Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.17748 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917997955776512 |
|---|---|
| author | Chisari, Eugenio von Hartz, Jan Ole Despinoy, Fabien Valada, Abhinav |
| author_facet | Chisari, Eugenio von Hartz, Jan Ole Despinoy, Fabien Valada, Abhinav |
| contents | Language-conditioned policies have recently gained substantial adoption in robotics as they allow users to specify tasks using natural language, making them highly versatile. While much research has focused on improving the action prediction of language-conditioned policies, reasoning about task descriptions has been largely overlooked. Ambiguous task descriptions often lead to downstream policy failures due to misinterpretation by the robotic agent. To address this challenge, we introduce AmbResVLM, a novel method that grounds language goals in the observed scene and explicitly reasons about task ambiguity. We extensively evaluate its effectiveness in both simulated and real-world domains, demonstrating superior task ambiguity detection and resolution compared to recent state-of-the-art baselines. Finally, real robot experiments show that our model improves the performance of downstream robot policies, increasing the average success rate from 69.6% to 97.1%. We make the data, code, and trained models publicly available at https://ambres.cs.uni-freiburg.de. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_17748 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Robotic Task Ambiguity Resolution via Natural Language Interaction Chisari, Eugenio von Hartz, Jan Ole Despinoy, Fabien Valada, Abhinav Robotics Language-conditioned policies have recently gained substantial adoption in robotics as they allow users to specify tasks using natural language, making them highly versatile. While much research has focused on improving the action prediction of language-conditioned policies, reasoning about task descriptions has been largely overlooked. Ambiguous task descriptions often lead to downstream policy failures due to misinterpretation by the robotic agent. To address this challenge, we introduce AmbResVLM, a novel method that grounds language goals in the observed scene and explicitly reasons about task ambiguity. We extensively evaluate its effectiveness in both simulated and real-world domains, demonstrating superior task ambiguity detection and resolution compared to recent state-of-the-art baselines. Finally, real robot experiments show that our model improves the performance of downstream robot policies, increasing the average success rate from 69.6% to 97.1%. We make the data, code, and trained models publicly available at https://ambres.cs.uni-freiburg.de. |
| title | Robotic Task Ambiguity Resolution via Natural Language Interaction |
| topic | Robotics |
| url | https://arxiv.org/abs/2504.17748 |