Reasoning Knowledge-Gap in Drone Planning via LLM-based Active Elicitation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910046006280192 |
|---|---|
| author | Fang, Zeyu Yu, Beomyeol Liu, Cheng Yang, Zeyuan Chen, Rongqian Lin, Yuxin Imani, Mahdi Lan, Tian |
| author_facet | Fang, Zeyu Yu, Beomyeol Liu, Cheng Yang, Zeyuan Chen, Rongqian Lin, Yuxin Imani, Mahdi Lan, Tian |
| contents | Human-AI joint planning in Unmanned Aerial Vehicles (UAVs) typically relies on control handover when facing environmental uncertainties, which is often inefficient and cognitively demanding for non-expert operators. To address this, we propose a novel framework that shifts the collaboration paradigm from control takeover to active information elicitation. We introduce the Minimal Information Neuro-Symbolic Tree (MINT), a reasoning mechanism that explicitly structures knowledge gaps regarding obstacles and goals into a queryable format. By leveraging large language models, our system formulates optimal binary queries to resolve specific ambiguities with minimal human interaction. We demonstrate the efficacy of this approach through a comprehensive workflow integrating a vision-language model for perception, voice interfaces, and a low-level UAV control module in both high-fidelity NVIDIA Isaac simulations and real-world deployments. Experimental results show that our method achieves a significant improvement in the success rate for complex search-and-rescue tasks while significantly reducing the frequency of human interaction compared to exhaustive querying baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07824 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Reasoning Knowledge-Gap in Drone Planning via LLM-based Active Elicitation Fang, Zeyu Yu, Beomyeol Liu, Cheng Yang, Zeyuan Chen, Rongqian Lin, Yuxin Imani, Mahdi Lan, Tian Robotics Human-AI joint planning in Unmanned Aerial Vehicles (UAVs) typically relies on control handover when facing environmental uncertainties, which is often inefficient and cognitively demanding for non-expert operators. To address this, we propose a novel framework that shifts the collaboration paradigm from control takeover to active information elicitation. We introduce the Minimal Information Neuro-Symbolic Tree (MINT), a reasoning mechanism that explicitly structures knowledge gaps regarding obstacles and goals into a queryable format. By leveraging large language models, our system formulates optimal binary queries to resolve specific ambiguities with minimal human interaction. We demonstrate the efficacy of this approach through a comprehensive workflow integrating a vision-language model for perception, voice interfaces, and a low-level UAV control module in both high-fidelity NVIDIA Isaac simulations and real-world deployments. Experimental results show that our method achieves a significant improvement in the success rate for complex search-and-rescue tasks while significantly reducing the frequency of human interaction compared to exhaustive querying baselines. |
| title | Reasoning Knowledge-Gap in Drone Planning via LLM-based Active Elicitation |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.07824 |