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

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.

[1]  Masayuki Inaba,et al.  Design Approach of Biologically-Inspired Musculoskeletal Humanoids , 2013 .

[2]  Sergey Levine,et al.  Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection , 2016, Int. J. Robotics Res..

[3]  Masayuki Inaba,et al.  Human mimetic musculoskeletal humanoid Kengoro toward real world physically interactive actions , 2016, 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids).

[4]  Masayuki Inaba,et al.  An advanced musculoskeletal humanoid Kojiro , 2007, 2007 7th IEEE-RAS International Conference on Humanoid Robots.

[5]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[6]  Masahito Togami,et al.  Basic Design of Human-Symbiotic Robot EMIEW , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  Masayuki Inaba,et al.  Online Self-body Image Acquisition Considering Changes in Muscle Routes Caused by Softness of Body Tissue for Tendon-driven Musculoskeletal Humanoids , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[8]  Alois Knoll,et al.  Toward Anthropomimetic Robotics: Development, Simulation, and Control of a Musculoskeletal Torso , 2013, Artificial Life.

[9]  Qiang Huang,et al.  Controller design of a two-wheeled inverted pendulum mobile robot , 2008, 2008 IEEE International Conference on Mechatronics and Automation.

[10]  Peter I. Corke,et al.  Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control , 2015, ICRA 2015.

[11]  Masayuki Inaba,et al.  Design of a Musculoskeletal Upper Limb with Pseudo Ball Joint Modules for the Control of Redundant Nonlinear Elastic Elements , 2018 .

[12]  Masayuki Inaba,et al.  A joint-space controller based on redundant muscle tension for multiple DOF joints in musculoskeletal humanoids , 2016, 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids).

[13]  Scott Kuindersma,et al.  Variable risk control via stochastic optimization , 2013, Int. J. Robotics Res..

[14]  Yoon Keun Kwak,et al.  Dynamic Analysis of a Nonholonomic Two-Wheeled Inverted Pendulum Robot , 2005, J. Intell. Robotic Syst..

[15]  Wojciech Zaremba,et al.  Domain randomization for transferring deep neural networks from simulation to the real world , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[16]  Masayuki Inaba,et al.  Online Learning of Joint-Muscle Mapping Using Vision in Tendon-Driven Musculoskeletal Humanoids , 2018, IEEE Robotics and Automation Letters.

[17]  Masayuki Inaba,et al.  Human mimetic foot structure with multi-DOFs and multi-sensors for musculoskeletal humanoid Kengoro , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[18]  Fei-Fei Li,et al.  Deep visual-semantic alignments for generating image descriptions , 2015, CVPR.

[19]  Seonghee Jeong,et al.  Wheeled inverted pendulum type assistant robot: inverted mobile, standing, and sitting motions , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[20]  Masayuki Inaba,et al.  Development of life-sized high-power humanoid robot JAXON for real-world use , 2015, 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids).