Jun Morimoto

Universitätsmedizin Göttingen, Göttingen, Lower Saxony, Germany

Are you Jun Morimoto?

Claim your profile

Publications (119)86.95 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a framework for generating coordinated periodic movements of robotic systems with multiple external inputs. We developed an adaptive pattern generator model that is composed of a two-factor observation model with a style parameter and phase dynamics with a phase variable. The style parameter controls the spatial patterns of the generated trajectories, and the phase variable manages its temporal profiles. By exploiting the style-phase separation in the pattern generation, we can independently design adaptation schemes for the spatial and temporal profiles of the pattern generator to multiple external inputs. To validate the effectiveness of our proposed method, we applied it to a user-exoskeleton model to achieve user-adaptive walking assistance for which the exoskeleton robot's movements need to be coordinated with the user walking patterns and environment. As a result, the exoskeleton robot successfully performed stable biped walking behaviors for walking assistance even when the style of the observed walking pattern and the period were suddenly changed.
    No preview · Article · Oct 2015 · Biological Cybernetics
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper we propose and evaluate a control system to (1) learn and (2) adapt robot motion for continuous non-rigid contact with the environment. We present the approach in the context of wiping surfaces with robots. Our approach is based on learning by demonstration. First an initial periodic motion, covering the essence of the wiping task, is transferred from a human to a robot. The system extracts and learns one period of motion. Once the user/demonstrator is content with the motion, the robot seeks and establishes contact with a given surface, maintaining a predefined force of contact through force feedback. The shape of the surface is encoded for the complete period of motion, but the robot can adapt to a different surface, perturbations or obstacles. The novelty stems from the fact that the feedforward component is learned and encoded in a dynamic movement primitive. By using the feedforward component, the feedback component is greatly reduced if not completely canceled. Finally, if the user is not satisfied with the periodic pattern, he/she can change parts of motion through predefined gestures or through physical contact in a manner of a tutor or a coach. The complete system thus allows not only a transfer of motion, but a transfer of motion with matching correspondences, i.e. wiping motion is constrained to maintain physical contact with the surface to be wiped. The interface for both learning and adaptation is simple and intuitive and allows for fast and reliable knowledge transfer to the robot. Simulated and real world results in the application domain of wiping a surface are presented on three different robotic platforms. Results of the three robotic platforms, namely a 7 degree-of-freedom Kuka LWR-4 robot, the ARMAR-IIIa humanoid platform and the Sarcos CB-i humanoid robot, depict different methods of adaptation to the environment and coaching.
    No preview · Article · Sep 2015 · Robotics and Autonomous Systems
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose an estimation method of human joint movements from measured EMG signals for assistive robot control. We focus on how to estimate joint movements using multiple EMG electrodes even under sensor failure situations. In real world applications, EMG sensor electrodes might become disconnected or detached from skin surfaces. If we consider EMG-based robot control for assistive robots, such sensor failures lead to significant errors in the estimation of user joint movements. To cope with these sensor failures, we propose a state estimation model that takes uncertain observations into account. Sensor channel anomalies are found by checking the covariance of the EMG signals measured by multiple EMG electrodes. To validate the proposed control framework, we artificially disconnect an EMG electrode or detach one side of an EMG probe from the skin surface during elbow joint movement estimation. We show proper control of a one-DOF exoskeleton robot based on the estimated joint torque using our proposed method even when one EMG electrode has a sensor problem; a standard method with no tolerability against uncertain observations was unable to deal with these fault situations. Furthermore, the errors of the estimated joint torque with our proposed method were smaller than the standard method or a method with a conventional sensor fault detection algorithm.
