Don't Yell at Your Robot: Physical Correction as the Collaborative Interface for Language Model Powered Robots
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915068811149312 |
|---|---|
| author | Zhang, Chuye Shao, Yifei Simon Parekh, Harshil Shi, Junyao Chaudhari, Pratik Kumar, Vijay Figueroa, Nadia |
| author_facet | Zhang, Chuye Shao, Yifei Simon Parekh, Harshil Shi, Junyao Chaudhari, Pratik Kumar, Vijay Figueroa, Nadia |
| contents | We present a novel approach for enhancing human-robot collaboration using physical interactions for real-time error correction of large language model (LLM) powered robots. Unlike other methods that rely on verbal or text commands, the robot leverages an LLM to proactively executes 6 DoF linear Dynamical System (DS) commands using a description of the scene in natural language. During motion, a human can provide physical corrections, used to re-estimate the desired intention, also parameterized by linear DS. This corrected DS can be converted to natural language and used as part of the prompt to improve future LLM interactions. We provide proof-of-concept result in a hybrid real+sim experiment, showcasing physical interaction as a new possibility for LLM powered human-robot interface. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_12602 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Don't Yell at Your Robot: Physical Correction as the Collaborative Interface for Language Model Powered Robots Zhang, Chuye Shao, Yifei Simon Parekh, Harshil Shi, Junyao Chaudhari, Pratik Kumar, Vijay Figueroa, Nadia Robotics Human-Computer Interaction We present a novel approach for enhancing human-robot collaboration using physical interactions for real-time error correction of large language model (LLM) powered robots. Unlike other methods that rely on verbal or text commands, the robot leverages an LLM to proactively executes 6 DoF linear Dynamical System (DS) commands using a description of the scene in natural language. During motion, a human can provide physical corrections, used to re-estimate the desired intention, also parameterized by linear DS. This corrected DS can be converted to natural language and used as part of the prompt to improve future LLM interactions. We provide proof-of-concept result in a hybrid real+sim experiment, showcasing physical interaction as a new possibility for LLM powered human-robot interface. |
| title | Don't Yell at Your Robot: Physical Correction as the Collaborative Interface for Language Model Powered Robots |
| topic | Robotics Human-Computer Interaction |
| url | https://arxiv.org/abs/2412.12602 |