Online Learning of Joint-Muscle Mapping Using Vision in Tendon-driven Musculoskeletal Humanoids

Abstract

The body structures of tendon-driven musculoskeletal humanoids are complex, and accurate modeling is difficult, because they are made by imitating the body structures of human beings. For this reason, we have not been able to move them accurately like ordinary humanoids driven by actuators in each axis, and large internal muscle tension and slack of tendon wires have emerged by the model error between its geometric model and the actual robot. Therefore, we construct a joint-muscle mapping (JMM) using a neural network (NN), which expresses a nonlinear relationship between joint angles and muscle lengths, and aim to move tendon-driven musculoskeletal humanoids accurately by updating the JMM online from data of the actual robot. In this study, the JMM is updated online by using the vision of the robot so that it moves to the correct position (Vision Updater). Also, we execute another update to modify muscle antagonisms correctly (Antagonism Updater). By using these two updaters, the error between the target and actual joint angles decrease to about 40% in 5 minutes, and we show through a manipulation experiment that the tendon-driven musculoskeletal humanoid Kengoro becomes able to move as intended. This novel system can adapt to the state change and growth of robots, because it updates the JMM online successively.

Accepted at IEEE Robotics and Automation Letters, 2018

References in corpus (1)

• Antagonist Inhibition Control in Redundant Tendon-driven Structures Based on Human Reciprocal Innervation for Wide Range Limb Motion of Musculoskeletal Humanoids

Cited by in corpus (12)

• Long-time Self-body Image Acquisition and its Application to the Control of Musculoskeletal Structures
• Musculoskeletal AutoEncoder: A Unified Online Acquisition Method of Intersensory Networks for State Estimation, Control, and Simulation of Musculoskeletal Humanoids
• Object Recognition, Dynamic Contact Simulation, Detection, and Control of the Flexible Musculoskeletal Hand Using a Recurrent Neural Network with Parametric Bias
• Online Self-body Image Acquisition Considering Changes in Muscle Routes Caused by Softness of Body Tissue for Tendon-driven Musculoskeletal Humanoids
• Robust Continuous Motion Strategy Against Muscle Rupture using Online Learning of Redundant Intersensory Networks for Musculoskeletal Humanoids
• TWIMP: Two-Wheel Inverted Musculoskeletal Pendulum as a Learning Control Platform in the Real World with Environmental Physical Contact
• Reflex-based Motion Strategy of Musculoskeletal Humanoids under Environmental Contact Using Muscle Relaxation Control
• A Method of Joint Angle Estimation Using Only Relative Changes in Muscle Lengths for Tendon-driven Humanoids with Complex Musculoskeletal Structures
• Hardware Design and Learning-Based Software Architecture of Musculoskeletal Wheeled Robot Musashi-W for Real-World Applications
• Online Learning of Danger Avoidance for Complex Structures of Musculoskeletal Humanoids and Its Applications
• Applications of Stretch Reflex for the Upper Limb of Musculoskeletal Humanoids: Protective Behavior, Postural Stability, and Active Induction
• Realization of Seated Walk by a Musculoskeletal Humanoid with Buttock-Contact Sensors From Human Constrained Teaching