    No preview · Article · Jun 2015 · Proceedings - IEEE International Conference on Robotics and Automation
  • Source
    Giuseppe Lisi · Jun Morimoto
    [Show abstract] [Hide abstract]
    ABSTRACT: In this study, we analyse the electroencephalography (EEG) signal associated with gait speed changes (i.e. acceleration or deceleration). For data acquisition, healthy subjects were asked to perform volitional speed changes between 0, 1, and 2 Km/h, during treadmill walk. Simultaneously, the treadmill controller modified the speed of the belt according to the subject's linear speed. A classifier is trained to distinguish between the EEG signal associated with constant speed gait and with gait speed changes, respectively. Results indicate that the classification performance is fair to good for the majority of the subjects, with accuracies always above chance level, in both batch and pseudo-online approaches. Feature visualisation and equivalent dipole localisation suggest that the information used by the classifier is associated with increased activity in parietal areas, where mu and beta rhythms are suppressed during gait speed changes. Specifically, the parietal cortex may be involved in motor planning and visuomotor transformations throughout the online gait adaptation, which is in agreement with previous research. The findings of this study may help to shed light on the cortical involvement in human gait control, and represent a step towards a BMI for applications in post-stroke gait rehabilitation.
    Preview · Article · May 2015 · PLoS ONE
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a fault tolerant framework for biosignal-based robot control with multiple sensor electrodes. In this approach, to cope with sensor faults, a reliable joint torque estimation model is selected from a group of estimation models based on sensor failure classifiers. The correlation among the electromyography (EMG) signal streams is used as input feature vectors for fault detection. To validate our proposed method, we artificially disconnect an EMG electrode or detach one side of an EMG probe from the skin surface during elbow-joint torque estimation experiments with five participants. When one EMG sensor electrode experiences one of the problems, the experimental results show that the joint torque can be estimated with significantly fewer errors using our proposed approach than a joint torque estimation method without sensor fault detection or than a method with a conventional sensor fault detection algorithm. Furthermore, we controlled a mannequin-arm-attached one-DOF exoskeleton based on the estimated torque profiles by generating movements with the estimated torque derived from the selected model.
    No preview · Article · Mar 2015 · Advanced Robotics
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper proposes a real-time balance control technique that can be implemented to bipedal robots (exoskeletons, humanoids) whose ankle joints are powered via variable physical stiffness actuators. To achieve active balancing, an abstracted biped model, torsional spring-loaded flywheel, is utilized to capture approximated angular momentum and physical stiffness, which are of importance in postural balancing. In particular, this model enables us to describe the mathematical relation between Zero Moment Point and physical stiffness. The exploitation of variable physical stiffness leads to the following contributions: i) Variable physical stiffness property is embodied in a legged robot control task, for the first time in the literature to the authors' knowledge. ii) Through experimental studies conducted with our bipedal exoskeleton, the advantages of variable physical stiffness strategy are demonstrated with respect to the optimal constant stiffness strategy. The results indicate that the variable stiffness strategy provides more favorable results in terms of external disturbance dissipation, mechanical power reduction, and ZMP/CoM position regulation.
    Full-text · Article · Mar 2015 · IEEE/ASME Transactions on Mechatronics
  • Source
    Jun Morimoto · Mitsuo Kawato
    [Show abstract] [Hide abstract]
