TWIMP: Two-Wheel Inverted Musculoskeletal Pendulum as a Learning Control Platform in the Real World with Environmental Physical Contact
Kento Kawaharazuka, Tasuku Makabe, Shogo Makino, Kei Tsuzuki, Yuya Nagamatsu, Yuki Asano, Takuma Shirai, Fumihito Sugai, Kei Okada, Koji Kawasaki, Masayuki Inaba
TL;DR
This work addresses the challenge of learning control for robots that must interact with real-world environments through physical contact. It introduces TWIMP, a hybrid platform combining a tendon-driven musculoskeletal upper limb with a two-wheel inverted pendulum lower limb to achieve soft environmental interaction and high mobility. The authors detail modular designs for both subsystems, integrate them into a unified TWIMP, and implement state-feedback with an optimal regulator alongside posture-adaptation mechanisms. Preliminary experiments demonstrate stable locomotion, manipulation capabilities, and resilience to impacts, supporting TWIMP as a practical platform for learning-control research in contact-rich settings. The study highlights future directions in learning-based control and hardware enhancements (e.g., spine or tail) to further improve stability and dexterity in the real world.
Abstract
By the recent spread of machine learning in the robotics field, a humanoid that can act, perceive, and learn in the real world through contact with the environment needs to be developed. In this study, as one of the choices, we propose a novel humanoid TWIMP, which combines a human mimetic musculoskeletal upper limb with a two-wheel inverted pendulum. By combining the benefit of a musculoskeletal humanoid, which can achieve soft contact with the external environment, and the benefit of a two-wheel inverted pendulum with a small footprint and high mobility, we can easily investigate learning control systems in environments with contact and sudden impact. We reveal our whole concept and system details of TWIMP, and execute several preliminary experiments to show its potential ability.