21 July 2020 in IEEE Robotics and Automation Letters
Reinforcement Learning (RL) methods have been proven successful in solving manipulation tasks autonomously. However, RL is still not widely adopted on real robotic systems because working with real hardware entails additional challenges, especially when using rigid position-controlled manipulators. These challenges include the need for a robust controller to avoid undesired behavior, that risk damaging the robot and its environment, and constant supervision from a human operator. The main contributions of this work are, first, we propose a fail-safe mechanism for safely training an RL agent on manipulation tasks using a rigid robot. Second, to enable a position-controlled manipulator to perform contact-rich manipulation tasks, we implemented two different force control schemes based on standard force feedback controllers; one is a modified parallel position-force control, and the other one is an impedance control. Third, we empirically study both control schemes when used as the action representation of an RL agent. We evaluate the trade-off between control complexity and performance by comparing several versions of the control schemes, each with a different number of force control parameters. The proposed methods are validated both on simulation and a real robot, a UR3 e-series robotic arm when executing contact-rich manipulation tasks.
7 March 2013 in IEEE Transactions on Biomedical Engineering
In this study, we propose a multiuser myoelectric interface that can easily adapt to novel users. When a user performs different motions (e.g., grasping and pinching), different electromyography (EMG) signals are measured. When different users perform the same motion (e.g., grasping), different EMG signals are also measured. Therefore, designing a myoelectric interface that can be used by multiple users to perform multiple motions is difficult. To cope with this problem, we propose for EMG signals a bilinear model that is composed of two linear factors:1) user dependent and 2) motion dependent. By decomposing the EMG signals into these two factors, the extracted motion-dependent factors can be used as user-independent features. We can construct a motion classifier on the extracted feature space to develop the multiuser interface. For novel users, the proposed adaptation method estimates the user-dependent factor through only a few interactions. The bilinear EMG model with the estimated user-dependent factor can extract the user-independent features from the novel user data. We applied our proposed method to a recognition task of five hand gestures for robotic hand control using four-channel EMG signals measured from subject forearms. Our method resulted in 73% accuracy, which was statistically significantly different from the accuracy of standard non-multiuser interfaces, as the result of a two-sample t-test at a significance level of 1%.
1 June 2011 in Neural Networks
21 May 2021 in Advanced Robotics
In this paper, the socio-economic problems facing the construction industry in Japan are presented, including the COVID19 pandemic, an aging population, aging infrastructure, and severe natural disasters, and a project to tackle the problem is introduced. This project, called ‘Collaborative robots for adaptation of diverse environments and innovation of infrastructure construction,’ is a sub-project of the Moonshot project organized by the Cabinet Office in Japan. The key approach to proceeding with this project is an ‘open design’ for robotics. Based on this approach, three aspects of the research plans are introduced: (1) robots that flexibly adapt to the environment, (2) Many-modal AI for environment evaluation, and (3) Physical AI and dynamic collaboration of multi-robots. GRAPHICAL ABSTRACT
2 April 2013 in Advanced Robotics
This article focuses on learning motor skills for anthropomorphic robots that must interact with non-rigid materials to perform such tasks as wearing clothes, turning socks inside out, and applying bandages. We propose a novel reinforcement learning framework for learning motor skills that interact with non-rigid materials. Our learning framework focuses on the topological relationship between the configuration of the robot and the non-rigid material based on the consideration that most details of the material (e.g. wrinkles) are not important for performing the motor tasks. This focus allows us to define the task performance and provide reward signals based on a low-dimensional variable, i.e. topology coordinates, in a real environment using reliable sensors. We constructed an experimental setting with an anthropomorphic dual-arm robot and a tailor-made T-shirt for it. To demonstrate the feasibility of our framework, a robot performed a T-shirt wearing task, whose goal was to put both of its arms into the corresponding sleeves of the T-shirt. The robot acquired sequential movements that put both of its arms into the T-shirt.
1 October 2017 in Neural Networks