 )  2016.04  [Refereed]

     View Summary

    This paper presents an easy means to produce a 3-axis Hall effect-based skin sensor for robotic applications. It uses an off-the-shelf chip and is physically small and provides digital output. Furthermore, the sensor has a soft exterior for safe interactions with the environment; in particular it uses soft silicone with about an 8 mm thickness. Tests were performed to evaluate the drift due to temperature changes, and a compensation using the integral temperature sensor was implemented. Furthermore, the hysteresis and the crosstalk between the 3-axis measurements were evaluated. The sensor is able to detect minimal forces of about 1 gf. The sensor was calibrated and results with total forces up to 1450 gf in the normal and tangential directions of the sensor are presented. The test revealed that the sensor is able to measure the different components of the force vector.

    DOI

  • Improving IMES Localization Accuracy by Integrating Dead Reckoning Information

    Kenjiro Fujii, Hiroaki Arie, Wei Wang, Yuto Kaneko, Yoshihiro Sakamoto, Alexander Schmitz, Shigeki Sugano

    SENSORS   16 ( 2 )  2016.02  [Refereed]

     View Summary

    Indoor positioning remains an open problem, because it is difficult to achieve satisfactory accuracy within an indoor environment using current radio-based localization technology. In this study, we investigate the use of Indoor Messaging System (IMES) radio for high-accuracy indoor positioning. A hybrid positioning method combining IMES radio strength information and pedestrian dead reckoning information is proposed in order to improve IMES localization accuracy. For understanding the carrier noise ratio versus distance relation for IMES radio, the signal propagation of IMES radio is modeled and identified. Then, trilateration and extended Kalman filtering methods using the radio propagation model are developed for position estimation. These methods are evaluated through robot localization and pedestrian localization experiments. The experimental results show that the proposed hybrid positioning method achieved average estimation errors of 217 and 1846 mm in robot localization and pedestrian localization, respectively. In addition, in order to examine the reason for the positioning accuracy of pedestrian localization being much lower than that of robot localization, the influence of the human body on the radio propagation is experimentally evaluated. The result suggests that the influence of the human body can be modeled.

    DOI

  • Intent Communication in Navigation through the Use of Light and Screen Indicators

    Moondeep C. Shrestha, Ayano Kobayashi, Tomoya Onishi, Erika Uno, Hayato Yanagawa, Yuta Yokoyama, Mitsuhiro Kamezaki, Alexander Schmitz, Shigeki Sugano

    ELEVENTH ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN ROBOT INTERACTION (HRI'16)     523 - 524  2016  [Refereed]

     View Summary

    Human's ability to perceive intent plays a crucial role in achieving smooth and efficient navigation. At the present state, even with the state-of-the-art anthropomorphic robots, displaying human-like non-verbal communication (kinesics) is a challenging task. This poses a significant difficulty in performing legible navigation behavior for robots. In this paper, we look into light (turn indicator) and screen (arrow indicator) indicators as a means of overcoming the shortcomings of the robot's non-verbal communication abilities. Our results show a statistically significant improvement in perceived comfort, predictability, and performance with the use of light indicators.

    DOI

  • SNR Modeling and Material Dependency Test of a Low-cost and Simple to Fabricate 3D Force Sensor for Soft Robotics

    Tito Pradhono Tomo, Wai Keat Wong, Alexander Schmitz, Harris Kristanto, Sophon Somlor, Jinsun Hwang, Shigeki Sugano

    2016 IEEE/SICE INTERNATIONAL SYMPOSIUM ON SYSTEM INTEGRATION (SII)     428 - 433  2016  [Refereed]

     View Summary

    This paper presents a low cost, easy to produce, small tactile sensor system, that can be embedded in a soft material and limited space. In the current implementation, we use a Hall-effect sensor and a magnet to measure the force. One sensor module can measure 3D force vector and temperature. This chip is planted inside a 55 x 55 x 8 mm of the silicon layer. The module has I2C digital output, requiring only four wires for each module. The experiment shows that the signal to noise ratio (SNR) for this module is relatively high, 21.4658 dB when 20g load is applied. The experiment also indicates that the sensor module measured loads differently depending on the type of material that is in contact.

    DOI

  • Intent Communication in Navigation through the Use of Light and Screen Indicators

    Moondeep C. Shrestha, Ayano Kobayashi, Tomoya Onishi, Erika Uno, Hayato Yanagawa, Yuta Yokoyama, Mitsuhiro Kamezaki, Alexander Schmitz, Shigeki Sugano

    ELEVENTH ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN ROBOT INTERACTION (HRI'16)   2016-April   523 - 524  2016  [Refereed]

     View Summary

    Human's ability to perceive intent plays a crucial role in achieving smooth and efficient navigation. At the present state, even with the state-of-the-art anthropomorphic robots, displaying human-like non-verbal communication (kinesics) is a challenging task. This poses a significant difficulty in performing legible navigation behavior for robots. In this paper, we look into light (turn indicator) and screen (arrow indicator) indicators as a means of overcoming the shortcomings of the robot's non-verbal communication abilities. Our results show a statistically significant improvement in perceived comfort, predictability, and performance with the use of light indicators.

    DOI

  • Exploring the Use of Light and Display Indicators for Communicating Directional Intent

    Moondeep C. Shrestha, Ayano Kobayashi, Tomoya Onishi, Hayato Yanagawa, Yuta Yokoyama, Erika Uno, Alexander Schmitz, Mitsuhiro Kamezaki, Shigeki Sugano

    2016 IEEE INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS (AIM)   2016-September   1651 - 1656  2016  [Refereed]

     View Summary

    Legible robot behavior is a key element for smooth and efficient navigation among humans. However, at present, even the state-of-the-art robots cannot communicate its internal state of directional intent by displaying human-like non-verbal cues. In this paper, we explore various modes for communicating directional intent of a robot across three different scenarios as a means of overcoming the shortcomings of the robot's non-verbal communication abilities. Specifically, we look into turn indicators, display indicators, and their combinations with sound and investigate their effectiveness across different passing scenarios. Our study shows us that using auxiliary communicating methods significantly improves the perceived feelings of our dependent measures. Further, communicating intention also helps in improving cooperation. However, the effectiveness greatly varies with the modes and the passing scenarios. In the case of 90 degrees crossing scenario, even though participants have positive perceived feelings, this does not necessarily translate into smooth and efficient navigation.

