🤖 AI Summary
Traditional aerial manipulation systems rely on expensive external sensing infrastructure, limiting deployment in complex indoor/outdoor field environments. To address this, we propose the first open-source, fully onboard-sensing-based soft aerial manipulation platform. Our approach integrates monocular/biocular visual SLAM, lightweight object detection and pose estimation, pneumatic soft actuators, and multi-sensor tightly-coupled localization, enabling fully autonomous navigation, grasping, and manipulation within a ROS 2 framework. Key contributions include: (1) the first demonstration of field-deployable, fully onboard autonomous aerial manipulation—without motion capture or GNSS; and (2) an open-source hardware-software stack, including a custom soft gripper and flight controller, significantly enhancing reproducibility and deployment flexibility. Experiments demonstrate >86% grasping success across diverse lighting conditions, low-texture scenes, and dynamic environments, validating the system’s robustness and practicality.
📝 Abstract
Aerial manipulation combines the versatility and speed of flying platforms with the functional capabilities of mobile manipulation, which presents significant challenges due to the need for precise localization and control. Traditionally, researchers have relied on offboard perception systems, which are limited to expensive and impractical specially equipped indoor environments. In this work, we introduce a novel platform for autonomous aerial manipulation that exclusively utilizes onboard perception systems. Our platform can perform aerial manipulation in various indoor and outdoor environments without depending on external perception systems. Our experimental results demonstrate the platform's ability to autonomously grasp various objects in diverse settings. This advancement significantly improves the scalability and practicality of aerial manipulation applications by eliminating the need for costly tracking solutions. To accelerate future research, we open source our ROS 2 software stack and custom hardware design, making our contributions accessible to the broader research community.