6DMA-Enabled ISAC for Low-Altitude Economy

TL;DR

This paper proposes a hierarchical deep reinforcement learning approach to optimize a six-dimensional movable antenna system for integrated sensing and communications in low-altitude environments, enhancing UAV data transmission.

Contribution

It introduces a novel 6DMA-enabled ISAC network with a hierarchical DRL algorithm for joint optimization of antenna movement, UAV flight, and beamforming.

Findings

The proposed algorithm outperforms fixed and partially movable schemes.

Joint optimization significantly improves data transmission rates.

The 6DMA system adapts effectively to UAV location distributions.

Abstract

In this paper, we investigate a six dimensional movable antenna (6DMA) enable integrated sensing and communications (ISAC) network in low-altitude economy. The studied 6DMA can move in a three-dimensional space and rotate around its surface center, making full use of spatial freedom to adapt to the different location distributions of uncrewed aerial vehicles (UAVs) adjust channel conditions in time. However, since the rotation and location change of 6DMA requires the assistance of a physical device, it is unreasonable for 6DMA to change locations too frequently. Therefore, we propose a hierarchical deep reinforcement learning algorithm based on twin delayed deep deterministic policy gradient. The first layer optimizes the rotation and location of 6DMA with infrequent updates, and the second layer optimizes the UAV flight direction and base station transmit beamforming matrix in each time slot. Under the condition of satisfying the sensing intensity of the sensing target, the total data transmission rate to the UAVs is maximized. The numerical results show that the proposed 6DMA-enable ISAC algorithm through joint optimization of multiple variables performs significantly better than the partially movable scheme and the fixed antenna position scheme.