    ABSTRACT: In the past two decades, brain science and robotics have made gigantic advances in their own fields, and their interactions have generated several interdisciplinary research fields. First, in the 'understanding the brain by creating the brain' approach, computational neuroscience models have been applied to many robotics problems. Second, such brain-motivated fields as cognitive robotics and developmental robotics have emerged as interdisciplinary areas among robotics, neuroscience and cognitive science with special emphasis on humanoid robots. Third, in brain-machine interface research, a brain and a robot are mutually connected within a closed loop. In this paper, we review the theoretical backgrounds of these three interdisciplinary fields and their recent progress. Then, we introduce recent efforts to reintegrate these research fields into a coherent perspective and propose a new direction that integrates brain science and robotics where the decoding of information from the brain, robot control based on the decoded information and multimodal feedback to the brain from the robot are carried out in real time and in a closed loop. © 2015 The Author(s) Published by the Royal Society. All rights reserved.
    Full-text · Article · Mar 2015 · Journal of The Royal Society Interface
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this study, we show that the motor control performance of a humanoid robot can be improved efficiently using its previous experiences in a Reinforcement Learning (RL) framework. RL is becoming a common approach to acquire a nonlinear optimal policy through trial and error. However, applying RL to real robot control is very difficult since it usually requires many learning trials. Such trials cannot be executed in real environments due to the limited durability of the real system. Therefore, in this study, instead of executing many learning trials, we use a recently developed RL algorithm called importance-weighted Policy Gradients with Parameter based Exploration (PGPE), with which the robot can efficiently reuse the previously sampled data to improve its policy parameters. We apply importance-weighted PGPE to CB-i, our real humanoid robot, and show that it can learn both target-reaching movement and cart-pole swing-up movements in a real environment within 10 minutes without any prior knowledge of the task or any carefully designed initial trajectory.
    No preview · Article · Feb 2015
  • Yuka Ariki · Tetsunari Inamura · Jun Morimoto
    [Show abstract] [Hide abstract]
    ABSTRACT: We introduce a novel approach to learn a humanoid interface by using observed human behaviors. We propose using the observed human movements to extract task-relevant degrees-of-freedoms (DOFs) so that we can construct the humanoid interface to generate high-dimensional humanoid movements by using low-dimensional user inputs. The extracted intrinsic DOFs are represented as a task-relevant manifold. On the other hand, since the manifold is derived from the observed human movements, we cannot directly use the movements generated through the manifold to control a humanoid. Therefore, we introduce a calibration procedure to convert the movements generated through the manifold to the humanoid robot movements. By using the task-relevant manifold and the movement conversion, we can control a many-DOF humanoid robot using a low-dimensional command input interface such as a game pad. We show that fourteen-degrees-of-freedom humanoid robot can be controlled to draw two-dimensional spiral and star shapes in the three-dimensional Cartesian space by using the proposed low-dimensional control interface.
    No preview · Article · Feb 2015
  • Norikazu Sugimoto · Jun Morimoto
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a reinforcement learning (RL) framework to improve policies for a high-dimensional system through fewer interactions with real environments than standard RL methods. In our learning framework, we first use off-line simulations to improve the controller parameters with an approximated environment model to generate samples along locally optimized trajectories. We then use the approximated dynamics to improve the performance of a tool manipulation task in a path integral RL framework, which updates a policy from the sampled trajectories of the state and action vectors and the cost. In this study, we apply our proposed method to a bimanual humanoid motor learning task in which we need to explicitly consider a closed-chain constraint. We show that a 51-DOF real humanoid robot can learn to manipulate a rod to hit via-points using both arms within 36 interactions in a real environment.
    No preview · Article · Feb 2015
  • Source
    Tadej Petric · Andrej Gams · Leon Zlajpah · Ales Ude · Jun Morimoto

