LocoGPT: GPT-Based Multi-Humanoid-Task Policy for Humanoid Locomotion
2026年1月1日·
·
0 min read
Takato Horii
Authors
Siddharth Padmanabhan, Kazuki Miyazawa, Takato Horii
Abstract
A humanoid locomotion approach based on a GPT-style multi-humanoid-task policy. Leveraging the general-purpose reasoning capabilities of large language models, the method realizes a unified policy that handles a wide range of locomotion tasks.
Type
Publication
IEEE Access, 14
Authors
Takato Horii
(he/him)
Associate Professor
Associate Professor at Graduate School of Engineering Science, Osaka University.
Research interests include cognitive developmental robotics, computational modeling
of emotional development, and human-robot interaction.