DroneVLA: VLA based Aerial Manipulation

TL;DR

DroneVLA presents an autonomous aerial manipulation system that interprets natural language commands to locate, navigate, grasp, and hand over objects using advanced vision-language reasoning and safe human interaction techniques.

Contribution

This work introduces a novel integration of vision-language reasoning, semantic navigation, and human-centric control for drone-based object manipulation from natural language commands.

Findings

Achieved precise localization with max error of 0.164m

Demonstrated effective natural language understanding for task prioritization

Validated safe human-drone interaction during object handover

Abstract

As aerial platforms evolve from passive observers to active manipulators, the challenge shifts toward designing intuitive interfaces that allow non-expert users to command these systems naturally. This work introduces a novel concept of autonomous aerial manipulation system capable of interpreting high-level natural language commands to retrieve objects and deliver them to a human user. The system is intended to integrate a MediaPipe based on Grounding DINO and a Vision-Language-Action (VLA) model with a custom-built drone equipped with a 1-DOF gripper and an Intel RealSense RGB-D camera. VLA performs semantic reasoning to interpret the intent of a user prompt and generates a prioritized task queue for grasping of relevant objects in the scene. Grounding DINO and dynamic A* planning algorithm are used to navigate and safely relocate the object. To ensure safe and natural interaction during the handover phase, the system employs a human-centric controller driven by MediaPipe. This module provides real-time human pose estimation, allowing the drone to employ visual servoing to maintain a stable, distinct position directly in front of the user, facilitating a comfortable handover. We demonstrate the system's efficacy through real-world experiments for localization and navigation, which resulted in a 0.164m, 0.070m, and 0.084m of max, mean euclidean, and root-mean squared errors, respectively, highlighting the feasibility of VLA for aerial manipulation operations.