Jun Morimoto

Learning-Based Joint Control with Hierarchical Reinforcement Learning and On-Device Execution

In typical robot learning, deep reinforcement learning policies are employed in the upper control layer to generate target joint angles for robot motion, while conventional controllers are used in the fast lower control layer to control each joint motor. This paper presents a fully neural network-ba…

M2oE: Modular Mixture of Experts for Multi-Morphology Reinforcement Learning of Modular Robots

Modular robots offer a promising solution for building versatile and adaptable robotic systems. For instance, space exploration robots can be designed to reconfigure to meet diverse task demands across varying environments. However, training such systems by Reinforcement Learning (RL) remains challe…

Motion Generation for Modular Robots Using Hierarchical Policies

When the Adversary Knows You Better: Adversarial Training for Learning-Based Legged Robots

Deep reinforcement learning has emerged as the dominant paradigm for training legged robots to locomote, however, when deployed in unstructured, dynamically varying real-world environments, the safety of neural network based controllers remains insufficiently guaranteed. Prior studies have demonstra…

Cutting Sequence Diffuser: Sim-to-Real Transferable Planning for Object Shaping by Grinding

Automating object shaping by grinding with a robot is a crucial industrial process that involves removing material with a rotating grinding belt. This process generates removal resistance depending on such process conditions as material type, removal volume, and robot grinding posture, all of which

Learning-Based Joint Control With Hierarchical Reinforcement Learning and On-Device Execution

In typical robot learning, deep reinforcement learning policies are employed in the upper control layer to generate target joint angles for robot motion, while conventional controllers are used in the fast lower control layer to control each joint motor. This paper presents a fully neural network-ba

VecNav: Vector Goal Robot Navigation from In-the-wild Videos

We propose VecNav, a novel approach that trains a monocular navigation model through self-supervision using uncalibrated, human-captured videos. These videos, characterized by unknown camera intrinsics and extrinsics, are readily available from video-sharing platforms (e.g. YouTube) and are referred

GAN-Based Semi-Supervised Training of LSTM Nets for Intention Recognition in Cooperative Tasks

The accumulation of a sufficient amount of data for training deep neural networks is a major hindrance in the application of deep learning in robotics. Acquiring real-world data requires considerable time and effort, yet it might still not capture the full range of potential environmental variations

Learning to Shape by Grinding: Cutting-Surface-Aware Model-Based Reinforcement Learning

Object shaping by grinding is a crucial industrial process in which a rotating grinding belt removes material. Object-shape transition models are essential to achieving automation by robots; however, learning such a complex model that depends on process conditions is challenging because it requires

Randomized-to-Canonical Model Predictive Control for Real-World Visual Robotic Manipulation

Many works have recently explored Sim-to-real transferable visual model predictive control (MPC). However, such works are limited to one-shot transfer, where real-world data must be collected once to perform the sim-to-real transfer, which remains a significant human effort in transferring the model

Selective Assist Strategy by Using Lightweight Carbon Frame Exoskeleton Robot

Exoskeleton robots need to always actively assist the user’s movements otherwise robot just becomes a heavy load for the user. However, estimating diversified movement intentions in a user’s daily life is not easy and no algorithm so far has achieved that level of estimation. In this s

Composing an Assistive Control Strategy Based on Linear Bellman Combination From Estimated User's Motor Goal

In assistive control strategies, we must estimate the user's movement intentions. In previous studies, such intended motions were inferred by linearly converting muscle activities to the joint torques of an assistive robot or classifying muscle activities to identify the most likely movement from pr

Computationally Affordable Hierarchical Framework for Humanoid Robot Control

We propose a hierarchical control framework for generating versatile motions by a humanoid robot. The central feature of our framework is computational affordability: a large amount of computation time is allowable in the upper-level hierarchy. Consequently, whole-body trajectory optimization for a…

Full-Body Optimal Control Toward Versatile and Agile Behaviors in a Humanoid Robot

In this letter, we develop an optimal control framework that takes the full-body dynamics of a humanoid robot into account. Employing full-body dynamics has been explored in, especially, an online optimal control approach known as model predictive control (MPC). However, whole-body motions cannot be

Quaternion-Based Trajectory Optimization of Human Postures for Inducing Target Muscle Activation Patterns

In exercise and rehabilitation, to effectively train the human body, human motion trajectory is essential because it induces muscle activity patterns. In this letter, we develop a novel framework for the trajectory optimization of human postures, including the head, the limbs, and the body to induce

Exploiting Human and Robot Muscle Synergies for Human-in-the-loop Optimization of EMG-based Assistive Strategies

In this study, we propose a novel human-in-the-loop optimization approach for exoskeleton robot control. We develop a method to optimize widely-used Electromyography (EMG)-based assistive strategies. If we use multiple EMG channels to control multi-DoF robots, optimization process becomes complex an…

Learning to Write Anywhere with Spatial Transformer Image-to-Motion Encoder-Decoder Networks

