International Research Collaboration with Tohoku University (Yuchen Wang)

Share





Our laboratory at the Vidyasirimedhi Institute of Science and Technology (VISTEC) had the opportunity to host Yuchen Wang, an exchange student from Tohoku University, Japan, as part of an international research collaboration between the two institutions.

During her exchange, Yuchen Wang worked closely with Thirawat Chuthong from Bio-inspired Robotics and Neural Engineering Lab, VISTEC under the supervision of Prof. Poramate Manoonpong, and collaborated with Assoc. Prof. Dai Owaki from Tohoku University.

The collaboration resulted in a research study entitled “From Insect Behavior to Transferable Robot Locomotion: Inferring Embodied Locomotor Principles from Limited Data via Adversarial Inverse Reinforcement Learning,” published in Bioinspiration & Biomimetics. The study investigates how locomotion principles can be learned from a limited amount of stick insect walking data and transferred to a six-legged robot.

The research demonstrated that a six-legged robot could learn locomotion from a limited amount of stick insect walking data and adapt its movement to different conditions, including uneven terrain and leg loss. This work provides a promising direction for developing adaptive and transferable locomotion strategies for legged robots.

This collaboration represents an important opportunity for international research exchange between VISTEC and Tohoku University, bringing together expertise in bio-inspired robotics, neural control, and machine learning to advance adaptive locomotion in legged robots.

Research Team

  • Yuchen Wang — Tohoku University
  • Thirawat Chuthong — VISTEC
  • Prof. Poramate Manoonpong — VISTEC
  • Assoc. Prof. Dai Owaki — Tohoku University
  • Prof. Mitsuhiro Hayashibe — Tohoku University

Publication

Title: From Insect Behavior to Transferable Robot Locomotion: Inferring Embodied Locomotor Principles from Limited Data via Adversarial Inverse Reinforcement Learning

Journal: Bioinspiration & Biomimetics

DOI: 10.1088/1748-3190/ae901f

Related News