Task allocation plays a vital role in multi-robot autonomous cleaning
systems, where multiple robots work together to clean a large area. However,
there are several problems in relevant research to date. Most current studies
mainly focus on deterministic, single-task allocation for cleaning robots,
without considering hybrid tasks in uncertain working environments. Moreover,
there is a lack of datasets and benchmarks for relevant research. In this
paper, we contribute to multi-robot hybrid-task allocation for uncertain
autonomous cleaning systems by addressing these problems. First, we model the
uncertainties in the cleaning environment via robust optimization and propose a
novel robust mixed-integer linear programming model with practical constraints
including hybrid cleaning task order and robot's ability. Second, we establish
a dataset of 100 instances made from floor plans, each of which has 2D
manually-labeled images and a 3D model. Third, we provide comprehensive results
on the collected dataset using three traditional optimization approaches and a
deep reinforcement learning-based solver. The evaluation results show that our
formulation meets the needs of multi-robot cleaning task allocation and the
robust solver can protect the system from the worst cases with little
additional cost. The benchmark will be available at
{this https URL}.

本文通过建立数据集，利用深度强化学习求解器，采用新的鲁棒混合整数线性规划模型，解决了不确定自主清洁系统中多机器人混合任务分配的问题，并且可以在保持性能的情况下，防止系统出现最坏情况，同时提供了一个基准数据集。