    DOI

  • Development of Robotic Fingertip Morphology for Enhanced Manipulation Stability

    Keung Or, Alexander Schmitz, Satoshi Funabashi, Mami Tomura, Shigeki Sugano

    2016 IEEE INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS (AIM)   2016-September   25 - 30  2016  [Refereed]

     View Summary

    This study aims to develop a fingertip in order to improve the manipulation performance of posture interpolation control for a multifingered robot hand.Increasing the contact area between the fingertips and object is one solution for improving grasping and manipulation stability.A reasonable fingertip shape design and material selection can increase the contact area.In this paper, we compare an anthropomorphic shape to a cylindrical body with a semispherical tip.In order to test the practical property such as contact area size of our proposed fingertip, a pressure experiment was conducted for comparing the two fingertip shapes under different workloads. Finally, we installed the fingertips on a commercial available robot hand Allegro Hand.Two tasks were conducted for evaluating our proposed fingertip with posture interpolation control. The results show that our proposed fingertip could improve manipulation performance by comparing the success rate in both the experiments.

    DOI

  • Position-Force Combination Control with Passive Flexibility for Versatile In-Hand Manipulation Based on Posture Interpolation

    Keung Or, Mami Tomura, Alexander Schmitz, Satoshi Funabashi, Shigeki Sugano

    2016 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2016)   2016-November   2542 - 2547  2016  [Refereed]

     View Summary

    In-hand manipulation is often needed to accomplish a practical task after grasping an object. In-hand manipulation of variously sized and shaped objects in multi-fingered hands without dropping the object is challenging. In this paper we suggest a combined strategy of force control and passive adaptation through soft fingertips with simple interpolation control to achieve in-hand manipulation between various postures and with various objects. While passive compliance can be achieved in numerous ways, this paper uses soft skin, as it does not require complex mechanisms and was easy to integrate in the robot hand (Allegro hand). Softness has proven to significantly ease object grasping, and the current paper shows the importance of softness also for in-hand manipulation. In particular, the simple interpolation strategy between various postures is successful when combined with soft fingertips, with or without force control, but fails with hard fingertips. Objects of varying size, shape and hardness were reliably manipulated. While the soft fingertips enabled good results in our experiments, a sufficiently precise definition of the postures and object size was required. When combining the interpolation control with a force control strategy, bigger errors in defining the posture and object size are possible, without deforming or dropping the object, and the resultant force is lower. As a result, we achieved robust in -hand manipulation between various postures and with objects of different size, shape and hardness.

    DOI

  • Design Optimisation and Performance Evaluation of a Toroidal Magnetorheological Hydraulic Piston Head

    Gonzalo Aguirre Dominguez, Mitsuhiro Kamezaki, Shan He, Somlor Sophon, Alexander Schmitz, Shigeki Sugano

    2016 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2016)   2016-November   350 - 355  2016  [Refereed]

     View Summary

    The advantages of mechanical compliance have driven the development of devices using new smart materials. A new kind of magnetorheological piston based on a toroidal array of magnetorheological valves, has been previously tested to prove its feasibility. However, being an initial prototype its potential was still limited by its complex design, and low output force. This study presents the revisions done to the design with several improvements targeting key performance parameters. An improved annular piston design is also introduced as comparison with conventional devices. The toroidal and annular piston head prototypes are built and tested, and their force performance compared with the previous iteration. The experimental results show an overall performance improvement of the toroidal assembly. However, the force model used in the study still fails to accurately predict the magnetic flux at the gaps of the piston head. This deviation is later verify and corrected using a FEM analysis. The force performance of the new toroidal assembly is on par with the commonplace annular design. It also displays a more linear behaviour, at the expense of lower energy efficiency. Finally, it also shows potential for a greater degree of customisation to meet different system requirements.

    DOI

  • A Combined Approach of Doppler and Carrier-based Hyperbolic Positioning with a Multi-channel GPS-pseudolite for Indoor Localization of Robots

    Kenjiro Fujii, Ryosuke Yonezawa, Yoshihiro Sakamoto, Alexander Schmitz, Shigeki Sugano

    2016 INTERNATIONAL CONFERENCE ON INDOOR POSITIONING AND INDOOR NAVIGATION (IPIN)    2016  [Refereed]

     View Summary

    A combined method of Doppler positioning and carrier-based hyperbolic positioning with a multi-channel GPS-pseudolite is proposed for indoor localization. This method uses carrier-phase output from a GPS/pseudolite receiver. The carrier-phase observable is precise but does not provide range information between the pseudolite and receiver antennas necessary for position calculation. This is because of the existence of carrier ambiguity. This problem can be solved by using the proposed combined method. In the present work, the positioning theory is established and experimentally evaluated with actual devices including a robot. The experimental result shows that a positioning accuracy of more than 10 cm is achievable.

