Line coverage is to cover linear infrastructure modeled as 1D segments by robots, which received attention in recent years. With the increasing urbanization, the area of the city and the density of infrastructure continues to increase, which brings two issues: (1) Due to the energy constraint, it is hard for the homogeneous robot team to cover the large-scale linear infrastructure starting from one depot; (2) In the large urban scene, the imbalance of robots' path greatly extends the time cost of the multi-robot system, which is more serious than that in smaller-size scenes. To address these issues, we propose a heterogeneous multi-robot approach consisting of several teams, each of which contains one transportation robot (TRob) and several coverage robots (CRobs). Firstly, a balanced graph partitioning (BGP) algorithm is proposed to divide the road network into several similar-size sub-graphs, and then the TRob delivers a group of CRobs to the subgraph region quickly. Secondly, a balanced ulusoy partitioning (BUP) algorithm is proposed to extract similar-length tours for each CRob from the sub-graph. Abundant experiments are conducted on seven road networks ranging in scales that are collected in this paper. Our method achieves robot utilization of 90% and the best maximal tour length at the cost of a small increase in total tour length, which further minimizes the time cost of the whole system. The source code and the road networks are available at https://github.com/suhangsong/BLC-LargeScale.

翻译：线段覆盖是指用机器人覆盖建模为一维线段的线性基础设施，近年来受到广泛关注。随着城市化进程加速，城市面积与基础设施密度持续增长，这带来了两个问题：(1) 由于能量限制，同质机器人团队难以从单一站点出发覆盖大规模线性基础设施；(2) 在大型城市场景中，机器人路径的不平衡会极大延长多机器人系统的时间成本，其严重程度远超小规模场景。为解决这些问题，我们提出了一种异质多机器人方法，该方法由多个团队组成，每个团队包含一个运输机器人(TRob)和多个覆盖机器人(CRobs)。首先，提出平衡图划分(BGP)算法将道路网络划分为多个规模相似的子图，随后TRob快速将一组CRobs运送至子图区域。其次，提出平衡乌鲁索伊划分(BUP)算法，从子图中为每个CRob提取长度相近的巡游路径。我们在本文收集的七个不同规模的道路网络上进行了大量实验。我们的方法实现了90%的机器人利用率，并以总路径长度小幅增加为代价获得了最优最大路径长度，从而进一步最小化整个系统的时间成本。源代码与道路网络见 https://github.com/suhangsong/BLC-LargeScale。