BPMN to PDDL: Translating Business Workflows for AI Planning

TL;DR

This paper presents a practical system that translates BPMN business process diagrams into PDDL for AI planning, supporting core constructs and enabling execution trace generation.

Contribution

It develops a functional pipeline from BPMN 2.0 to PDDL, supporting key constructs and demonstrating planning-based process simulation.

Findings

Supports core BPMN constructs including tasks and gateways

Enables generation of valid execution traces using AI planning

Bridges the gap between theoretical models and practical tooling

Abstract

Business Process Model and Notation (BPMN) is a widely used standard for modelling business processes. While automated planning has been proposed as a method for simulating and reasoning about BPMN workflows, most implementations remain incomplete or limited in scope. This project builds upon prior theoretical work to develop a functional pipeline that translates BPMN 2.0 diagrams into PDDL representations suitable for planning. The system supports core BPMN constructs, including tasks, events, sequence flows, and gateways, with initial support for parallel and inclusive gateway behaviour. Using a non-deterministic planner, we demonstrate how to generate and evaluate valid execution traces. Our implementation aims to bridge the gap between theory and practical tooling, providing a foundation for further exploration of translating business processes into well-defined plans.