    DOI

  • A Modular, Distributed, Soft, 3-Axis Sensor System for Robot Hands

    Tito Pradhono Tomo, Wai Keat Wong, Alexander Schmitz, Harris Kristanto, Alexandre Sarazin, Lorenzo Jamone, Sophon Somlor, Shigeki Sugano

    2016 IEEE-RAS 16TH INTERNATIONAL CONFERENCE ON HUMANOID ROBOTS (HUMANOIDS)     454 - 460  2016  [Refereed]

     View Summary

    Integrating distributed sensors in the skin of robot hands is challenging, as the space is limited. This paper presents a dense and small tactile sensor system that can be installed on robotic hands. In the current implementation, the system is constituted by modules that are 26mm long and 27mm wide and they have been successfully integrated on the internal side of each finger phalange of the commercially available Allegro Hand (except the fingertips). Each sensor module contains 16 tri-axial taxels; each taxel is able to measure the applied 3D force vector using a Hall effect sensor and a magnet. The sensor modules are 4mm high, including the printed circuit board (PCB) with the sensors and the soft silicone with the magnets. The back of the PCB is flat without any components mounted, which eases the integration. Each sensor has I2C digital output, and each sensor module is connected to four I2C buses, requiring only seven wires for each module. The tri-axial taxels are close to each other (4.7 mm from the center of one taxel to the next), but experiments proved that independent force vectors can be measured and that the crosstalk is limited.

    DOI

  • A Study on Fingertip Designs and their Influences on Performing Stable Prehension for Robot Hands

    Keung Or, Shu Morikuni, Shun Ogasa, Satoshi Funabashi, Alexander Schmitz, Shigeki Sugano

    2016 IEEE-RAS 16TH INTERNATIONAL CONFERENCE ON HUMANOID ROBOTS (HUMANOIDS)     772 - 777  2016  [Refereed]

     View Summary

    This research aims to clarify and analyze potential factors in fingertip designs and conditions which may affect prehension performances in addition to the control strategy. In this paper, four factors of fingertip designs and conditions are considered: hardness, thickness of the skin, shape and the surface friction condition of the fingertip. Six fingertips were made in order to compare these factors and their influences on grasp stability under different conditions (high and low workload). An evaluation experiment was conducted in order to investigate how the proposed properties affect the grasping performance under different workloads. Results show an unexpected effectiveness of the soft skin grasping performance compared to less deformable materials, even with reduced friction; also the orientation of the fingertips significantly affects the grasping performance in the case of anthropomorphic fingertips. These results can be useful for designing a new robot hand and a control strategy, which can potentially lead to a better stability and efficient performance.

    DOI

  • Robust in-hand manipulation of variously sized and shaped objects

    Satoshi Funabashi, Alexander Schmitz, Takashi Sato, Sophon Somlor, Shigeki Sugano

    IEEE International Conference on Intelligent Robots and Systems   2015-   257 - 263  2015.12

     View Summary

    Moving objects within the hand is challenging, especially if the objects are of various shape and size. In this paper we use machine learning to learn in-hand manipulation of such various sized and shaped objects. The TWENDY-ONE hand is used, which has various properties that makes it well suited for in-hand manipulation: a high number of actuated joints, passive degrees of freedom and soft skin, six-axis force/torque (F/T) sensors in each fingertip, and distributed tactile sensors in the skin. A dataglove is used to gather training samples for teaching the required behavior. The object size information is extracted from the initial grasping posture. After training a neural network, the robot is able to manipulate objects of untrained sizes and shape. The results show the importance of size and tactile information. Compared to interpolation control, the adaptability for the initial posture gap could be greatly extended. Final results show that with deep learning the number of required training sets can be drastically reduced.

    DOI

  • Feature Extraction by Deep Learning for Improved In-Hand Manipulation

    FUNABASHI Satoshi, SATO Takashi, SCHMITZ Alexander, SUGANO Shigeki

    The ... international conference on advanced mechatronics : toward evolutionary fusion of IT and mechatronics : ICAM : abstracts   2015 ( 6 ) 31 - 32  2015.12

     View Summary

    This article presents feature extraction with deep learning for in-hand manipulation. It is important that robot hands can manipulate different sized and shaped objects. In order to generate versatile manipulation with such objects, we used deep learning to extract critical information from object manipulating motions.

    CiNii

  • A novel tri-axial capacitive-type skin sensor

    Sophon Somlor, Richard Sahala Hartanto, Alexander Schmitz, Shigeki Sugano

    ADVANCED ROBOTICS   29 ( 21 ) 1375 - 1391  2015.11  [Refereed]

     View Summary

    This paper introduces a novel tri-axial capacitive force sensor. The sensor can measure the force vector, is embedded in soft 7mm-thick silicone skin, enables temperature sensitivity compensation and has digital output. To measure the force vector, tilted capacitive sensor elements are used which are facing in different directions to differentiate the tangential forces. The sensor is intended for distributed contact sensing in a robotic skin, but could be also used for other applications such as novel haptic user interfaces in wearable devices. A series of experiments was performed and showed good sensor characteristics. The concept of the tilted force transducers has been proven to have the capability of detecting the force vector acting on the local sensor surface.

    DOI

  • Hyperbolic Positioning with Antenna Arrays and Multi-Channel Pseudolite for Indoor Localization

    Kenjirou Fujii, Yoshihiro Sakamoto, Wei Wang, Hiroaki Arie, Alexander Schmitz, Shigeki Sugano

    SENSORS   15 ( 10 ) 25157 - 25175  2015.10  [Refereed]

     View Summary

    A hyperbolic positioning method with antenna arrays consisting of proximately-located antennas and a multi-channel pseudolite is proposed in order to overcome the problems of indoor positioning with conventional pseudolites (ground-based GPS transmitters). A two-dimensional positioning experiment using actual devices is conducted. The experimental result shows that the positioning accuracy varies centimeter- to meter-level according to the geometric relation between the pseudolite antennas and the receiver. It also shows that the bias error of the carrier-phase difference observables is more serious than their random error. Based on the size of the bias error of carrier-phase difference that is inverse-calculated from the experimental result, three-dimensional positioning performance is evaluated by computer simulation. In addition, in the three-dimensional positioning scenario, an initial value convergence analysis of the non-linear least squares is conducted. Its result shows that initial values that can converge to a right position exist at least under the proposed antenna setup. The simulated values and evaluation methods introduced in this work can be applied to various antenna setups; therefore, by using them, positioning performance can be predicted in advance of installing an actual system.

    DOI

  • A Haptic Interface with Adjustable Stiffness Using MR Fluid

    Sophon Somlor, Gonzalo Aguirre Dominguez, Alexander Schmitz, Mitsuhiro Kamezaki, Shigeki Sugano

    2015 IEEE/ASME INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS (AIM)     1132 - 1137  2015  [Refereed]

     View Summary

    This paper describes a combined tactile sensor and haptic interface that can change its stiffness using magnetorheological fluids (MR fluid). The tactile sensor consists of 6 distributed capacitive sensors that can sense the location and the amount of applied force. Above the sensors is a chamber filled with MR fluid. By changing the magnetic field, the hardness of the MR fluid, and thereby of the haptic interface, can be changed. Fast changes of the magnetization direction lead to a sensation of vibration. The resulting device can be used for novel haptic input devices or for robotic grippers. A prototype device has been constructed, and the effects of the varying magnetic field and the resulting varying stiffness of the MR fluid on the distributed force sensing with the capacitive sensors has been evaluated. We discovered that the measured forces vary very little with changes in the strength of the magnetic field.

    DOI

  • First Results of Tilted Capacitive Sensors to Detect Shear Force

    Sophon Somlor, Alexander Schmitz, Richard Sahala Hartanto, Shigeki Sugano

    2015 IEEE INTERNATIONAL SYMPOSIUM ON ROBOTICS AND INTELLIGENT SENSORS (IEEE IRIS2015)   76   101 - 106  2015  [Refereed]

     View Summary

    This paper proposes a new soft capacitive-type 3-axis force sensor. The prototype version which can detect a multi-axis force vector is embedded inside 7mm-thick silicone skin, and provides digital output via an I2C bus. Tilted capacitive force transducers were used to measure the force vector; the transducers faced different directions to differentiate the tangential forces. Preliminary experiments were performed and the concept of the tilted force transducers has been proven to have the capability of differentiating the force vector acting on the sensor surface. (c) 2015 The Authors. Published by Elsevier B. V.

    DOI

  • A Concept for a Robot Arm with Adjustable Series Clutch Actuators and Passive Gravity Compensation for Enhanced Safety

    Alexander Schmitz, Soumya Bhavaraju, Sophon Somlor, Gonzalo Aguirre Dominguez, Mitsuhiro Kamezaki, Wei Wang, Shigeki Sugano

    2015 IEEE/ASME INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS (AIM)   2015-August   1322 - 1327  2015  [Refereed]

     View Summary

    Passive compliance is useful for robotic arms to ensure their safety. Often springs are used, but they are problematic because they reduce the achievable accelerations and can lead to underdamped oscillations. Torque limiters enhance the safety, but usually the torque limit cannot be adjusted to a desired torque. Electronically adjustable torque limiters, also known as series clutch actuators, have several benefits, especially for robotic arms, but they also have severe limitations. This paper suggests incorporating series clutch actuators into a gravity compensated arm. Consequently, gravity should not limit the isotropically achievable force anymore and in the case of power outage the arm keeps its position. The benefits and limitations of a series clutch actuator in a gravity compensated arm are discussed, and a prototype of such an arm is presented. Commercially available magnetic friction clutches are used. Preliminary experiments demonstrate that the safety can be increased.

    DOI

  • Using Contact-based Inducement for Efficient Navigation in a Congested Environment

    Moondeep C. Shrestha, Yosuke Nohisa, Alexander Schmitz, Shouichi Hayakawa, Erika Uno, Yuta Yokoyama, Hayato Yanagawa, Keung Or, Shigeki Sugano

    2015 24TH IEEE INTERNATIONAL SYMPOSIUM ON ROBOT AND HUMAN INTERACTIVE COMMUNICATION (RO-MAN)   2015-November   456 - 461  2015  [Refereed]

     View Summary

    As robots progressively continue to enter human lives, it becomes important for robots to navigate safely and efficiently in crowded environments. In fact, efficient navigation in crowded areas is an important prerequisite for successful coexistence between humans and robots. In this paper, we explore an unconventional idea wherein a robot tries to achieve a more efficient navigation by influencing an obstructing human to move away by means of contact. First, preliminary human reaction experiments were conducted wherein we established that we can successfully induce a human to move in a desired direction. Following this result, we have proposed a novel motion planning approach which considers inducement by contact. The system is then verified through simulation and real experiments. The results show us that the proposed method can be utilized for safer and more efficient navigation in a crowded, but relatively static environment.

    DOI

  • Development of a Hall-Effect Based Skin Sensor

    Tito Pradhono Tomo, Sophon Somlor, Alexander Schmitz, Shuji Hashimoto, Shigeki Sugano, Lorenzo Jamone

    2015 IEEE SENSORS     1007 - 1010  2015  [Refereed]

     View Summary

    In this paper we introduce a prototype of a novel hall-effect based skin sensor for robotic applications. It uses a small sized chip that provides 3-axis digital output in a compact package. Our purpose was to evaluate the feasibility of measuring 3-axis force while maintain a soft exterior for safe interactions. Silicone was used to produce the soft skin layer with about 8 mm thickness. An MLX90393 chip was installed at the bottom of layer, with a small magnet approximately 5mm above it to measure 3-axial magnetic field data. To evaluate the sensor's performance, an experiment was conducted by measuring normal and shear force when applying total forces of 0.7-14N in the normal and tangential directions of the sensor. The test revealed that the sensor prototype was able to differentiate the components of the force vector, with limited crosstalk. A calibration was performed to convert the measurements of the magnetic field to force values.

