TrustNavGPT: Modeling Uncertainty to Improve Trustworthiness of Audio-Guided LLM-Based Robot Navigation
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_ | 1866929449355706368 |
|---|---|
| author | Sun, Xingpeng Zhang, Yiran Tang, Xindi Bedi, Amrit Singh Bera, Aniket |
| author_facet | Sun, Xingpeng Zhang, Yiran Tang, Xindi Bedi, Amrit Singh Bera, Aniket |
| contents | While LLMs are proficient at processing text in human conversations, they often encounter difficulties with the nuances of verbal instructions and, thus, remain prone to hallucinate trust in human command. In this work, we present TrustNavGPT, an LLM based audio guided navigation agent that uses affective cues in spoken communication elements such as tone and inflection that convey meaning beyond words, allowing it to assess the trustworthiness of human commands and make effective, safe decisions. Our approach provides a lightweight yet effective approach that extends existing LLMs to model audio vocal features embedded in the voice command and model uncertainty for safe robotic navigation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_01867 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TrustNavGPT: Modeling Uncertainty to Improve Trustworthiness of Audio-Guided LLM-Based Robot Navigation Sun, Xingpeng Zhang, Yiran Tang, Xindi Bedi, Amrit Singh Bera, Aniket Robotics While LLMs are proficient at processing text in human conversations, they often encounter difficulties with the nuances of verbal instructions and, thus, remain prone to hallucinate trust in human command. In this work, we present TrustNavGPT, an LLM based audio guided navigation agent that uses affective cues in spoken communication elements such as tone and inflection that convey meaning beyond words, allowing it to assess the trustworthiness of human commands and make effective, safe decisions. Our approach provides a lightweight yet effective approach that extends existing LLMs to model audio vocal features embedded in the voice command and model uncertainty for safe robotic navigation. |
| title | TrustNavGPT: Modeling Uncertainty to Improve Trustworthiness of Audio-Guided LLM-Based Robot Navigation |
| topic | Robotics |
| url | https://arxiv.org/abs/2408.01867 |