Bipedal Walking of Underwater Soft Robot Based on Data-Driven Model Inspired by Octopus

Qiuxuan Wu; Yan Wu; Xiaochen Yang; Botao Zhang; Jian Wang; Sergey A Chepinskiy; Anton A Zhilenkov

doi:10.3389/frobt.2022.815435

Bipedal Walking of Underwater Soft Robot Based on Data-Driven Model Inspired by Octopus

Front Robot AI. 2022 Apr 20:9:815435. doi: 10.3389/frobt.2022.815435. eCollection 2022.

Authors

Qiuxuan Wu^{1

2

3}, Yan Wu¹, Xiaochen Yang^{1

2}, Botao Zhang^{1

2}, Jian Wang^{2

4}, Sergey A Chepinskiy⁴, Anton A Zhilenkov³

Affiliations

¹ Institute of Electrical Engineering, School of Automation, Hangzhou Dianzi University, Hangzhou, China.
² HDU-ITMO Joint Institute, Hangzhou Dianzi University, Hangzhou, China.
³ Institute of Hydrodynamics and Control Processes, Saint-Petersburg State Marine Technical University, Saint Petersburg, Russia.
⁴ Faculty of Control Systems and Robotics, ITMO University, Saint Petersburg, Russia.

Abstract

The soft organisms in nature have always been a source of inspiration for the design of soft arms and this paper draws inspiration from the octopus's tentacle, aiming at a soft robot for moving flexibly in three-dimensional space. In the paper, combined with the characteristics of an octopus's tentacle, a cable-driven soft arm is designed and fabricated, which can motion flexibly in three-dimensional space. Based on the TensorFlow framework, a data-driven model is established, and the data-driven model is trained using deep reinforcement learning strategy to realize posture control of a single soft arm. Finally, two trained soft arms are assembled into an octopus-inspired biped walking robot, which can go forward and turn around. Experimental analysis shows that the robot can achieve an average speed of 7.78 cm/s, and the maximum instantaneous speed can reach 12.8 cm/s.

Keywords: Octopus’s tentacle; bipedal coordinated walking; cable drive; data-driven model; deep reinforcement learning; soft arm.