    DOI

  • An Investigation into the Social Acceptance of Using Contact for Inducing an Obstructing Human

    Moondeep C. Shrestha, Ayano Kobayashi, Tomoya Onishi, Erika Uno, Hayato Yanagawa, Yuta Yokoyama, Mitsuhiro Kamezaki, Alexander Schmitz, Shigeki Sugano

    2015 IEEE-RAS 15TH INTERNATIONAL CONFERENCE ON HUMANOID ROBOTS (HUMANOIDS)   2015-December   941 - 946  2015  [Refereed]

     View Summary

    In densely populated scenarios with cramped spaces, it is very difficult to achieve safe and efficient navigation without cooperation from humans. One way in which we can seek cooperation from humans is by using contact to influence them to give way. However, such a method may incur certain psychological implications and therefore requires an acceptability check to ensure whether such action is acceptable or not. For this purpose, we investigate the participant subjective response towards robot-initiated touch during the course of navigation. We conducted a 2 (robotic experience vs. none) x 2 (warning vs. none) between-subject experiment with 44 people in which a mobile robotic platform exerted contact on an unaware and obstructing participant to make way towards its goal. Our results show that prior experience with robots produces slightly better response even though the results are not statistically significant. However, a verbal warning prior to contact yielded much more favorable response. In general, the participants did not find contact to be uncomfortable and were not opposed to robot-initiated contact if deemed necessary.

    DOI

  • Interpolation Control Posture Design for In-Hand Manipulation

    Keung Or, Mami Tomura, Alexander Schmitz, Satoshi Funabashi, Shigeki Sugano

    2015 IEEE/SICE INTERNATIONAL SYMPOSIUM ON SYSTEM INTEGRATION (SII)     187 - 192  2015  [Refereed]

     View Summary

    Object handling and manipulation are important functions of dexterous anthropomorphic hands. As it is difficult to create a manipulation model analytically for performing complex tasks as humans do, a simple way to accomplish generic in-hand manipulation is desirable for robotic hands, especially for robot hands with few sensors. In this paper, we designed standard grasping postures based on the grasping behavior of humans. Interpolation control is used to control the robot hand. The combination of these postures results in versatile object manipulation. This control strategy is evaluated by testing it with the 16 degrees of freedom Allegro Hand grasping different sizes of spheres.

    DOI

  • Methods for Improving IMES Transmitters: Transmission Diversity, Variable Beamwidth Antenna, and Leaky Coaxial Cable

    Kenjiro Fujii, Takamasa Kawaguchi, Hisanori Matsumoto, Makoto Tanikawara, Takashi Toyama, Yoshihiro Sakamoto, Wei Wang, Hiroaki Arie, Alexander Schmitz, Shigeki Sugano

    2015 IEEE/SICE INTERNATIONAL SYMPOSIUM ON SYSTEM INTEGRATION (SII)     326 - 331  2015  [Refereed]

     View Summary

    IMES is an indoor messaging and positioning system. In the present work, three methods for improving the IMES transmitter are proposed based on the result of a radio acquisition analysis: transmission diversity, a variable beamwidth antenna, and a leaky coaxial cable (LCX). The transmission diversity method increases the possibility of signal acquisition in areas with weak signal. A small-sized variable beamwidth antenna is developed to mitigate the multipath interference in narrow spaces. A field experiment with a LCX in an actual train setup is conducted to verify the effect of the LCX for the positioning of moving vehicles. The evaluation results of the proposed methods suggest their potential to be applied to practical applications.

    DOI

  • Tactile Object Recognition using Deep Learning and Dropout

    Alexander Schmitz, Yusuke Bansho, Kuniaki Noda, Hiroyasu Iwata, Tetsuya Ogata, Shigeki Sugano

    2014 14th IEEE-RAS International Conference on Humanoid Robots (Humanoids)     1044 - 1050  2014  [Refereed]

     View Summary

    Recognizing grasped objects with tactile sensors is beneficial in many situations, as other sensor information like vision is not always reliable. In this paper, we aim for multimodal object recognition by power grasping of objects with an unknown orientation and position relation to the hand. Few robots have the necessary tactile sensors to reliably recognize objects: in this study the multifingered hand of TWENDY-ONE is used, which has distributed skin sensors covering most of the hand, 6 axis F/T sensors in each fingertip, and provides information about the joint angles. Moreover, the hand is compliant. When using tactile sensors, it is not clear what kinds of features are useful for object recognition. Recently, deep learning has shown promising results. Nevertheless, deep learning has rarely been used in robotics and to our best knowledge never for tactile sensing, probably because it is difficult to gather many samples with tactile sensors. Our results show a clear improvement when using a denoising autoencoder with dropout compared to traditional neural networks. Nevertheless, a higher number of layers did not prove to be beneficial.

    DOI

  • A Prototype Force Sensing Unit for a Capacitive-type Force-Torque Sensor

    S. Somlor, A. Schmitz, R. S. Hartanto, S. Sugano

    2014 IEEE/SICE INTERNATIONAL SYMPOSIUM ON SYSTEM INTEGRATION (SII)     684 - 689  2014  [Refereed]

     View Summary

    Force sensing is a crucial task for robots, especially when the end effectors such as fingers and hands need to interact with an unknown environment, for example in a humanoid robot. In order to sense such forces, a force/torque sensor is an essential component. Many available force/torque sensors are based on strain gauges, but other sensing principles are also possible. In this paper we describe steps towards a capacitive type based sensor. Several MEMS capacitive sensors are described in the literature; however very few larger sensors are available, as capacitive sensors usually have disadvantages such as severe hysteresis and temperature sensitivity. On the other hand, capacitive sensors have the advantage of the availability of small sized chips for sensor readout and digitization. We employ copper beryllium for the transducer, which has been modified from the ones described in the literature to be able to be used in a small sized, robust force/torque sensor. Therefore, as the first step toward the goal of building such a sensor, in this study we have created a prototype sensing unit and have tested its sensitivity. No viscoelastic materials are used for the sensing unit, which usually introduce severe hysteresis in capacitive sensors. We have achieved a high signal-to-noise ratio, high sensitivity and a range of 10 Newton.

