ReLI: A Language-Agnostic Approach to Human-Robot Interaction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916991220056064 |
|---|---|
| author | Nwankwo, Linus Ellensohn, Bjoern Özdenizci, Ozan Rueckert, Elmar |
| author_facet | Nwankwo, Linus Ellensohn, Bjoern Özdenizci, Ozan Rueckert, Elmar |
| contents | Adapting autonomous agents for real-world industrial, domestic, and other daily tasks is currently gaining momentum. However, in global or cross-lingual application contexts, ensuring effective interaction with the environment and executing unrestricted human-specified tasks regardless of the language remains an unsolved problem. To address this, we propose ReLI, a language-agnostic approach that enables autonomous agents to converse naturally, semantically reason about their environment, and perform downstream tasks, regardless of the task instruction's modality or linguistic origin. First, we ground large-scale pre-trained foundation models and transform them into language-to-action models that can directly provide common-sense reasoning and high-level robot control through natural, free-flow conversational interactions. Further, we perform cross-lingual adaptation of the models to ensure that ReLI generalises across the global languages. To demonstrate ReLI's robustness, we conducted extensive experiments on various short- and long-horizon tasks, including zero- and few-shot spatial navigation, scene information retrieval, and query-oriented tasks. We benchmarked the performance on $140$ languages involving $70K+$ multi-turn conversations. On average, ReLI achieved over $90\%\pm0.2$ accuracy in cross-lingual instruction parsing and task execution success. These results demonstrate its potential to advance natural human-agent interaction in the real world while championing inclusive and linguistic diversity. Demos and resources will be public at: https://linusnep.github.io/ReLI/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_01862 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ReLI: A Language-Agnostic Approach to Human-Robot Interaction Nwankwo, Linus Ellensohn, Bjoern Özdenizci, Ozan Rueckert, Elmar Robotics Adapting autonomous agents for real-world industrial, domestic, and other daily tasks is currently gaining momentum. However, in global or cross-lingual application contexts, ensuring effective interaction with the environment and executing unrestricted human-specified tasks regardless of the language remains an unsolved problem. To address this, we propose ReLI, a language-agnostic approach that enables autonomous agents to converse naturally, semantically reason about their environment, and perform downstream tasks, regardless of the task instruction's modality or linguistic origin. First, we ground large-scale pre-trained foundation models and transform them into language-to-action models that can directly provide common-sense reasoning and high-level robot control through natural, free-flow conversational interactions. Further, we perform cross-lingual adaptation of the models to ensure that ReLI generalises across the global languages. To demonstrate ReLI's robustness, we conducted extensive experiments on various short- and long-horizon tasks, including zero- and few-shot spatial navigation, scene information retrieval, and query-oriented tasks. We benchmarked the performance on $140$ languages involving $70K+$ multi-turn conversations. On average, ReLI achieved over $90\%\pm0.2$ accuracy in cross-lingual instruction parsing and task execution success. These results demonstrate its potential to advance natural human-agent interaction in the real world while championing inclusive and linguistic diversity. Demos and resources will be public at: https://linusnep.github.io/ReLI/. |
| title | ReLI: A Language-Agnostic Approach to Human-Robot Interaction |
| topic | Robotics |
| url | https://arxiv.org/abs/2505.01862 |