Hybrid F' and ROS2 Architecture for Vision-Based Autonomous Flight: Design and Experimental Validation

TL;DR

This paper introduces a hybrid architecture combining NASA's F' framework with ROS2 for vision-based autonomous quadrotor flight, demonstrating real-time performance, robustness, and efficient resource use through experimental validation.

Contribution

The paper presents a novel integrated architecture that merges F' and ROS2 via Protocol Buffers, enabling deterministic control and flexible perception in autonomous aerial vehicles.

Findings

Achieved 87.19 Hz vision-based position estimation with high data continuity.

Successfully executed 15 ground commands with 100% success rate.

Maintained low resource utilization and zero stale telemetry messages.

Abstract

Autonomous aerospace systems require architectures that balance deterministic real-time control with advanced perception capabilities. This paper presents an integrated system combining NASA's F' flight software framework with ROS2 middleware via Protocol Buffers bridging. We evaluate the architecture through a 32.25-minute indoor quadrotor flight test using vision-based navigation. The vision system achieved 87.19 Hz position estimation with 99.90\% data continuity and 11.47 ms mean latency, validating real-time performance requirements. All 15 ground commands executed successfully with 100 % success rate, demonstrating robust F'--PX4 integration. System resource utilization remained low (15.19 % CPU, 1,244 MB RAM) with zero stale telemetry messages, confirming efficient operation on embedded platforms. Results validate the feasibility of hybrid flight-software architectures combining certification-grade determinism with flexible autonomy for autonomous aerial vehicles.