DL-DRL: A double-level deep reinforcement learning approach for large-scale task scheduling of multi-UAV

TL;DR

This paper introduces DL-DRL, a double-level deep reinforcement learning framework that efficiently solves large-scale multi-UAV task scheduling by decomposing the problem into task allocation and route planning, outperforming traditional methods.

Contribution

The paper proposes a novel double-level DRL approach with an interactive training strategy, enabling scalable and efficient multi-UAV task scheduling for large problem sizes.

Findings

DL-DRL outperforms traditional heuristics and learning-based methods in solution quality.

The approach maintains high performance on problems with up to 1000 tasks.

The interactive training strategy improves training efficiency and solution balance.

Abstract

Exploiting unmanned aerial vehicles (UAVs) to execute tasks is gaining growing popularity recently. To solve the underlying task scheduling problem, the deep reinforcement learning (DRL) based methods demonstrate notable advantage over the conventional heuristics as they rely less on hand-engineered rules. However, their decision space will become prohibitively huge as the problem scales up, thus deteriorating the computation efficiency. To alleviate this issue, we propose a double-level deep reinforcement learning (DL-DRL) approach based on a divide and conquer framework (DCF), where we decompose the task scheduling of multi-UAV into task allocation and route planning. Particularly, we design an encoder-decoder structured policy network in our upper-level DRL model to allocate the tasks to different UAVs, and we exploit another attention based policy network in our lower-level DRL model to construct the route for each UAV, with the objective to maximize the number of executed tasks given the maximum flight distance of the UAV. To effectively train the two models, we design an interactive training strategy (ITS), which includes pre-training, intensive training and alternate training. Experimental results show that our DL-DRL performs favorably against the learning-based and conventional baselines including the OR-Tools, in terms of solution quality and computation efficiency. We also verify the generalization performance of our approach by applying it to larger sizes of up to 1000 tasks. Moreover, we also show via an ablation study that our ITS can help achieve a balance between the performance and training efficiency.