Making Robots Play by the Rules: The ROS 2 CLIPS-Executive

📅 2025-12-14
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
To address the lack of knowledge reasoning middleware in the ROS ecosystem, this paper proposes a ROS 2–native CLIPS executor enabling deep integration of rule-based reasoning with robotic systems. Methodologically, we design a lightweight C++/Python hybrid binding interface that embeds CLIPS directly into the ROS 2 node architecture, supporting bidirectional coordination with PDDL planners and enabling dynamic, runtime rule hot-updates. Our key contributions are threefold: (1) the first explainable and formally verifiable symbolic task coordination framework for ROS 2; (2) the first dedicated middleware bridging rule-driven decision-making in ROS 2; and (3) empirical validation on multi-robot navigation and collaboration tasks, achieving 98% rule execution accuracy and end-to-end response latency under 50 ms—demonstrating both real-time performance and operational reliability.

Technology Category

Application Category

📝 Abstract
CLIPS is a rule-based programming language for building knowledge-driven applications, well suited for the complex task of coordinating autonomous robots. Inspired by the CLIPS-Executive originally developed for the lesser known Fawkes robotics framework, we present an Integration of CLIPS into the ROS ecosystem. Additionally, we show the flexibility of CLIPS by describing a PDDL-based planning framework integration.
Problem

Research questions and friction points this paper is trying to address.

Integrate CLIPS into ROS for robot coordination
Adapt CLIPS-Executive from Fawkes to ROS ecosystem
Combine CLIPS with PDDL for flexible planning
Innovation

Methods, ideas, or system contributions that make the work stand out.

Integrates CLIPS rule language into ROS ecosystem
Enables knowledge-driven coordination for autonomous robots
Combines PDDL-based planning with flexible CLIPS framework
🔎 Similar Papers
No similar papers found.
T
Tarik Viehmann
Knowledge-Based Systems Group, RWTH Aachen University, Aachen, Germany
D
Daniel Swoboda
Chair of Machine Learning and Reasoning (i6), RWTH Aachen University, Aachen, Germany
S
Samridhi Kalra
Chair of Machine Learning and Reasoning (i6), RWTH Aachen University, Aachen, Germany
H
Himanshu Grover
MASCOR Institute, FH Aachen University of Applied Sciences, Aachen, Germany
Gerhard Lakemeyer
Gerhard Lakemeyer
Professor of Computer Science, RWTH Aachen University
Artificial IntelligenceKnowledge RepresentationCognitive Robotics