    DOI

  • Sensor Prediction and Grasp Stability Evaluation for In-Hand Manipulation

    Kohei Kojima, Takashi Sato, Alexander Schmitz, Hiroaki Arie, Hiroyasu Iwata, Shigeki Sugano

    2013 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)     2479 - 2484  2013  [Refereed]

     View Summary

    Handling objects with a single hand without dropping the object is challenging for a robot. A possible way to aid the motion planning is the prediction of the sensory results of different motions. Sequences of different movements can be performed as an offline simulation, and using the predicted sensory results, it can be evaluated whether the desired goal is achieved. In particular, the task in this paper is to roll a sphere between the fingertips of the dexterous hand of the humanoid robot TWENDY-ONE. First, a forward model for the prediction of the touch state resulting from the in-hand manipulation is developed. As it is difficult to create such a model analytically, the model is obtained through machine learning. To get real world training data, a dataglove is used to control the robot in a master-slave way. The learned model was able to accurately predict the course of the touch state while performing successful and unsuccessful in-hand manipulations. In a second step, it is shown that this simulated sequence of sensor states can be used as input for a stability assessment model. This model can accurately predict whether a grasp is stable or whether it results in dropping the object. In a final step, a more powerful grasp stability evaluator is introduced, which works for our task regardless of the sphere diameter.

    DOI

  • THE DESIGN OF THE iCub HUMANOID ROBOT

    Alberto Parmiggiani, Marco Maggiali, Lorenzo Natale, Francesco Nori, Alexander Schmitz, Nikos Tsagarakis, Jose Santos Victor, Francesco Becchi, Giulio Sandini, Giorgio Metta

    INTERNATIONAL JOURNAL OF HUMANOID ROBOTICS   9 ( 4 ) 1 - 23  2012.12  [Refereed]

     View Summary

    This article describes the hardware design of the iCub humanoid robot. The iCub is an open-source humanoid robotic platform designed explicitly to support research in embodied cognition. This paper covers the mechanical and electronic design of the first release of the robot. A series upgrades developed for the second version of the robot (iCub2), which are aimed at the improvement of the mechanical and sensing performance, are also described.

    DOI

  • Methods and Technologies for the Implementation of Large-Scale Robot Tactile Sensors

    Alexander Schmitz, Perla Maiolino, Marco Maggiali, Lorenzo Natale, Giorgio Cannata, Giorgio Metta

    IEEE TRANSACTIONS ON ROBOTICS   27 ( 3 ) 389 - 400  2011.06  [Refereed]

     View Summary

    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. Eachmodule 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.

    DOI

  • Improvement of tactile capacitive sensors of the humanoid robot iCub's fingertips

    A. Ascia, M. Biso, A. Ansaldo, A. Schmitz, D. Ricci, L. Natale, G. Metta, G. Sandini

    2011 IEEE SENSORS     504 - 507  2011  [Refereed]

     View Summary

    Humanoid robots use tactile fingertips to perform object manipulation. In this paper, an improved prototype of a tactile capacitive fingertip for the hands of the humanoid robot iCub is presented. In particular, a conductive silicone based material has been used to improve the characteristics of the capacitive sensor and an additional silicone foam layer has been also introduced in the sensor architecture to prevent behavior variation due to fingertip deterioration (e.g., caused by object manipulation). A characterization of the fingertip sensing behavior is presented. This work is funded by the European Commission as part of the project ICT-FP7-231500 RoboSKIN.

    DOI

  • A Toolbox for Supporting the Design of Large-Scale Capacitive Tactile Systems

    Thuy-Hong-Loan, L, Maiolino, P, Mastrogiovanni, F, Cannata, G, Schmitz, A

    IEEE-RAS International Conference on Humanoid Robots (Humanoids 2011), Bled, Sloveni    2011

    DOI

  • A Tactile Sensor for the Fingertips of the Humanoid Robot iCub

    Alexander Schmitz, Marco Maggiali, Lorenzo Natale, Bruno Bonino, Giorgio Metta

    IEEE/RSJ 2010 INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2010)     2212 - 2217  2010  [Refereed]

     View Summary

    In order to successfully perform object manipulation, humanoid robots must be equipped with tactile sensors. However, the limited space that is available in robotic fingers imposes severe design constraints. In [1] we presented a small prototype fingertip which incorporates a capacitive pressure system. This paper shows an improved version, which has been integrated on the hand of the humanoid robot iCub. The fingertip is 14.5 mm long and 13 mm wide. The capacitive pressure sensor system has 12 sensitive zones and includes the electronics to send the 12 measurements over a serial bus with only 4 wires. Each synthetic fingertip is shaped approximately like a human fingertip. Furthermore, an integral part of the capacitive sensor is soft silicone foam, and therefore the fingertip is compliant. We describe the structure of the fingertip, their integration on the humanoid robot iCub and present test results to show the characteristics of the sensor.

    DOI

  • Touch Sensors for Humanoid Hands

    Alexander Schmitz, Marco Maggiali, Lorenzo Natale, Giorgio Metta

    2010 IEEE RO-MAN     691 - 697  2010  [Refereed]

     View Summary

    The sense of touch is of major importance for object handling. Nevertheless, adequate cutaneous sensors for humanoid robot hands are still missing. Designing such sensors is challenging, because they should not only give reliable measurements and integrate many sensing points into little space, but they should also be compliant and should not obstruct the other functions of the robot. This paper presents a capacitive pressure sensor system with 108 sensitive zones for the hands of the humanoid robot iCub. In particular, the palm has 48 taxels and each of the five fingertips has 12 taxels. The size and the shape of the hand are similar to that of a human child. When designing the sensors, we paid special attention to the integration on the robot. Also the ease and speed of production was an important design factor. Furthermore, the sensor incorporates silicone foam and is therefore compliant. We show the working principle of the sensor, how it has been integrated into the hands, and describe experiments that have been performed to show the characteristics of the sensor.

