Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Goal-Oriented UAV Communication Design and Optimization for Target Tracking: A MachineLearning Approach

Wenchao Wu, Yanning Wu, Yuanqing Yang, Yansha Deng

TL;DR

This paper addresses the gap between conventional communication-centric metrics and task performance in UAV target tracking. It introduces a goal-oriented communication framework called DeepP, which uses a deep Q-network to jointly optimize downlink C&C data generation and the maximum number of proactive repetitions for each transmission. By modeling the task as a POMDP and applying a DRL-based policy that leverages historical observations, the approach aims to maximize a long-term tracking reward that reflects tracking accuracy. Simulation results demonstrate that DeepP significantly improves the probability of successful tracking compared with a PID baseline, including substantial gains when the repetition count is optimized. The work highlights the potential of task-oriented optimization in UAV control systems and provides a practical methodology for integrating communication decisions with real-time tracking objectives.

Abstract

To accomplish various tasks, safe and smooth control of unmanned aerial vehicles (UAVs) needs to be guaranteed, which cannot be met by existing ultra-reliable low latency communications (URLLC). This has attracted the attention of the communication field, where most existing work mainly focused on optimizing communication performance (i.e., delay) and ignored the performance of the task (i.e., tracking accuracy). To explore the effectiveness of communication in completing a task, in this letter, we propose a goal-oriented communication framework adopting a deep reinforcement learning (DRL) algorithm with a proactive repetition scheme (DeepP) to optimize C&C data selection and the maximum number of repetitions in a real-time target tracking task, where a base station (BS) controls a UAV to track a mobile target. The effectiveness of our proposed approach is validated by comparing it with the traditional proportional integral derivative (PID) algorithm.

Goal-Oriented UAV Communication Design and Optimization for Target Tracking: A MachineLearning Approach

TL;DR

This paper addresses the gap between conventional communication-centric metrics and task performance in UAV target tracking. It introduces a goal-oriented communication framework called DeepP, which uses a deep Q-network to jointly optimize downlink C&C data generation and the maximum number of proactive repetitions for each transmission. By modeling the task as a POMDP and applying a DRL-based policy that leverages historical observations, the approach aims to maximize a long-term tracking reward that reflects tracking accuracy. Simulation results demonstrate that DeepP significantly improves the probability of successful tracking compared with a PID baseline, including substantial gains when the repetition count is optimized. The work highlights the potential of task-oriented optimization in UAV control systems and provides a practical methodology for integrating communication decisions with real-time tracking objectives.

Abstract

To accomplish various tasks, safe and smooth control of unmanned aerial vehicles (UAVs) needs to be guaranteed, which cannot be met by existing ultra-reliable low latency communications (URLLC). This has attracted the attention of the communication field, where most existing work mainly focused on optimizing communication performance (i.e., delay) and ignored the performance of the task (i.e., tracking accuracy). To explore the effectiveness of communication in completing a task, in this letter, we propose a goal-oriented communication framework adopting a deep reinforcement learning (DRL) algorithm with a proactive repetition scheme (DeepP) to optimize C&C data selection and the maximum number of repetitions in a real-time target tracking task, where a base station (BS) controls a UAV to track a mobile target. The effectiveness of our proposed approach is validated by comparing it with the traditional proportional integral derivative (PID) algorithm.
Paper Structure (9 sections, 17 equations, 2 figures, 1 algorithm)

This paper contains 9 sections, 17 equations, 2 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model and Problem Formulation
  3. Real-time Target Tracking Task
  4. Channel Model
  5. Proactive repetition scheme
  6. Problem Formulation
  7. DRL-Based Velocity and Maximum Repetition Number Selection
  8. Simulation Results
  9. Conclusion

Figures (2)

  • Figure 1: System model
  • Figure 2: Performance comparison.