From text to motion: grounding GPT-4 in a humanoid robot “Alter3”
This paper introduces Alter3, a humanoid robot that demonstrates spontaneous motion generation through the integration of GPT-4, a cutting-edge Large Language Model (LLM). This integration overcomes the challenge of applying LLMs to direct robot control, which typically struggles with the hardware-s...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-05-01
|
| Series: | Frontiers in Robotics and AI |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frobt.2025.1581110/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849325324927500288 |
|---|---|
| author | Takahide Yoshida Atsushi Masumori Atsushi Masumori Takashi Ikegami Takashi Ikegami |
| author_facet | Takahide Yoshida Atsushi Masumori Atsushi Masumori Takashi Ikegami Takashi Ikegami |
| author_sort | Takahide Yoshida |
| collection | DOAJ |
| description | This paper introduces Alter3, a humanoid robot that demonstrates spontaneous motion generation through the integration of GPT-4, a cutting-edge Large Language Model (LLM). This integration overcomes the challenge of applying LLMs to direct robot control, which typically struggles with the hardware-specific nuances of robotic operation. By translating linguistic descriptions of human actions into robotic movements via programming, Alter3 can autonomously perform a diverse range of actions, such as adopting a “selfie” pose or simulating a “ghost.” This approach not only shows Alter3’s few-shot learning capabilities but also its adaptability to verbal feedback for pose adjustments without manual fine-tuning. This research advances the field of humanoid robotics by bridging linguistic concepts with physical embodiment and opens new avenues for exploring spontaneity in humanoid robots. |
| format | Article |
| id | doaj-art-212570ee8fc645b0be489e03221f967a |
| institution | Kabale University |
| issn | 2296-9144 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Robotics and AI |
| spelling | doaj-art-212570ee8fc645b0be489e03221f967a2025-08-20T03:48:27ZengFrontiers Media S.A.Frontiers in Robotics and AI2296-91442025-05-011210.3389/frobt.2025.15811101581110From text to motion: grounding GPT-4 in a humanoid robot “Alter3”Takahide Yoshida0Atsushi Masumori1Atsushi Masumori2Takashi Ikegami3Takashi Ikegami4Graduate School of Arts and Sciences, The University of Tokyo, Tokyo, JapanGraduate School of Arts and Sciences, The University of Tokyo, Tokyo, JapanAlternative Machine Inc., Tokyo, JapanGraduate School of Arts and Sciences, The University of Tokyo, Tokyo, JapanAlternative Machine Inc., Tokyo, JapanThis paper introduces Alter3, a humanoid robot that demonstrates spontaneous motion generation through the integration of GPT-4, a cutting-edge Large Language Model (LLM). This integration overcomes the challenge of applying LLMs to direct robot control, which typically struggles with the hardware-specific nuances of robotic operation. By translating linguistic descriptions of human actions into robotic movements via programming, Alter3 can autonomously perform a diverse range of actions, such as adopting a “selfie” pose or simulating a “ghost.” This approach not only shows Alter3’s few-shot learning capabilities but also its adaptability to verbal feedback for pose adjustments without manual fine-tuning. This research advances the field of humanoid robotics by bridging linguistic concepts with physical embodiment and opens new avenues for exploring spontaneity in humanoid robots.https://www.frontiersin.org/articles/10.3389/frobt.2025.1581110/fullhumanoid robotlarge language modelsmotion generationembodimentagency |
| spellingShingle | Takahide Yoshida Atsushi Masumori Atsushi Masumori Takashi Ikegami Takashi Ikegami From text to motion: grounding GPT-4 in a humanoid robot “Alter3” Frontiers in Robotics and AI humanoid robot large language models motion generation embodiment agency |
| title | From text to motion: grounding GPT-4 in a humanoid robot “Alter3” |
| title_full | From text to motion: grounding GPT-4 in a humanoid robot “Alter3” |
| title_fullStr | From text to motion: grounding GPT-4 in a humanoid robot “Alter3” |
| title_full_unstemmed | From text to motion: grounding GPT-4 in a humanoid robot “Alter3” |
| title_short | From text to motion: grounding GPT-4 in a humanoid robot “Alter3” |
| title_sort | from text to motion grounding gpt 4 in a humanoid robot alter3 |
| topic | humanoid robot large language models motion generation embodiment agency |
| url | https://www.frontiersin.org/articles/10.3389/frobt.2025.1581110/full |
| work_keys_str_mv | AT takahideyoshida fromtexttomotiongroundinggpt4inahumanoidrobotalter3 AT atsushimasumori fromtexttomotiongroundinggpt4inahumanoidrobotalter3 AT atsushimasumori fromtexttomotiongroundinggpt4inahumanoidrobotalter3 AT takashiikegami fromtexttomotiongroundinggpt4inahumanoidrobotalter3 AT takashiikegami fromtexttomotiongroundinggpt4inahumanoidrobotalter3 |