TWIMP: Two-Wheel Inverted Musculoskeletal Pendulum as a Learning Control Platform in the Real World with Environmental Physical Contact

TL;DR

This paper introduces TWIMP, a novel humanoid platform combining musculoskeletal design and a two-wheel inverted pendulum to facilitate learning control in contact-rich environments, demonstrating its potential through preliminary experiments.

Contribution

The paper presents a new humanoid platform, TWIMP, integrating musculoskeletal and two-wheel inverted pendulum features for real-world learning control with environmental contact.

Findings

Demonstrated soft contact capabilities with external environment

Showed mobility and contact handling in preliminary tests

Validated potential for learning control in contact-rich scenarios

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.