ROSPlan: Planning in the Robot Operating System

  title={ROSPlan: Planning in the Robot Operating System},
  author={Michael Cashmore and Maria Fox and Derek Long and Daniele Magazzeni and Bram Ridder and Arnau Carrera and Narc{\'i}s Palomeras and Nat{\`a}lia Hurt{\'o}s and Marc Carreras},
  booktitle={International Conference on Automated Planning and Scheduling},
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… 

Figures from this paper

PlanSys2: A Planning System Framework for ROS2

The ROS2 Planning System (PlanSys2 in short) is described, a framework for symbolic planning that incorporates novel approaches for execution on robots working in demanding environments that aims to be the reference task planning framework in ROS2.

Planning for Robots with Skills

This paper presents a method for automatically generating planning problems from existing skill definitions such that the resulting problems can be solved using off-the-shelf planning software, and the solutions can be used to control robot actions in the world.

An Action Interface Manager for ROSPlan

A novel implementation of a mapping module that greatly reduces the amount of effort that is required to integrate an automated planner with a robotic platform and includes a Graphical User Interface though which the mapping can be easily generated and updated.

Logic programming for deliberative robotic task planning

A survey on recent advances in the application of logic programming to the problem of task planning is presented and different planners and their suitability for specific robotic applications are analyzed, based on expressivity in domain representation, computational efficiency and software implementation.

Probabilistic Planning for Robotics with ROSPlan

A standardized integration of probabilistic planners into ROSPlan that allows for reasoning with non-deterministic effects and is agnostic to the probabilism planner used is presented.

Autonomous Building of Structures in Unstructured Environments via AI Planning

A novel AI planning representation, based on a Cartesian coordinate system, for enabling the autonomous operations of Multi-Robot Systems in 3D environments and scale up performance by implementing direct FDR (Finite Domain Representation) generation based on the best performing PDDL model, bypassing the PDDL-to-FDR translation used by the majority of modern planners.

A Tool to Model Task Planning Domain for Human-Robot Collaboration

A novel software tool, called TENANT (Tool fostEriNg Ai plaNning in roboTics), that facilitates domain experts in goals, tasks and a set operational constraints enabling the automatic generation of planning models for robot control is presented.

Task planning of mobile robots in distributed service framework

An effective and flexible task planning system of mobile robots is designed in distributed service framework with Robot Operating System (ROS) and the logical description tool Planning Domain Definition Language (PDDL) is used to describe the task dynamically based on the designed knowledge base and distributed sensing.

A ROSPlan-Based Multi-Robot Navigation System

A multi-robot version of RosPlan, which that is a framework for embedding a generic task planner in a ROS system, is proposed, which includes a new method to dispatch the actions; a system to ensure that each robot execute only its actions and a new ROS Package for multi- robot navigation.

Integrating Classical Planning and Real Robots in Industrial and Service Robotics Domains

An architecture to integrate classical planning and real autonomous mobile robots and to deal with execution issues the authors code the agent actions with automatas and prove the flexibility of the system by testing on two different domains.



Combined task and motion planning through an extensible planner-independent interface layer

This work proposes a new approach that uses off-the-shelf task planners and motion planners and makes no assumptions about their implementation and uses a novel representational abstraction that requires only that failures in computing a motion plan for a high-level action be identifiable and expressible in the form of logical predicates at the task level.

Interleaving Temporal Planning and Execution in Robotics Domains

A framework to integrate deliberative planning, plan repair and execution control in a dynamic environment with stringent temporal constraints is proposed, based on lifted partial order temporal planning techniques which produce flexible plans and allow, under certain conditions discussed in the paper, plan Repair interleaved with plan execution.

KVP: A knowledge of volumes approach to robot task planning

This paper presents a novel “knowledge of volumes” framework for solving generic robot tasks in partially known environments that combines the power of symbolic, knowledge-level AI planning with the efficient computation of volumes, which serve as an intermediate representation for both robot action and perception.

Concurrent planning and execution for autonomous robots

  • R. Simmons
  • Computer Science
    IEEE Control Systems
  • 1992
The use of TCA in a system that walks a legged robot through rugged terrain is described, using TCA features for task sequencing and monitoring to concurrently plan and execute steps.

IDEA: Planning at the Core of Autonomous Reactive Agents

This paper presents IDEA (Intelligent Distributed Execution Architecture) a unified planning and execution framework and is working to fully duplicate the functionalities of the DS1 Remote Agent and extend it to domains of higher complexity than autonomous.

Knowledge-based Specification of Robot Motions

This paper investigates how constraint-based motion representations used in robot control can be combined with a semantic knowledge base in order to let a robot reason about movements and to automatically generate executable motion descriptions that can be adapted to different robots, objects and tools.

A systematic agent framework for situated autonomous systems

This framework manages the information flow within the partitioned structure to ensure consistency in order to direct the flow of goals and observations in a timely manner and promises a domain-independent, scalable and robust approach for control of real-world autonomous robots operating in dynamic environments.

ROS: an open-source Robot Operating System

This paper discusses how ROS relates to existing robot software frameworks, and briefly overview some of the available application software which uses ROS.

COLA2: A Control Architecture for AUVs

The whole architecture has been validated in a cable tracking mission divided in two main phases and has been proved in a realistic simulation of a whole cable tracking MissionCOLA2.

PRS: a high level supervision and control language for autonomous mobile robots

The main reasons why PRS is well suited for this type of application are discussed: the semantics of its plan (procedure) representation, which is important for plan execution and goal refinement, and its ability to construct and act on partial plans.