    DOI

  • Design, Realization and Sensorization of the Dexterous iCub Hand

    Schmitz, A, Pattacini, U, Nori, F, Natale, L, Metta, G, Sandini, G

    IEEE-RAS International Conference on Humanoid Robots (Humanoids 2010), Nashville, Tennessee, USA    2010

    DOI

  • A Prototype Fingertip with High Spatial Resolution Pressure Sensing for the Robot iCub

    Alexander Schmitz, Marco Maggiali, Marco Randazzo, Lorenzo Natale, Giorgio Metta

    2008 8TH IEEE-RAS INTERNATIONAL CONFERENCE ON HUMANOID ROBOTS (HUMANOIDS 2008)     430 - 435  2008  [Refereed]

     View Summary

    Tactile feedback is of crucial importance for object manipulation in unknown environments. In this paper we describe the design and realization of a fingertip which includes a capacitive pressure sensor with 12 sensitive zones. It is naturally shaped and its size is small enough so that it can be mounted on the fingers of the humanoid robot iCub. It also embeds the electronic device which performs A/D conversion: This is beneficial for the signal to noise ratio and reduces the number of wires required to connect the fingertip to the robot. The fingertip is made of silicone, which makes its surface and inner structure compliant and flexible. We present preliminary experiments performed with the first prototype.

    DOI

  • On the Robustness of Simple Speed Control for a Quadruped Robot.

    Schmitz, A, Gómez, G. J, Iida, F, Pfeifer, R

    International Conference on Morphological Computation, Venice, Italy    2007

  • Versatile In-Hand Manipulation of Objects with Different Sizes and Shapes Using Neural Networks

    Funabashi, S, Schmitz, A, Sato, T, Somlor, S, Sugano, S

    IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids 2018)     1 - 9  [Refereed]

    DOI

  • Continuous Sensing Ability of Robot Finger Joints with Tactile Sensors

    HSU, Chincheng, Schmitz, Alexander, Kusayanagi, Kosuke, Sugano, Shigeki

    IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM 2019)    [Refereed]

  • Robot Finger with Remote Center of Motion Mechanism for Covering Joints with Thick Skin.

    Chincheng HSU, Alexander SCHMITZ, Kosuke KUSAYANAGI, Shigeki SUGANO

    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019)    [Refereed]

  • Sequential clustering for tactile image compression to enable direct adaptive feedback

    Andreas Geier, Yan Gang, Tito Pradhono Tomo, Shun Ogasa, Sophon Somlor, Alexander Schmitz, Shigeki Sugano

    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019)    [Refereed]

  • Development of a 3-Axis Human Fingertip Tactile Sensor Based on Distributed Hall Effect Sensors

    Harris Kristanto, Prathamesh Sathe, Alexander Schmitz, Chincheng HSU, Tito Pradhono Tomo, Sophon Somlor, Shigeki Sugano

    IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids 2019)    [Refereed]

  • Magnetic 3-Axis Soft and Sensitive Fingertip Sensors Integration for the iCub Humanoid Robot

    Alexis Carlos Holgado, Nicola Piga, Tito Pradhono Tomo, Giulia Vezzani, Alexander Schmitz, Lorenzo Natale, Shigeki Sugano

    IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids 2019)    [Refereed]

▼display all

Books and Other Publications

  • Intrinsically Motivated Learning in Natural and Artificial Systems

    Baldassarre, G, Mirolli, M( Part: Contributor)

    Springer-Verlag, Berlin  2013 ISBN: 9783642323751

     View Summary

    Interdisciplinary authors explain latest theories on mammalian intelligence and learning, artificial intelligence, creativity, and evolution Identifies scientific and technological open challenges and most promising research directions Grounds theoretical with practical robotics experiments

Misc

  • ロボットの移動方向表出システムが人間の移動に及ぼす影響に関する調査

    大西智也, SHRESTHA Moondeep Chandra, 宇野絵莉香, 柳川勇人, SCHMITZ Alexander, 亀崎允啓, 菅野重樹

    日本ロボット学会学術講演会予稿集(CD-ROM)   34th  2016

    J-GLOBAL

  • ロボットの移動効率と人の心理面に配慮した人-ロボット協調移動フレームワークの提案

    横山悠太, 柳川勇人, 小林彩乃, SCHMITZ Alexander, 亀崎允啓, 菅野重樹

    日本ロボット学会学術講演会予稿集(CD-ROM)   34th  2016

    J-GLOBAL

Industrial Property Rights

  • 光学式触覚センサ

    シュミッツ,アレクサンダー, 許 晉誠, ソムロア,ソフォン, トモ,ティト プラドノ, 菅野 重樹

    Patent

  • 関節構造体及びロボットハンド

    シュミッツ,アレクサンダー, 許 晉誠, 草柳 晃介, 菅野 重樹

    Patent

  • 機械装置の動力伝達システム

    シュミッツ,アレクサンダー, 汪 偉, オルガド, アレクシス カルロス, 許 晉誠, 小林 健人, アルバレス ロペス, ハビエル, 王 語詩, 菅野 重樹

    Patent

  • 接触力調整エンドエフェクタ

    汪 偉, 許 晉誠, シュミッツ,アレクサンダー, オルガド, アレクシス カルロス, 小林 健人, アルバレス ロペス, ハビエル, 菅野 重樹

    Patent

  • トルクリミッタ

    シュミッツ,アレクサンダー, 汪 偉, オルガド, アレクシス カルロス, 許 晉誠, 小林 健人, アルバレス ロペス, ハビエル, 王 語詩, 菅野 重樹

    Patent

  • 身体部位接触力センサ

    6719756

    シュミッツ,アレクサンダー, ソムロア,ソフォン, トモ,ティト プラドノ, クリスタント,ハリス, 黄 振善, 菅野 重樹

    Patent

  • 多軸力センサ

    菅野 重樹, ハルタント,リチャード, シュミッツ,アレクサンダー, ソムロア,ソフォン

    Patent

▼display all

Other

  • https://www.robot-digest.com/contents/?id=1537952025-869007

    2018.11
     
     

