ROSPlan: Planning in the Robot Operating System

TLDR

ROS is a distributed, modular framework for building robotic systems, and task planning assembles actions to achieve goals while minimizing costs, which is essential for avoiding dead‑ends and enabling intelligent behavior. The paper introduces ROSPLAN, an architecture for integrating task planning into ROS‑based robotic systems. ROSPLAN’s modular architecture embeds planning components within ROS, as demonstrated by a case study on autonomous underwater vehicles. The case study with autonomous underwater vehicles demonstrates ROSPLAN’s flexibility and robustness across diverse scenarios.

Abstract

The Robot Operating System (ROS) is a set of software libraries and tools used to build robotic systems. ROS is known for a distributed and modular design. Given a model of the environment, task planning is concerned with the assembly of actions into a structure that is predicted to achieve goals. This can be done in a way that minimises costs, such as time or energy. Task planning is vital in directing the actions of a robotic agent in domains where a causal chain could lock the agent into a dead-end state. Moreover, planning can be used in less constrained domains to provide more intelligent behaviour. This paper describes the ROSP LAN framework, an architecture for embedding task planning into ROS systems. We provide a description of the architecture and a case study in autonomous robotics. Our case study involves autonomous underwater vehicles in scenarios that demonstrate the flexibility and robustness of our approach.