    Full-text · Dataset · Nov 2014

  • No preview · Conference Paper · Nov 2014
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we introduce our ongoing work on the development of an upper body exoskeleton robot, driven by a pneumatic-electric hybrid actuation system. Since the limb of an exoskeleton robot needs to have small inertia to achieve agility and safety, using a heavy actuator is not preferable. Furthermore, we need to use backdrivable actuators that can generate sufficiently large torques to support user movements. These two requirements may seem contradictory. In order to cope with this development problem, we use a hybrid actuation system composed of Pneumatic Artificial Muscles (PAMs) and small-size electromagnetic motors. Although we and other research groups have already presented the advantage of the hybrid actuation system, we newly propose the usage of Bowden cable in a hybrid actuator to transmit the force generated by the PAMs to joints of our exoskeleton robot so that we can design a compact upper limb with small inertia. In addition, small size electric motors are mechanically connected to joints in order to compensate uncertainty generated by the PAM dynamics and the Bowden cable. We demonstrate that the proposed joint is backdrivable with the capability of large torque generation for the gravity compensation task both in One-DOF system with a dummy weight and right arm of the upper body exoskeleton with a mannequin arm. We also show the right arm exoskeleton can be moved using a torque input, extracted from sensory information via a goniometer.
    No preview · Conference Paper · Sep 2014
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose to tackle in this paper the problem of controlling whole-body humanoid robot behavior through non-invasive brain-machine interfacing (BMI), motivated by the perspective of mapping human motor control strategies to human-like mechanical avatar. Our solution is based on the adequate reduction of the controllable dimensionality of a high-DOF humanoid motion in line with the state-of-the-art possibilities of non-invasive BMI technologies, leaving the complement subspace part of the motion to be planned and executed by an autonomous humanoid whole-body motion planning and control framework. The results are shown in full physics-based simulation of a 36-degree-of-freedom humanoid motion controlled by a user through EEG-extracted brain signals generated with motor imagery task.
    Full-text · Article · Aug 2014 · Frontiers in Systems Neuroscience
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we introduce our newly developed biosignal-based vertical weight support system that is composed of pneumatic artificial muscles (PAMs) and an electromyography (EMG) measurement device. By using our developed weight support system, assist force can be varied based on measured muscle activities; most existing systems can only generate constant assist forces. In this paper, we estimated knee and ankle joint torques from measured EMGs using floating base inverse dynamics. Knee and ankle joint estimated torques are converted to vertical forces by the kinematic model of a subject. The converted vertical forces are used as force inputs for the PAM actuator system. To validate our system's control performance, four healthy subjects performed a one-leg squat with his left leg while his right leg was assisted by our proposed system. We used the vertical force estimated from the measured EMG signals as a control input to the weight support system. We compared EMG magnitudes with four different experimental conditions: 1) normal two-leg squat; 2) one-leg squat without the assist system; 3) one-leg squat with EMG-based weight support; and 4) one-leg squat with constant force support. The EMG magnitude with the proposed weight support system was much closer to that with normal two-leg squat than that with one-leg squat without the assist system and than that with one-leg squat with constant force support.
    No preview · Article · Jul 2014 · IEEE Systems Journal
  • Source
    Giuseppe Lisi · Tomoyuki Noda · Jun Morimoto
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper investigates the influence of the leg afferent input, induced by a leg assistive robot, on the decoding performance of a BMI system. Specifically, it focuses on a decoder based on the event-related (de)synchronization (ERD/ERS) of the sensorimotor area. The EEG experiment, performed with healthy subjects, is structured as a 3 × 2 factorial design, consisting of two factors: "finger tapping task" and "leg condition." The former is divided into three levels (BMI classes), being left hand finger tapping, right hand finger tapping and no movement (Idle); while the latter is composed by two levels: leg perturbed (Pert) and leg not perturbed (NoPert). Specifically, the subjects' leg was periodically perturbed by an assistive robot in 5 out of 10 sessions of the experiment and not moved in the remaining sessions. The aim of this study is to verify that the decoding performance of the finger tapping task is comparable between the two conditions NoPert and Pert. Accordingly, a classifier is trained to output the class of the finger tapping, given as input the features associated with the ERD/ERS. Individually for each subject, the decoding performance is statistically compared between the NoPert and Pert conditions. Results show that the decoding performance is notably above chance, for all the subjects, under both conditions. Moreover, the statistical comparison do not highlight a significant difference between NoPert and Pert in any subject, which is confirmed by feature visualization.
