Integrated Sensing and Communications for UAV-Assisted Internet of Things: A Deep Reinforcement Learning Approach

Strategic Insights -

Research from the Dalian University of Technology in China has led to a new study on Mathematics, where a team of engineers designed a UAV-ISAC assisted IoT system to sense and acquire information from IoT devices in complex environments. This system utilizes Integrated Sensing and Communications (ISAC) technology, which is expected to be applied to uncrewed aerial vehicle (UAV)-assisted Internet of Things (IoT) systems. The study explores the challenges of designing such a system, including unknown IoT node positions, non-convex optimization problems, and constrained resources. To address these challenges, the researchers proposed an algorithm based on multi-step learning Dueling Double Deep Q-learning network (DDQN) from deep reinforcement learning (DRL).

Key Takeaways:

  • The UAV-ISAC assisted IoT system was designed to sense and acquire information from IoT devices in complex environments.
  • The system utilizes Integrated Sensing and Communications (ISAC) technology and applies to uncrewed aerial vehicle (UAV)-assisted Internet of Things (IoT) systems.
  • The researchers identified several challenges in designing the system, including unknown IoT node positions, non-convex optimization problems, and constrained resources.
  • The proposed algorithm, based on multi-step learning Dueling Double Deep Q-learning network (DDQN) from deep reinforcement learning (DRL), achieved stable convergence under different constraint thresholds.
  • The algorithm was compared to other benchmark algorithms, and the research concluded that it achieved superior performance.
  • The study has been peer-reviewed and published in Ieee Transactions On Vehicular Technology.
  • The research was funded by the Funds of National Key Laboratory of Advanced Communication Networks.
  • The team of researchers includes Xin Liu, Jiahua Wu, Chang Zhao, and Zechen Liu from Dalian University of Technology.

Statistics:

  • 74 expedited conference issue number in Ieee Transactions On Vehicular Technology publication.
  • 9604-9616 pages in the publication of Ieee Transactions On Vehicular Technology.
  • 2025 publication date of the research in Ieee Transactions On Vehicular Technology.

Sources:

  • Integrated Sensing and Communications for Uav Assisted Internet of Things Based On Deep Reinforcement Learning. Ieee Transactions On Vehicular Technology, 2025;74(6):9604-9616. (Ieee-inst Electrical Electronics Engineers Inc)
  • Xin Liu, Jiahua Wu, Chang Zhao, and Zechen Liu, Dalian University of Technology.
  • NewsRx. New Mathematics Data Have Been Reported by Researchers at Dalian University of Technology (Integrated Sensing and Communications for Uav Assisted Internet of Things Based On Deep Reinforcement Learning). Journal of Engineering. July 14, 2025; p 2199.