The website has been updated for the 2024 round of the competition (for important dates, see Submission).
Student participant with Master’s thesis in the context of the AbstractSwarm competition has been awarded, see press release of TH Bingen.
The evaluation of the 2023 round including agent implementations is available. See Roundup 2023.
A long-term goal of Artificial Intelligence (AI) research is the development of “general” intelligence which is able to solve a broad variety of different problems. To further approach this extensive goal, problem scenarios from the broad field of logistics seem to serve as eligible test environments, that can be extremely diverse, highly dynamic and variable of size. Furthermore, many logistics-related problems (e. g., in hospital logistics) have a good accessibility and are easy to comprehend, but hard to solve.
The main goal of the competition is to stimulate AI/CI research in the context of multi-agent and swarm systems as cooperative problem solvers for a priori unknown problems, with a focus on logistics—especially for hospital process optimization in medical informatics.
For this purpose, the AbstractSwarm simulation system will be used, further developed at the Medical Informatics department of the Institute of Medical Biostatistics, Epidemiology and Informatics (IMBEI) at the University Medical Center of the Johannes Gutenberg University Mainz, Germany.
The AbstractSwarm Multi-Agent Logistics Competition calls for applying results from AI/CI, multi-agent/swarm systems and related research to logistics, especially focusing on the cooperativity of agents.
This is the fourth round of the competition, which runs at GECCO 2024, to be held in July. The announcement of the winners as well as all other results is planned to be presented both at GECCO 2024 (exact time and date to be announced).
In the AbstractSwarm Multi-Agent Logistics Competition, participants must develop agents that are able to cooperatively solve different smaller a priori unknown logistics problems. A logistics problem is given as a graph containing agents (round components) and stations (squared components). Agents have to visit their connected stations at the right time to prevent other agents from having idle time. An agent can interact with the graph
Presentation Video of the Competition Shown at GECCO 2023)
Tutorial 1: Core Ideas, Loading & Running Scenarios
Tutorial 2: How to Create Agents
Tutorial 3: Running Simulations from the Command Line
Several small episodic example scenarios of different (simplified) logistics and related problems are provided here for download, which you can load using the AbstractSwarm system for testing or training your agents.
Treatments | Ten patients have to get three different treatments each. The treatment locations have different amounts of space and have a distance of five units to each other. Spatio-temporal scheduling problem. | |
Ward Round | A doctor has to do a ward round to visit four patient rooms in a hallway. A nurse has to do some office work, but must be available every time the doctor visits a room. Spatio-temporal coordination problem with only two agents. | |
X-Ray Scheduling | Twenty patients that have to be x-rayed must be distributed to three x-ray stations. Multi-agent scheduling problem. | |
X-Ray Scheduling 2 | Same as X-Ray Scheduling with distances among the three x-ray stations being additionally modeled. Multi-agent scheduling problem with spatial dependencies. | |
Crossroads | Trucks on two different roads (a slow one and a fast one) have to get from a starting point to a destination. The roads are crossing in the middle, where an agent has to control the traffic lights to optimize the traffic flow (colored in green). Traffic flow control problem with directed spatial dependencies and a cell-based character (where stations represent the cells of the roads). | |
Storage | The best way of storing ten products in three shelves of a linearly organized storehouse must be found here (where the products are represented by agents). The solution is obviously to store all ten products in the first shelf (colored in yellow), since it is located at the entrance of the storehouse and thus distances for storing can be minimized. Storage problem with sparse rewards (agents only receive better rewards if all agents decide to avoid one of the shelves located in the back). | |
Delivery | Three deliverers must coordinate each other to provide one delivery for each of the six customers in a district. The delivers start at the bottom left customer (colored in white). Multi-agent delivery problem. |
Please submit your agent implementation by email to apeldoorn@uni-mainz.de, either as a zipped attachment or by providing a link to the corresponding .zip file in your repository, not later than:
31st of May, 2024
The .zip file should contain the complete agent implementation folder, including the AbstractSwarmAgentInterface.java file together with all other needed files (further .java files, .jar files of needed external libraries, files to be loaded, and the like).
Optionally, you can also submit a competition entry describing your agent implementation (max. two pages) to the GECCO 2024 conference, not later than:
8th of April, 2024
For details see the GECCO 2024 call for competition entries and the submission site.
There also a preview of the submission form available.
All accepted competition entries will be published together with the GECCO 2024 proceedings.
Please note:
"As a published ACM author, you and your co-authors are subject to all ACM Publications Policies (https://www.acm.org/publications/policies/toc), including ACM's new Publications Policy on Research Involving Human Participants and Subjects (https://www.acm.org/publications/policies/research-involving-human-participants-and-subjects)."
A certificate will be provided to the winner(s) of the competition.
If you consider submitting a competition entry or full paper related to the AbstractSwarm Multi-Agent Logistics Competition, you can cite AbstractSwarm as follows:
Apeldoorn, D.: AbstractSwarm – A Generic Graphical Modeling Language for Multi-Agent Systems. In: Klusch, M., Thimm, M., Paprzycki, M. (eds.) Multiagent System Technologies. LNCS, vol. 8076, pp. 180–192. Springer, Berlin Heidelberg, 2013.
and/or refer to this website.