    Preview · Article · May 2014 · Frontiers in Systems Neuroscience
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this study, we show that a movement policy can be improved efficiently using the previous experiences of a real robot. Reinforcement Learning (RL) is becoming a popular approach to acquire a nonlinear optimal policy through trial and error. However, it is considered very difficult to apply RL to real robot control since it usually requires many learning trials. Such trials cannot be executed in real environments because unrealistic time is necessary and the real system's durability is limited. Therefore, in this study, instead of executing many learning trials, we propose to use a recently developed RL algorithm, importance-weighted PGPE, by which the robot can efficiently reuse previously sampled data to improve it's policy parameters. We apply importance-weighted PGPE to CB-i, our real humanoid robot, and show that it can learn a target reaching movement and a cart-pole swing up movement in a real environment without using any prior knowledge of the task or any carefully designed initial trajectory.
    Full-text · Article · May 2014
  • Source
    Tadej Petric · Andrej Gams · Leon Zlajpah · Ales Ude · Jun Morimoto
    [Show abstract] [Hide abstract]
    ABSTRACT: The creation and adaptation of motor behaviors is an important capability for autonomous robots. In this paper we propose an approach for altering existing robot behaviors online, where a human coach interactively changes the robot motion to achieve the desired outcome. Using hand gestures, the human coach can specify the desired modifications to the previously acquired behavior. To preserve a natural posture while performing the task, the movement is encoded in the robot’s joint space using periodic dynamic movement primitives. The coaching gestures are mapped to the robot joint space via robot Jacobian and used to create a virtual force field affecting the movement. A recursive least squares technique is used to modify the existing movement with respect to the virtual force field. The proposed approach was evaluated on a simulated three degrees of freedom planar robot and on a real humanoid robot, where human coaching gestures were captured by an RGB-D sensor. Although our focus was on rhythmic movements, the developed approach is also applicable to discrete (point-to-point) movements.
    Full-text · Conference Paper · May 2014
  • Tatsuya Teramae · Tomoyuki Noda · Jun Morimoto
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose an optimal control framework for pneumatic actuators. In particular, we consider using Pneumatic Artificial Muscle (PAM) as a part of Pneumatic-Electric (PE) hybrid actuation system. An optimal control framework can be useful for PE hybrid system to properly distribute desired torque outputs to the actuators that have different characteristics. In the optimal control framework, the standard choice to represent control cost is squared force or torque outputs. However, since the control input for PAM is pressure rather than the force or the torque, we should explicitly consider the pressure of PAM as the control cost in an objective function of the optimal control method. We show that we are able to use pressure input as the control cost for PAM by explicitly considering the model which represents a relationship between the pressure input and the force output of PAM. We demonstrate that one-DOF robot with the PE hybrid actuation system can generate pressure-optimized ball throwing movements by using the optimal control method.
    No preview · Conference Paper · May 2014
  • Source
    Ales Ude · Bojan Nemec · Tadej Petric · Jun Morimoto
    [Show abstract] [Hide abstract]
    ABSTRACT: Dynamic movement primitives (DMPs) were proposed as an efficient way for learning and control of complex robot behaviors. They can be used to represent point-to-point and periodic movements and can be applied in Cartesian or in joint space. One problem that arises when DMPs are used to define control policies in Cartesian space is that there exists no minimal, singularity-free representation of orientation. In this paper we show how dynamic movement primitives can be defined for non minimal, singularity free representations of orientation, such as rotation matrices and quaternions. All of the advantages of DMPs, including ease of learning, the ability to include coupling terms, and scale and temporal invariance, can be adopted in our formulation. We have also proposed a new phase stopping mechanism to ensure full movement reproduction in case of perturbations.
    Full-text · Conference Paper · May 2014

Publication Stats

2k Citations
86.95 Total Impact Points

Institutions

  • 2013
    • Universitätsmedizin Göttingen
      Göttingen, Lower Saxony, Germany
  • 2010
    • Jožef Stefan Institute
      • Department of Automation, Robotics and biocybernetics
      Lubliano, Ljubljana, Slovenia
  • 2008
    • University of California, Los Angeles
      Los Ángeles, California, United States
  • 2000-2008
    • Japan Science and Technology Agency (JST)
      Edo, Tōkyō, Japan
  • 2006
    • CNS
      Sydney, New South Wales, Australia
  • 2004
    • Carnegie Mellon University
      • Robotics Institute
      Pittsburgh, Pennsylvania, United States
  • 1998
    • Nara Institute of Science and Technology
      • Graduate School of Information Science
      Ikuma, Nara, Japan
  • 1997
    • Osaka University
      Suika, Ōsaka, Japan