Learning to recognize and reproduce handwritten characters is already a challenging task both for humans and robots alike, but learning to do the same thing for characters that can be transformed arbitrarily in space, as humans do when writing on a blackboard for instance, significantly ups the ante…

Deep Encoder-Decoder Networks for Mapping Raw Images to Dynamic Movement Primitives

In this paper we propose a new approach for learning perception-action couplings. We show that by collecting a suitable set of raw images and the associated movement trajectories, a deep encoder-decoder network can be trained that takes raw images as input and outputs the corresponding dynamic movem…

EMG-Based Model Predictive Control for Physical Human-Robot Interaction: Application for Assist-As-Needed Control

In this letter, we propose an electromyography (EMG)-based optimal control framework to design physical human-robot interaction for rehabilitation and develop a novel assist-as-needed (AAN) controller based on a model predictive control (MPC) approach. To enhance the recovery of motor functions, enc

Reinforcement Learning of Phase Oscillators for Fast Adaptation to Moving Targets

Online movement generation in tasks involving real humanoid robots interacting with fast-moving targets is extremely difficult. This paper approaches this problem via imitation and reinforcement learning using phase variables. Imitation learning is used to acquire primitive trajectories of the demon

Robotizing Double-Bar Ankle-Foot Orthosis

This paper introduces an approach that robotizes an ankle-foot orthosis (AFO). In particular, toward post-stroke gait rehabilitation, we robotize a double-bar AFO, which is widely used in rehabilitation facilities, by newly designing a modular joint, a pneumatic actuator, and a Bowden cable force-tr…

Learning task-parametrized assistive strategies for exoskeleton robots by multi-task reinforcement learning

Recent studies suggest that reinforcement learning has great potential for generating assistive strategies in exoskeletons through physical interactions between a user and a robot. Previous methods focused on a task-specific assistive strategy, where for every single task (situation/context), the us…

Power-augmentation control approach for arm exoskeleton based on human muscular manipulability

The paper presents a novel control method for the arm exoskeletons that takes into account the muscular force manipulability of the human arm. In contrast to classical controllers that provide assistance without considering the biomechanical properties of the human arm, we propose a control method t…

User-robot collaborative excitation for PAM model identification in exoskeleton robots

Pneumatic Artificial Muscle (PAM) actuators have been used as exoskeletons because of their inherited compliance and high power-weight ratio. However, creating accurate models remains difficult mainly due to the compliance issue; the model can be changed by the force applied by the user. Therefore,…

Dry-wireless EEG and asynchronous adaptive feature extraction towards a plug-and-play co-adaptive brain robot interface

This paper introduces a novel asynchronous adaptive brain machine interface (BMI), based on a dry-wireless headset, to trigger the movement of a lower limb exoskeleton robot by foot motor imagery. Specifically, it addresses two issues that are critical for the development of a plug-and-play brain ro

Learning assistive strategies from a few user-robot interactions: Model-based reinforcement learning approach

Designing an assistive strategy for exoskeletons is a key ingredient in movement assistance and rehabilitation. While several approaches have been explored, most studies are based on mechanical models of the human user, i.e., rigid-body dynamics or Center of Mass (CoM)-Zero Moment Point (ZMP) invert

Trajectory representation by nonlinear scaling of dynamic movement primitives

An effective robot trajectory representation should encode all relevant aspects of the desired motion. For kinematic representations, this means that both the spatial course of the trajectory and its speed profile must be specified. The concept of dynamic movement primitives (DMP) provides a kinemat…

Accelerating synchronization of movement primitives: Dual-arm discrete-periodic motion of a humanoid robot

Human-demonstrated motion transferred to a robotic platform often needs to be adapted to the current state of the environment or to modified task requirements. Adaptation, i. e. learning of a modified behavior, needs to be fast to enable quick utilization of the robot either in industry or in future…

Development of a pneumatic-electromagnetic hybrid linear actuator with an integrated structure

Conventional hybrid actuators can achieve a better force/torque bandwidth than a single principle actuator without losing back-drivability. However, hybrid actuators occupy space at least equal to the sum of the volumes of two or more actuators and multiple transmissions consisting of timing belts,…

Estimating joint movements from observed EMG signals with multiple electrodes under sensor failure situations toward safe assistive robot control

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 becom…

Torque and variable stiffness control for antagonistically driven pneumatic muscle actuators via a stable force feedback controller

This paper describes a novel controller that is capable of simultaneously controlling torque and variable stiffness in real-time, for actuators with antagonistically driven pneumatic artificial muscles (PAMs). To this end, two contributions are presented: i) A stable force feedback controller that c…

Towards balance recovery control for lower body exoskeleton robots with Variable Stiffness Actuators: Spring-loaded flywheel model

This paper presents a biologically-inspired real-time balance recovery control strategy that is applied to a lower body exoskeleton with variable physical stiffness actuators at its ankle joints. For this purpose, a torsional spring-loaded flywheel model is presented to encapsulate both approximated…