Knowledge Engineering for Planning and Scheduling

KEPS 2026

Workshop at the 36th International Conference on Automated Planning and Scheduling (ICAPS)

Room 9 at Clayton Hotel Burlington Road, Dublin, Ireland

9:00 a.m. - 5:30 p.m., June 28th 2026

Important Dates

The reference timezone for all deadlines is UTC-12. That is, as long as there is still some place anywhere in the world where the deadline has not yet passed, you are on time!

Workshop acceptance

March 10th, 2026

Call for Papers announcement

March 17th, 2026

Paper submission deadline

April 16th, 2026
April 24th, 2026

Notification of acceptance

May 20th, 2026

Call for Papers

Despite the progress in automated planning and scheduling systems, these systems still need to be fed by carefully engineered domain and problem descriptions and they need to be fine-tuned for particular domains and problems. Knowledge engineering for AI planning and scheduling deals with the acquisition, design, validation, and maintenance of domain models, as well as the selection and optimization of appropriate machinery to work on them. These processes directly influence the success of real-world planning and scheduling applications. The importance of knowledge engineering techniques is clearly demonstrated by the performance gap between domain-independent planners and planners that exploit domain-specific knowledge.

This workshop continues the tradition of several International Competitions on Knowledge Engineering for Planning and Scheduling (ICKEPS) and previous KEPS workshops. While ICKEPS primarily focuses on software tools and domain encoding techniques, this workshop covers all aspects of knowledge engineering for AI planning and scheduling.

Topics of Interest

Formulation of domains and problem descriptions
Methods and tools for acquiring domain knowledge
Pre- and post-processing techniques for planners and schedulers
Acquisition and refinement of control knowledge
Formal languages for describing domains
Re-use of domain knowledge
Translators from domain-specific languages to solver-ready models (e.g., PDDL)
Formats for the specification of heuristics, parameters and control knowledge for solvers
Import of domain knowledge from general ontologies
Ontologies describing planner and scheduler capabilities
Automated reformulation of planning problems
Automated knowledge extraction processes
Domain model, problem, and plan validation
Visualization methods for domain models, search spaces and plans
Mapping domain properties and planning techniques
Plan representation and reuse
Knowledge engineering aspects of plan analysis

Submission Instructions

Two types of papers can be submitted. Full technical papers with the length up to 8 pages + 1 for references, are standard research papers. Short papers with the length between 2 and 4 pages (+1 for references) describe either a particular application or focus on open challenges. All papers must be submitted in PDF format and must conform to the AAAI style template.

Policy on Previously Published Papers: we welcome submissions based on recent publications from other (non-ICAPS) venues such as specialized conferences (e.g., AAMAS, ICRA, KR) or general AI conferences (e.g., AAAI, IJCAI, ECAI). Such submissions must clearly indicate the original venue. Submissions currently under review elsewhere are also welcome since the workshop is a non-archival venue. No copyright transfer is required. If the paper is under double-blind review at another venue, please anonymize the submission.

Schedule

Workshop Introduction

09:00 – 09:10

Session 1 · Knowledge Acquisition & Domain Learning

09:10 – 10:30

  • Are We There Yet? Bridging the Knowledge Acquisition Gap in Automated Planning

    Roman Barták, Lukáš Chrpa, Simona Ondrčková, Kristýna Pantůčková

  • Automatically Uncovering Intended Domain Constraints in Automated Planning

    Elliot Gestrin, Johannes Fichte, Jendrik Seipp

  • Predicting Macro-Learning Performance Using Structural Regularity

    Anton Gustafsson, Jendrik Seipp, Elliot Gestrin

  • JUS: Extending SIFT to Learn Planning Domains from Justified Plans

    Alexander Lodemann, Michael Ventura, Gregor Behnke, Birte Glimm

  • On the Use of Large Language Models as Domain Model Configurators

    Ilche Georgievski, Daniel Elis, Mauro Vallati

  • Offline Learning of Planning Domains with Subsymbolic Predicates Invention

    Leonardo Lamanna

Coffee Break

10:30 – 10:50

Session 2 · Classical, Numeric & Uncertain Planning

10:50 – 12:30

  • Planning while Learning with Anytime Sound and Complete Models

    Pablo Copete, Diego Aineto, Eva Onaindia, Enrico Scala

  • Planning with Uncertain Action Models

    Francesco Percassi, Alessandro Saetti, Enrico Scala

  • Automated Planning with Incomplete Open World Models

    Mikhail Soutchanski

  • Configuring Lifted Initial States for Classical Planning

    Alba Gragera, Raquel Fuentetaja, Ángel García-Olaya

  • Incremental Planning over Lifted Abstractions

    Michelle Kornherr, Daniel Gnad, Zeynep G. Saribatur, Johannes K. Fichte

  • Planning Task Shielding: Detecting and Repairing Flaws in Planning Tasks through Turning them Unsolvable

