AeroGrab: A Unified Framework for Aerial Grasping in Cluttered Environments

TL;DR

This paper introduces an integrated aerial grasping system that combines active exploration, language understanding, and collision-aware grasp prediction to improve reliability in cluttered environments.

Contribution

It presents a novel end-to-end pipeline that unifies scene understanding, active exploration, grasp generation, and feasibility evaluation for aerial manipulation.

Findings

Robust grasping in cluttered real-world scenarios.

Effective integration of active perception with grasp feasibility.

High success rate in complex environments.

Abstract

Reliable aerial grasping in cluttered environments remains challenging due to occlusions and collision risks. Existing aerial manipulation pipelines largely rely on centroid-based grasping and lack integration between the grasp pose generation models, active exploration, and language-level task specification, resulting in the absence of a complete end-to-end system. In this work, we present an integrated pipeline for reliable aerial grasping in cluttered environments. Given a scene and a language instruction, the system identifies the target object and actively explores it to gain better views of the object. During exploration, a grasp generation network predicts multiple 6-DoF grasp candidates for each view. Each candidate is evaluated using a collision-aware feasibility framework, and the overall best grasp is selected and executed using standard trajectory generation and control methods. Experiments in cluttered real-world scenarios demonstrate robust and reliable grasp execution, highlighting the effectiveness of combining active perception with feasibility-aware grasp selection for aerial manipulation.