AGCo-MATA: Air-Ground Collaborative Multi-Agent Task Allocation in Mobile Crowdsensing

TL;DR

This work addresses efficient task allocation in a heterogeneous air-ground mobile crowd sensing setting by formulating two regimes: AG-FAMT (when $N > M$) and AG-MAFT (when $N < M$). It introduces MT-MCMF for maximizing task completion with minimal travel distance (AG-FAMT) and a W-ILP approach with linear weighting (and K-means preprocessing) for balancing travel time and distance (AG-MAFT), complemented by a UAV charging strategy (PCTP) to sustain long-term missions. Across a large-scale, D4D-derived real-world dataset, the proposed methods outperform baselines in both task throughput and path efficiency, demonstrating improved sensing quality and resource use under varying task distributions and privacy constraints. Together, these contributions provide a scalable, energy-conscious framework for robust, cooperative air-ground mobile crowd sensing in urban environments.

Abstract

Rapid progress in intelligent unmanned systems has presented new opportunities for mobile crowd sensing (MCS). Today, heterogeneous air-ground collaborative multi-agent framework, which comprise unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs), have presented superior flexibility and efficiency compared to traditional homogeneous frameworks in complex sensing tasks. Within this context, task allocation among different agents always play an important role in improving overall MCS quality. In order to better allocate tasks among heterogeneous collaborative agents, in this paper, we investigated two representative complex multi-agent task allocation scenarios with dual optimization objectives: (1) For AG-FAMT (Air-Ground Few Agents More Tasks) scenario, the objectives are to maximize the task completion while minimizing the total travel distance; (2) For AG-MAFT (Air-Ground More Agents Few Tasks) scenario, where the agents are allocated based on their locations, has the optimization objectives of minimizing the total travel distance while reducing travel time cost. To achieve this, we proposed a Multi-Task Minimum Cost Maximum Flow (MT-MCMF) optimization algorithm tailored for AG-FAMT, along with a multi-objective optimization algorithm called W-ILP designed for AG-MAFT, with a particular focus on optimizing the charging path planning of UAVs. Our experiments based on a large-scale real-world dataset demonstrated that the proposed two algorithms both outperform baseline approaches under varying experimental settings, including task quantity, task difficulty, and task distribution, providing a novel way to improve the overall quality of mobile crowdsensing tasks.

Figures (11)

• Figure 1: Two scenarios of agents selection.
• Figure 2: MT-MCMF model of AG-FAMT problem.
• Figure 3: Charging trajectory of UAVs flying towards UGV.
• Figure 4: An illustration of the three types of task distribution.
• Figure 5: Distributions of areas and tasks.