Latency Reduction and Packet Synchronization in Low-Resource Devices Connected by DDS Networks in Autonomous UAVs
Real-time flight controllers are becoming dependent on general-purpose operating systems, as the modularity and complexity of guidance, navigation, and control systems and algorithms increases. The non-deterministic nature of operating systems creates a critical weakness in the development of motion...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-11-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/22/9269 |
_version_ | 1797457763678289920 |
---|---|
author | Joao Leonardo Silva Cotta Daniel Agar Ivan R. Bertaska John P. Inness Hector Gutierrez |
author_facet | Joao Leonardo Silva Cotta Daniel Agar Ivan R. Bertaska John P. Inness Hector Gutierrez |
author_sort | Joao Leonardo Silva Cotta |
collection | DOAJ |
description | Real-time flight controllers are becoming dependent on general-purpose operating systems, as the modularity and complexity of guidance, navigation, and control systems and algorithms increases. The non-deterministic nature of operating systems creates a critical weakness in the development of motion control systems for robotic platforms due to the random delays introduced by operating systems and communication networks. The high-speed operation and sensitive dynamics of UAVs demand fast and near-deterministic communication between the sensors, companion computer, and flight control unit (FCU) in order to achieve the required performance. In this paper, we present a method to assess communications latency between a companion computer and an RTOS open-source flight controller, which is based on an XRCE-DDS bridge between clients hosted in the low-resource environment and the DDS network used by ROS2. A comparison based on the measured statistics of latency illustrates the advantages of XRCE-DDS compared to the standard communication method based on MAVROS-MAVLink. More importantly, an algorithm to estimate latency offset and clock skew based on an exponential moving average filter is presented, providing a tool for latency estimation and correction that can be used by developers to improve synchronization of processes that rely on timely communication between the FCU and companion computer, such as synchronization of lower-level sensor data at the higher-level layer. This addresses the challenges introduced in GNC applications by the non-deterministic nature of general-purpose operating systems and the inherent limitations of standard flight controller hardware. |
first_indexed | 2024-03-09T16:27:39Z |
format | Article |
id | doaj.art-9ca1604baacd436b9b4a4c20a521bb06 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T16:27:39Z |
publishDate | 2023-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-9ca1604baacd436b9b4a4c20a521bb062023-11-24T15:05:59ZengMDPI AGSensors1424-82202023-11-012322926910.3390/s23229269Latency Reduction and Packet Synchronization in Low-Resource Devices Connected by DDS Networks in Autonomous UAVsJoao Leonardo Silva Cotta0Daniel Agar1Ivan R. Bertaska2John P. Inness3Hector Gutierrez4Department of Aerospace Engineering, Physics and Space Sciences, Florida Institute of Technology, Melbourne, FL 32901, USACore Developer, PX4 Autopilot, 8092 Zurich, SwitzerlandControl Systems Design and Analysis Branch, NASA Marshall Space Flight Center, Huntsville, AL 35812, USAControl Systems Design and Analysis Branch, NASA Marshall Space Flight Center, Huntsville, AL 35812, USADepartment of Mechanical and Civil Engineering, Florida Institute of Technology, Melbourne, FL 32901, USAReal-time flight controllers are becoming dependent on general-purpose operating systems, as the modularity and complexity of guidance, navigation, and control systems and algorithms increases. The non-deterministic nature of operating systems creates a critical weakness in the development of motion control systems for robotic platforms due to the random delays introduced by operating systems and communication networks. The high-speed operation and sensitive dynamics of UAVs demand fast and near-deterministic communication between the sensors, companion computer, and flight control unit (FCU) in order to achieve the required performance. In this paper, we present a method to assess communications latency between a companion computer and an RTOS open-source flight controller, which is based on an XRCE-DDS bridge between clients hosted in the low-resource environment and the DDS network used by ROS2. A comparison based on the measured statistics of latency illustrates the advantages of XRCE-DDS compared to the standard communication method based on MAVROS-MAVLink. More importantly, an algorithm to estimate latency offset and clock skew based on an exponential moving average filter is presented, providing a tool for latency estimation and correction that can be used by developers to improve synchronization of processes that rely on timely communication between the FCU and companion computer, such as synchronization of lower-level sensor data at the higher-level layer. This addresses the challenges introduced in GNC applications by the non-deterministic nature of general-purpose operating systems and the inherent limitations of standard flight controller hardware.https://www.mdpi.com/1424-8220/23/22/9269flight control unitcompanion computerDDS networknon-deterministic delaycommunication latencyMAVLink |
spellingShingle | Joao Leonardo Silva Cotta Daniel Agar Ivan R. Bertaska John P. Inness Hector Gutierrez Latency Reduction and Packet Synchronization in Low-Resource Devices Connected by DDS Networks in Autonomous UAVs Sensors flight control unit companion computer DDS network non-deterministic delay communication latency MAVLink |
title | Latency Reduction and Packet Synchronization in Low-Resource Devices Connected by DDS Networks in Autonomous UAVs |
title_full | Latency Reduction and Packet Synchronization in Low-Resource Devices Connected by DDS Networks in Autonomous UAVs |
title_fullStr | Latency Reduction and Packet Synchronization in Low-Resource Devices Connected by DDS Networks in Autonomous UAVs |
title_full_unstemmed | Latency Reduction and Packet Synchronization in Low-Resource Devices Connected by DDS Networks in Autonomous UAVs |
title_short | Latency Reduction and Packet Synchronization in Low-Resource Devices Connected by DDS Networks in Autonomous UAVs |
title_sort | latency reduction and packet synchronization in low resource devices connected by dds networks in autonomous uavs |
topic | flight control unit companion computer DDS network non-deterministic delay communication latency MAVLink |
url | https://www.mdpi.com/1424-8220/23/22/9269 |
work_keys_str_mv | AT joaoleonardosilvacotta latencyreductionandpacketsynchronizationinlowresourcedevicesconnectedbyddsnetworksinautonomousuavs AT danielagar latencyreductionandpacketsynchronizationinlowresourcedevicesconnectedbyddsnetworksinautonomousuavs AT ivanrbertaska latencyreductionandpacketsynchronizationinlowresourcedevicesconnectedbyddsnetworksinautonomousuavs AT johnpinness latencyreductionandpacketsynchronizationinlowresourcedevicesconnectedbyddsnetworksinautonomousuavs AT hectorgutierrez latencyreductionandpacketsynchronizationinlowresourcedevicesconnectedbyddsnetworksinautonomousuavs |