Robotics as a Service (RaaS) emerges as a new paradigm to motivate diversified potential of the “remote-controlled economy” for flexible and efficient service provision with the help of cloud computing. The multi-robot cooperation (MRC) technology has been widely used in various intelligent logistics scenarios, such as warehouses, factories, airports and subway stations, benefiting from the advantages of high operational efficiency and low labor cost. While promising, the corresponding challenge is that the service functions deployed on logistics robots (LRs) are more prone to failures such as resource exhaustion and error configuration in the multi-robot system (MRS). In this way, it becomes extremely important to discover and locate abnormal services as soon as possible so as to ensure the stable and secure operation of MRS, further reducing or even avoiding economic loss. Due to the flexibility, scalability and resilience of Network Function Virtualization (NFV), this paper aims at proposing a NFV based complete service chain tracking and positioning process with a more fine-grained level of LRs. Specifically, a micro-service-based system framework for high-accurate service tracking and fault function positioning is constructed, in which two main micro-service functions are designed for service chain tracking and positioning to maintain the stability and reliability of the MRS. On one hand, the tracking micro-service proposes an improved Hopcroft-Karp algorithm to determine the optimal probing and tracking path for MRC. On the other hand, the positioning micro-service proposes a delay-aware dichotomy probing algorithm to minimize the number of probe packets. Experimental results indicate that the proposed system framework and mechanisms outperform the state-of-the-art methods in terms of tracking and positioning accuracy in the MRS.

中文翻译：

---

迈向精细化服务：NFV辅助跟踪定位，利用微服务实现多机器人协作


机器人即服务（RaaS）作为一种新范式应运而生，旨在激发“远程控制经济”的多元化潜力，借助云计算灵活高效地提供服务。多机器人协作（MRC）技术已广泛应用于仓库、工厂、机场、地铁站等各种智能物流场景，受益于作业效率高、人力成本低等优势。虽然前景广阔，但相应的挑战是部署在物流机器人（LR）上的服务功能更容易出现故障，例如多机器人系统（MRS）中的资源耗尽和错误配置。这样一来，尽快发现并定位异常服务，以保证MRS的稳定安全运行，进一步减少甚至避免经济损失就显得尤为重要。由于网络功能虚拟化（NFV）的灵活性、可扩展性和弹性，本文旨在提出一种基于NFV的完整服务链跟踪和定位流程，具有更细粒度的LR级别。具体来说，构建了基于微服务的高精度服务跟踪和故障功能定位的系统框架，其中设计了两个主要的微服务功能用于服务链跟踪和定位，以保持MRS的稳定性和可靠性。一方面，跟踪微服务提出了一种改进的Hopcroft-Karp算法来确定MRC的最佳探测和跟踪路径。另一方面，定位微服务提出了延迟感知二分探测算法，以最小化探测数据包的数量。 实验结果表明，所提出的系统框架和机制在 MRS 的跟踪和定位精度方面优于最先进的方法。