This paper addresses a multi-robot planning problem in environments with partially unknown semantics. The environment is assumed to have known geometric structure (e.g., walls) and to be occupied by static labeled landmarks with uncertain positions and classes. This modeling approach gives rise to an uncertain semantic map generated by semantic SLAM algorithms. Our goal is to design control policies for robots equipped with noisy perception systems so that they can accomplish collaborative tasks captured by global temporal logic specifications. To specify missions that account for environmental and perceptual uncertainty, we employ a fragment of Linear Temporal Logic (LTL), called co-safe LTL, defined over perception-based atomic predicates modeling probabilistic satisfaction requirements. The perception-based LTL planning problem gives rise to an optimal control problem, solved by a novel sampling-based algorithm, that generates open-loop control policies that are updated online to adapt to a continuously learned semantic map. We provide extensive experiments to demonstrate the efficiency of the proposed planning architecture.
翻译:本文针对的是部分未知语义学环境中的多机器人规划问题。 环境假定有已知的几何结构( 如墙壁), 并被固定的标签标志所占据, 位置和等级不确定 。 这种建模方法导致语义学 SLAM 算法产生的语义图不确定 。 我们的目标是为配备噪音感知系统的机器人设计控制政策, 以便他们完成全球时间逻辑规格所捕捉的协作任务 。 要具体说明造成环境和感知不确定性的任务, 我们使用称为共同安全的LTL的线性时空逻辑(LTL)碎片, 其定义是超越基于感知的原子前端模型的满足度要求 。 基于感知的LTL规划问题引发了最佳控制问题, 由新型的基于采样的算法解决, 产生开放环控政策, 在线更新以适应持续学习的语义图 。 我们提供广泛的实验, 以证明拟议规划架构的效率 。