Apeldoorn, Daan (University Medical Center of the Johannes Gutenberg University Mainz, IMBEI Medical Informatics)
Dockhorn, Alexander (Leibniz Universität Hannover)
Panholzer, Torsten (University Medical Center of the Johannes Gutenberg University Mainz, IMBEI Medical Informatics)
If you have further questions, please contact the competition organizers through their websites (see Organizers).
The set of scenarios used for the evaluation of this year's round is available from the following link:
Evaluation Scenarios Set 2023
The set consists of ten diverse scenarios that comprise
Agent Name | Submitting Developer/Team | Score (Area) | Rank 2023 | Download |
AgentLearning | Elisa Schmid (Leibniz University Hannover) | ≈ 29.73 | None (best from 2022) | AgentLearning.zip |
OSGKIAGMetaLearnerBFR | Bronston Brown, Felix Schmitt, Rémi Dima (Otto-Schott-Gymnasium Mainz) | ≈ 30.7 | 1 | OSG_KIAGMetaLearnerBFR.zip |
OSGKIAG-ABMetaLearner01 | Leonard Halstenberg, Emanuel Mindrescu (Otto-Schott-Gymnasium Mainz) | ≈ 31.49 | 2 | OSGKIAG-ABMetaLearner01.zip |
AgentMetaLearner | Jan Mühlstein, Muhammed Ocakbegi (Otto-Schott-Gymnasium Mainz) | ≈ 31.53 | 3 | AgentMetaLearner.zip |
OSGKIAG-ABMetaLearner07 | Leonard Halstenberg, Emanuel Mindrescu (Otto-Schott-Gymnasium Mainz) | ≈ 32.47 | 4 | OSGKIAG-ABMetaLearner07.zip |
AgentReaves | Athar Adel (Frankfurt University of Applied Sciences) | ≈ 36.68 | 5 | AgentReaves.zip |
AgentBardV2 | Athar Adel (Frankfurt University of Applied Sciences) | ≈ 37.98 | 6 | AgentBardV2.zip |
AgentRonaldoReward | Athar Adel (Frankfurt University of Applied Sciences) | ≈ 39.84 | 7 | AgentRonaldoReward.zip |
AgentColemanSum | Athar Adel (Frankfurt University of Applied Sciences) | ≈ 44.57 | 8 | AgentColemanSum.zip |
AgentMinDistanceMaxSpace | SM Mehedi Hasan (Frankfurt University of Applied Sciences) | ≈ 45.48 | 9 | AgentMinDistanceMaxSpace.zip |
AgentRandom | (shipped with framework) | ≈ 46.9 | None (baseline agent) | AgentRandom.zip |
The set of scenarios used for the evaluation of this year's round is available from the following link:
Evaluation Scenarios Set 2022
The set consists of ten diverse scenarios that comprise
Agent Name | Submitting Developer/Team | Score (Area) | Rank 2022 | Download |
AgentLearning | Elisa Schmid (Leibniz University Hannover) | ≈ 23.63 | None (late submission) | AgentLearning.zip |
AgentProb | Elisa Schmid (Leibniz University Hannover) | ≈ 25.53 | None (late submission) | AgentProb.zip |
AgentPlace | Elisa Schmid (Leibniz University Hannover) | ≈ 30.81 | 1 | AgentPlace.zip |
Agent_PW_QPlusQueue | Patrick Winkel (Bingen Technical University of Applied Sciences) | ≈ 34.26 | 2 | AgentPWQPlusQueue.zip |
Agent_PW_QPlusSOM | Patrick Winkel (Bingen Technical University of Applied Sciences) | ≈ 34.98 | 3 | AgentPWQPlusSOM.zip |
AgentReactiveMinDistance | (shipped with framework) | ≈ 38.55 | None (baseline agent) | AgentReactiveMinDistance.zip |
AgentReactiveMaxFreeSpace | (shipped with framework) | ≈ 47.33 | None (baseline agent) | AgentReactiveMaxFreeSpace.zip |
OSG_KIAGLearningAgent | Frederic (Otto-Schott-Gymnasium Mainz), Karolina (Otto-Schott-Gymnasium Mainz), Alexander (Otto-Schott-Gymnasium Mainz), Philipp (Otto-Schott-Gymnasium Mainz) |
≈ 49.49 | 4 | OSGKIAGLearningAgent.zip |
AgentRandom | (shipped with framework) | ≈ 50.29 | None (baseline agent) | AgentRandom.zip |
OSG_KIAG_RuleAgent | Hendrik Hofmann (Otto-Schott-Gymnasium Mainz), Julius Buchold (Otto-Schott-Gymnasium Mainz), Ferdinand (Otto-Schott-Gymnasium Mainz) |
≈ 50.76 | 5 | OSGKIAGRuleAgent.zip |