    Alberto Pozanco, Marianela Morales, Pietro Totis, Daniel Borrajo

  • Optimal Parity Resolution in Difference Models via Numeric Planning

    Luigi Bonassi, James Wilson, Ruth Chang, Kit Fine, Nick Hawes

Lunch Break

13:00 – 14:30

Session 3 · Scheduling & Planning Applications

14:30 – 16:00

  • Extracting Structural Knowledge from Precedence-Induced Betweenness Patterns in Scheduling Problem

    Isabel Català, Christian Pérez, Miguel A. Salido

  • The Role of Knowledge Engineering within a Fielded Planning Application

    Lee McCluskey, Alan Lindsay, Mauro Vallati, Keith McCabe

  • Distribution Network Transition Problem: A Planning Knowledge Model Capturing Structural Constraints

    Francesco Percassi, Sandra Castellanos-Paez, Mauro Vallati, Marie-Cécile Alvarez-Hérault

  • On the Use of AI Planning for Water Management of the Red River Basin in Vietnam

    Diego Aineto, Nicola Bettinzoli, Ngo Le An, Enrico Scala, Ivan Serina

  • Semantic Mediation: An LLM-Based Approach for Ground Truth in Human-in-the-Loop Automated Planning in Supply Chain Network

    Ryan Farish, Ron Petrick

  • Modeling Challenges in Procedure Synthesis for Earth Independent Anomaly Response

    J. Benton, Irina Kostitsyna, Richard Levinson, Alison Paredes

  • Medical Procedure Tracking using Abductive Planning — A PARADIGM Shift

    Michael Wessel, Michael Cogswell, Jason Tyan, Bob Price

Coffee Break

16:00 – 16:20

Session 4 · Robotics & Multi-agent Planning

16:20 – 17:30

  • When Can Planning Benefit from Common-Sense Knowledge?

    Ma'Ayan Armony, Albert Meroño-Peñuela, Gerard Canal

  • Dynamic Scene Reconstruction for Planning Environments

    Albaraa Othman, Prab Singh, Emanuele De Pellegrin, Maria Koskinopoulou, Ron Petrick

  • OOMPA 2025.08: A First Cut of the Toolkit for Object-Oriented Modeling for Planning and Acting

    Mark Roberts, David Chan, Dana Nau, Jamie Macbeth

  • Structuring World State Knowledge for Multi-UAV Automated Planning

    Kai Sommer, Jean Jane Kiam

  • maPO: An Ontology for Multi-Agent Path Finding and Its Usage for Explaining Planner Behaviour

    Bharath Muppasani, Ritirupa Dey, Biplav Srivastava, Vignesh Narayanan

Closing

17:25 – 17:30

Organizing Committee

Lukáš Chrpa

Czech Technical University

Lukas Chrpa

Leonardo Lamanna

Fondazione Bruno Kessler

Leonardo Lamanna

Ron Petrick

Heriot-Watt University

Ron Petrick

Mauro Vallati

University of Huddersfield

Mauro Vallati

Tiago Vaquero

NASA JPL, Caltech

Tiago Vaquero

Program Committee

Diego Aineto

Universitat Politècnica de València

Roman Barták

Charles University

Luigi Bonassi

University of Oxford

Matteo Cardellini

Università degli Studi di Genova

Sandra Castellanos-Paez

Grenoble Computer Science Laboratory, Université Grenoble Alpes

Lukáš Chrpa

Czech Technical University in Prague

Emanuele De Pellegrin

University of Edinburgh

Susana Fernandez

Universidad Carlos III de Madrid

Mary Ellen Foster

University of Glasgow

Jeremy Frank

NASA

Richard Freedman

Smart Information Flow Technologies, LLC

Raquel Fuentetaja

Universidad Carlos III de Madrid

Alba Gragera

Universidad Carlos III de Madrid

Lorenzo James

IESEG School of Management

Alessandro La Farciola

Fondazione Bruno Kessler

Leonardo Lamanna

Fondazione Bruno Kessler

Lee McCluskey

University of Huddersfield

Eva Onaindia

Universitat Politècnica de València

Andrea Orlandini

CNR

Simon Parkinson

University of Huddersfield

Francesco Percassi

University of Huddersfield

Ron Petrick

Heriot-Watt University

David Smith

Independent

Roni Stern

Ben Gurion University of the Negev

Elisa Tosello

Fondazione Bruno Kessler

Mauro Vallati

University of Huddersfield

Tiago Vaquero

NASA Jet Propulsion Laboratory, Caltech