     View Summary

    Article about 3d tactile sensor

  • Exhibition at Japan Robot Week

    2018.10
     
     
  • Innovation Leader Summit 2018

    2018.10
     
     

     View Summary

    Top 20 out of 558 startups

  • Exhibition at IEEE ICRA 2018

    2018.04
     
     
  • Exhibition at RoboDEX 2018

    2018.01
     
     
  • https://newspicks.com/news/2696588

    2017.12
     
     

     View Summary

    2017年12月22日付、NewsPicksに、Nicebotのインタビュー記事が掲載。独自開発のアクチュエーターやセンサ組み合わせによる安全性について玉城絵美准教授のコメントが紹介された。

  • http://waseda-edge.jp/event_report_2017?id=20171204

    2017.12
     
     

     View Summary

    2017年12月4日に西早稲田キャンパスにおいて、WASEDA-EDGE人材育成プログラムの企画の一環として行われたFMラジオ局J-WAVEの「INNOVATION WORLD」の公開収録にNicebotが参加し活動紹介を行った。(*放送は12月22日)

  • https://newswitch.jp/p/11199

    2017.11
     
     

     View Summary

    日刊工業新聞に、早大発のベンチャー立ち上げに関しての記事が掲載される。独自開発の指の触覚計測センサが詳細に説明される。

  • Exhibition at IREX 2017

    2017.11
     
     

▼display all

Awards

  • Tech Sirius 2018 第三位

    2018.02   合同会社テックアクセルベンチャーズ   安全で操作が簡単な、人に優しく易しいロボット

    Winner: Nicebot(早稲田

  • 平成29年度「論文賞

    2017.10   一般財団法人FA財団   A novel tri-axial capacitive-type skin sensor

    Winner: Sophon Somlor, Richard, Sahala Hartanto, Alexander Schmitz, Shigeki Sugano

  • Soft Material Robot Challenge (Soft Components Challenge) The 2nd place

    2017.06   IEEE International Conference on Robotics and Automation(ICRA2017)   “a Soft Distributed 3-axis Skin Sensor System and its Implementation on a Robotic Fingertip”

    Winner: Team uSkin

  • Best paper award

    2015.10   IEEE International Symposium on Robotics and Intelligent Sensors (IEEE-IRIS 2015)   First Results of Tilted Capacitive Sensors to Detect Shear Force.

    Winner: Somlor, S, Schmitz, A, Hartanto, R.S, Sugano S

Research Projects

  • Dense 3-axis tactile sensing and AI to implement human-like manual skills in robots

    Project Year :

    2019.04
    -
    2022.03
     

  • Small sized force/torque sensors for robotic arms and hands

    Project Year :

    2015.04
    -
    2017.03
     

     View Summary

    We developed tactile sensors based on capacitive and Hall effect sensing, and implemented them in robot hands. The main novelty is that the skin sensors enable 3-axis force sensing (x,y,z force) in a small and soft form factor. Moreover, capacitive 6-axis force-torque sensors were implemented. All sensors require a minimum number of wires for ease of integration. Furthermore, we performed research on in-hand manipulation

Presentations

  • Active exploration with a tactile robot hand

    SCHMITZ, Alexander, Somlor, Sophon  [Invited]

    ICRA 2018 Workshop “Active touch for perception and interaction” 

    Presentation date: 2018.04

  • Organizer: "The Robotic Sense of Touch: From Sensing to Understanding."

    S. Somlor, A. Schmitz, L. Jamone, L. Natale, G. Cheng

    IEEE International Conference on Robotics and Automation (ICRA 2017) 

    Presentation date: 2017.05

  • Tactile Sensing in TWENDY-ONE and new, soft, tri-axial force skin sensors

    SCHMITZ, Alexander, Sugano, Shigeki  [Invited]

    ICRA 2015 workshop “Get in touch! Tactile & Force Sensing for Autonomous, Compliant, Intelligent Robots” 

    Presentation date: 2015

Specific Research

  • Dense 3-axis tactile sensing and AI to implement human-like manual skills in robots

    2021  

     View Summary

    On the hardware side,the existing 3-axis tactile sensors were developed further with a fluid reservoir,which increases their softness and decreases the sensor’s hysteresis. Novel3-axis capacitive tactile sensors were developed, which are not susceptible to magneticinterference. Combined force and proximity tactile sensors were developed, forenhanced safety in human-robot interaction. A novel hand with remote center ofmotion mechanisms was implemented, so that thick tactile sensors can also coverthe joints of the robot hand. On the software side, ourtactile sensors were used for slip detection and prediction, as well as for inhand manipulation.

  • Dense 3-axis tactile sensing and AI to implement human-like manual skills in robots

    2021  

     View Summary

    On the hardware side, the existing 3-axistactile sensors were developed further with a fluid reservoir, which increasestheir softness and decreases the sensor’s hysteresis. Novel 3-axis capacitivetactile sensors were developed, which are not susceptible to magneticinterference. Combined force and proximity tactile sensors were developed, forenhanced safety in human-robot interaction. A novel hand with remote center ofmotion mechanisms was implemented, so that thick tactile sensors can also coverthe joints of the robot hand. &nbsp;On the software side, our tactile sensors wereused for slip detection and prediction, as well as for in hand manipulation.

 

Syllabus

▼display all

Teaching Experience

  • Research on Human Robot Interface

    Waseda University  

  • Intensive Seminar on Embodiment Informatics (実体情報学特別演習)

    Waseda University  

  • Practice on Embodiment Informatics A~J (実体情報学演習A~J)

    Waseda University  

  • Embodiment Informatics (実体情報学概論)

    Waseda University  

  • Seminar on Sensing in Embodiment Informatics A & B

    Waseda University  

  • Advanced Topics in Robots and Systems A & B

    Waseda University  

▼display all