VernaCopter: Disambiguated Natural-Language-Driven Robot via Formal Specifications
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915184604348416 |
|---|---|
| author | van de Laar, Teun Zhang, Zengjie Qi, Shuhao Haesaert, Sofie Sun, Zhiyong |
| author_facet | van de Laar, Teun Zhang, Zengjie Qi, Shuhao Haesaert, Sofie Sun, Zhiyong |
| contents | It has been an ambition of many to control a robot for a complex task using natural language (NL). The rise of large language models (LLMs) makes it closer to coming true. However, an LLM-powered system still suffers from the ambiguity inherent in an NL and the uncertainty brought up by LLMs. This paper proposes a novel LLM-based robot motion planner, named \textit{VernaCopter}, with signal temporal logic (STL) specifications serving as a bridge between NL commands and specific task objectives. The rigorous and abstract nature of formal specifications allows the planner to generate high-quality and highly consistent paths to guide the motion control of a robot. Compared to a conventional NL-prompting-based planner, the proposed VernaCopter planner is more stable and reliable due to less ambiguous uncertainty. Its efficacy and advantage have been validated by two small but challenging experimental scenarios, implying its potential in designing NL-driven robots. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_09536 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VernaCopter: Disambiguated Natural-Language-Driven Robot via Formal Specifications van de Laar, Teun Zhang, Zengjie Qi, Shuhao Haesaert, Sofie Sun, Zhiyong Robotics Artificial Intelligence It has been an ambition of many to control a robot for a complex task using natural language (NL). The rise of large language models (LLMs) makes it closer to coming true. However, an LLM-powered system still suffers from the ambiguity inherent in an NL and the uncertainty brought up by LLMs. This paper proposes a novel LLM-based robot motion planner, named \textit{VernaCopter}, with signal temporal logic (STL) specifications serving as a bridge between NL commands and specific task objectives. The rigorous and abstract nature of formal specifications allows the planner to generate high-quality and highly consistent paths to guide the motion control of a robot. Compared to a conventional NL-prompting-based planner, the proposed VernaCopter planner is more stable and reliable due to less ambiguous uncertainty. Its efficacy and advantage have been validated by two small but challenging experimental scenarios, implying its potential in designing NL-driven robots. |
| title | VernaCopter: Disambiguated Natural-Language-Driven Robot via Formal Specifications |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2409.09536 |