Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Environmental Awareness Dynamic 5G QoS for Retaining Real Time Constraints in Robotic Applications

Gerasimos Damigos, Akshit Saradagi, Sara Sandberg, George Nikolakopoulos

TL;DR

This work tackles maintaining real-time constraints for 5G-enabled UAVs by introducing a PFSM-driven, environment-aware framework that dynamically selects 5G QoS data flows to cope with network load and cluttered environments. The approach offloads time-critical tasks to edge cloud and uses dynamic QoS, rate adaptation, and fallback to onboard autonomy to keep RTT within the MPC's operation period. The key contributions include formalizing the problem, a PFSM-based dynamic QoS mechanism with environmental risk signaling, and real-world validation in a 5G SA network demonstrating improved latency stability and robustness under background traffic. The practical impact lies in enabling reliable, edge-assisted robotic operations over 5G by adaptively managing radio resources in the presence of environmental and network variability.

Abstract

The fifth generation (5G) cellular network technology is mature and increasingly utilized in many industrial and robotics applications, while an important functionality is the advanced Quality of Service (QoS) features. Despite the prevalence of 5G QoS discussions in the related literature, there is a notable absence of real-life implementations and studies concerning their application in time-critical robotics scenarios. This article considers the operation of time-critical applications for 5G-enabled unmanned aerial vehicles (UAVs) and how their operation can be improved by the possibility to dynamically switch between QoS data flows with different priorities. As such, we introduce a robotics oriented analysis on the impact of the 5G QoS functionality on the performance of 5G-enabled UAVs. Furthermore, we introduce a novel framework for the dynamic selection of distinct 5G QoS data flows that is autonomously managed by the 5G-enabled UAV. This problem is addressed in a novel feedback loop fashion utilizing a probabilistic finite state machine (PFSM). Finally, the efficacy of the proposed scheme is experimentally validated with a 5G-enabled UAV in a real-world 5G stand-alone (SA) network.

Environmental Awareness Dynamic 5G QoS for Retaining Real Time Constraints in Robotic Applications

TL;DR

This work tackles maintaining real-time constraints for 5G-enabled UAVs by introducing a PFSM-driven, environment-aware framework that dynamically selects 5G QoS data flows to cope with network load and cluttered environments. The approach offloads time-critical tasks to edge cloud and uses dynamic QoS, rate adaptation, and fallback to onboard autonomy to keep RTT within the MPC's operation period. The key contributions include formalizing the problem, a PFSM-based dynamic QoS mechanism with environmental risk signaling, and real-world validation in a 5G SA network demonstrating improved latency stability and robustness under background traffic. The practical impact lies in enabling reliable, edge-assisted robotic operations over 5G by adaptively managing radio resources in the presence of environmental and network variability.

Abstract

The fifth generation (5G) cellular network technology is mature and increasingly utilized in many industrial and robotics applications, while an important functionality is the advanced Quality of Service (QoS) features. Despite the prevalence of 5G QoS discussions in the related literature, there is a notable absence of real-life implementations and studies concerning their application in time-critical robotics scenarios. This article considers the operation of time-critical applications for 5G-enabled unmanned aerial vehicles (UAVs) and how their operation can be improved by the possibility to dynamically switch between QoS data flows with different priorities. As such, we introduce a robotics oriented analysis on the impact of the 5G QoS functionality on the performance of 5G-enabled UAVs. Furthermore, we introduce a novel framework for the dynamic selection of distinct 5G QoS data flows that is autonomously managed by the 5G-enabled UAV. This problem is addressed in a novel feedback loop fashion utilizing a probabilistic finite state machine (PFSM). Finally, the efficacy of the proposed scheme is experimentally validated with a 5G-enabled UAV in a real-world 5G stand-alone (SA) network.
Paper Structure (9 sections, 3 equations, 5 figures, 2 tables)

This paper contains 9 sections, 3 equations, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. System Architecture
  4. Problem definition
  5. QoS & Dynamic QoS motivation
  6. 5G QoS & Relative Priority
  7. Dynamic Resource Selection
  8. Experimental Evaluation
  9. Conclusions and Future Developments

Figures (5)

  • Figure 1: 5G-cloud-enabled UAV with distributed components in the cloud. The cloud offloading of time-critical algorithms are supported by various configurable QoS profiles.
  • Figure 2: System architecture and distributed component diagram.
  • Figure 3: PFSM architecture.
  • Figure 4: No QoS scenario and PFSM. The 5G-UAV performs a stationary hover where the offloaded MPC and an object detection algorithm are hosted in the edge cloud. Significant background load is introduced in the network cell and the system becomes unstable.
  • Figure 5: PFSM and dynamic QoS utilization enabled. The 5G-UAV performs a circular trajectory where the offloaded MPC and an object detection algorithm are hosted in the edge cloud. Significant background load is introduced in the network cell. The PFSM alternates between the designed states so that the 5G-UAV maintains optimal behavior and stability.