Trajectory Design for UAV-Based Internet-of-Things Data Collection: A Deep Reinforcement Learning Approach

  title={Trajectory Design for UAV-Based Internet-of-Things Data Collection: A Deep Reinforcement Learning Approach},
  author={Yang Wang and Zhen Gao and Jun Zhang and Xianbin Cao and Dezhi Zheng and Yue Gao and Derrick Wing Kwan Ng and Marco di Renzo},
  • Yang Wang, Zhen Gao, +5 authors M. Renzo
  • Published 23 July 2021
  • Computer Science, Engineering, Mathematics
  • ArXiv
In this paper, we investigate an unmanned aerial vehicle (UAV)-assisted Internet-of-Things (IoT) system in a sophisticated three-dimensional (3D) environment, where the UAV’s trajectory is optimized to efficiently collect data from multiple IoT ground nodes. Unlike existing approaches focusing only on a simplified two-dimensional scenario and the availability of perfect channel state information (CSI), this paper considers a practical 3D urban environment with imperfect CSI, where the UAV’s… Expand


Deep Reinforcement Learning for Fresh Data Collection in UAV-assisted IoT Networks
  • Mengjie Yi, Xijun Wang, Juan Liu, Yan Zhang, B. Bai
  • Computer Science, Mathematics
  • IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)
  • 2020
A Markov Decision Process is formulated to find the optimal flight trajectory of the UAV and transmission scheduling of the sensors that minimizes the weighted sum of the age of information (AoI) and a UAV-assisted data collection algorithm based on deep reinforcement learning (DRL) is further proposed to overcome the curse of dimensionality. Expand
AoI-Minimal Trajectory Planning and Data Collection in UAV-Assisted Wireless Powered IoT Networks
This article investigates the unmanned aerial vehicle (UAV)-assisted wireless powered Internet-of-Things system, where a UAV takes off from a data center, flies to each of the ground sensor nodesExpand
3D UAV Trajectory Design and Frequency Band Allocation for Energy-Efficient and Fair Communication: A Deep Reinforcement Learning Approach
A deep reinforcement learning (DRL)-based algorithm, named as EEFC-TDBA (energy-efficient fair communication through trajectory design and band allocation) that chooses the state-of-the-art DRL algorithm, deep deterministic policy gradient (DDPG), as its basis is proposed. Expand
3D Trajectory Optimization in Rician Fading for UAV-Enabled Data Harvesting
An efficient algorithm is proposed to derive its suboptimal solution by using the block coordinate descent technique, which iteratively optimizes the communication scheduling, the UAV’s horizontal trajectory, and its vertical trajectory. Expand
Mobile Unmanned Aerial Vehicles (UAVs) for Energy-Efficient Internet of Things Communications
To enable reliable uplink communications for the IoT devices with a minimum total transmit power, a novel framework is proposed for jointly optimizing the 3D placement and the mobility of the UAVs, device-UAV association, and uplink power control. Expand
Flight Time Minimization of UAV for Data Collection Over Wireless Sensor Networks
It is observed that the UAV’s optimal speed is proportional to the given energy of the sensors and the inter-sensor distance, but it is inversely proportional toThe data upload requirement. Expand
Learning-Based Energy-Efficient Data Collection by Unmanned Vehicles in Smart Cities
This paper proposes to leverage emerging deep reinforcement learning (DRL) techniques for enabling model-free unmanned vehicles control, and presents a novel and highly effective control framework, called “DRL-RVC,” which utilizes the powerful convolutional neural network for feature extraction of the necessary information and makes decisions under the guidance of the deep Q network. Expand
Multi-Antenna UAV Data Harvesting: Joint Trajectory and Communication Optimization
This paper considers a UAV-enabled wireless sensor network (WSN), where a multi-antenna UAV is dispatched to collect data from a group of sensor nodes (SNs), and proposes a traveling salesman problem (TSP)-based trajectory initialization. Expand
Joint Optimization on Trajectory, Altitude, Velocity, and Link Scheduling for Minimum Mission Time in UAV-Aided Data Collection
This article proposes a UAV-aided data collection design to gather data from a number of ground users (GUs) to minimize the total mission time and proposes a segment-based trajectory optimization algorithm (STOA) to avoid repeat travel and a group-based trajectories Optimization algorithm (GTOA) in large-scale high-density GU deployment to relieve massive computation introduced by STOA. Expand
Path Design for Cellular-Connected UAV with Reinforcement Learning
  • Yong Zeng, Xiaoli Xu
  • Computer Science, Engineering
  • 2019 IEEE Global Communications Conference (GLOBECOM)
  • 2019
A new reinforcement learning-based UAV path design algorithm is proposed by applying temporal-difference method to directly learn the state-value function of the corresponding Markov Decision Process to avoid the coverage holes of cellular networks even in the complex urban environment. Expand