Path planning as a service PPaaS: Cloud-based robotic path planning

Abstract

Cloud computing framework can provide promising solutions for service robots to overcome various challenges in unstructured environments. In this paper, we present the design and implementation details of a novel cloud-based system architecture for robotic path planning. The proposed system, called Path Planning as a Service (PPaaS), is based on a three-layered architectural design: cloud server layer, cloud engine layer, and client robot layer. The cloud server layer is implemented with Hadoop Distributed File System. It contains a path plan database, which stores the solution paths that can be shared among robots. The cloud engine layer, which is the core of the architecture, utilizes Rapyuta cloud engine to create configurable containers for different robotic platforms. It also provides an on-demand path planning software in the cloud, which computes the optimal paths for robots to reach the goal positions. A load balancer is suggested to manage the container allocation in machines and coordinate local/cloud computation load balancing. The client robot layer is formed by a set of physical robots that employ PPaaS in the cloud. The communication framework of the entire system is based on Robot Operating System (ROS) platform, despite that robot clients do not necessarily run ROS. We have extended the proposed system for a case study of people tracking and following by multiple robots. We have also experimentally verified the feasibility and effectiveness of solving the shortest path problem via parallel processing in the cloud. The technical implementation details as well as the challenges of the proposed cloud robotics system are presented in the paper.