AERMANI-VLM: Structured Prompting and Reasoning for Aerial Manipulation with Vision Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mishra, Sarthak, Yadav, Rishabh Dev, Das, Avirup, Gupta, Saksham, Pan, Wei, Roy, Spandan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912685304578048
author Mishra, Sarthak
Yadav, Rishabh Dev
Das, Avirup
Gupta, Saksham
Pan, Wei
Roy, Spandan
author_facet Mishra, Sarthak
Yadav, Rishabh Dev
Das, Avirup
Gupta, Saksham
Pan, Wei
Roy, Spandan
contents The rapid progress of vision--language models (VLMs) has sparked growing interest in robotic control, where natural language can express the operation goals while visual feedback links perception to action. However, directly deploying VLM-driven policies on aerial manipulators remains unsafe and unreliable since the generated actions are often inconsistent, hallucination-prone, and dynamically infeasible for flight. In this work, we present AERMANI-VLM, the first framework to adapt pretrained VLMs for aerial manipulation by separating high-level reasoning from low-level control, without any task-specific fine-tuning. Our framework encodes natural language instructions, task context, and safety constraints into a structured prompt that guides the model to generate a step-by-step reasoning trace in natural language. This reasoning output is used to select from a predefined library of discrete, flight-safe skills, ensuring interpretable and temporally consistent execution. By decoupling symbolic reasoning from physical action, AERMANI-VLM mitigates hallucinated commands and prevents unsafe behavior, enabling robust task completion. We validate the framework in both simulation and hardware on diverse multi-step pick-and-place tasks, demonstrating strong generalization to previously unseen commands, objects, and environments.
format Preprint
id arxiv_https___arxiv_org_abs_2511_01472
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AERMANI-VLM: Structured Prompting and Reasoning for Aerial Manipulation with Vision Language Models
Mishra, Sarthak
Yadav, Rishabh Dev
Das, Avirup
Gupta, Saksham
Pan, Wei
Roy, Spandan
Robotics
The rapid progress of vision--language models (VLMs) has sparked growing interest in robotic control, where natural language can express the operation goals while visual feedback links perception to action. However, directly deploying VLM-driven policies on aerial manipulators remains unsafe and unreliable since the generated actions are often inconsistent, hallucination-prone, and dynamically infeasible for flight. In this work, we present AERMANI-VLM, the first framework to adapt pretrained VLMs for aerial manipulation by separating high-level reasoning from low-level control, without any task-specific fine-tuning. Our framework encodes natural language instructions, task context, and safety constraints into a structured prompt that guides the model to generate a step-by-step reasoning trace in natural language. This reasoning output is used to select from a predefined library of discrete, flight-safe skills, ensuring interpretable and temporally consistent execution. By decoupling symbolic reasoning from physical action, AERMANI-VLM mitigates hallucinated commands and prevents unsafe behavior, enabling robust task completion. We validate the framework in both simulation and hardware on diverse multi-step pick-and-place tasks, demonstrating strong generalization to previously unseen commands, objects, and environments.
title AERMANI-VLM: Structured Prompting and Reasoning for Aerial Manipulation with Vision Language Models
topic Robotics
url https://arxiv.org/abs/2511.01472