The DOI matches its Crossref record; 68 of the 68 references it cites were found in a registry or an index; 11 of the 43 sources its claims cite were checked for support.
Automatic design of stigmergy-based behaviours for robot swarms
Open accessAbstract
Stigmergy is a form of indirect communication and coordination in which individuals influence their peers by modifying the environment in various ways, including rearranging objects in space and releasing chemicals. For example, some ant species lay pheromone trails to efficiently navigate between food sources and nests. Besides being used by social animals, stigmergy has also inspired the development of algorithms for combinatorial optimisation and multi-robot systems. In swarm robotics, collective behaviours based on stigmergy have always been designed manually, which is time consuming, costly, hardly repeatable, and depends on the expertise of the designer. Here, we show that stigmergy-based behaviours can be produced via automatic design: an optimisation process based on simulations generates collective behaviours for a group of robots that can lay and sense artificial pheromones. The results of our experiments indicate that the collective behaviours designed automatically are as good as—and in some cases better than—those produced manually. By taking advantage of pheromone-based stigmergy, the automatic design process generated collective behaviours that exhibit spatial organisation, memory, and communication.
Overview
CoChat Summary
TL;DR
Habanero is an automatic off-line AutoMoDe method that designs stigmergy-based collective behaviours for e-puck swarms able to lay and sense artificial pheromone trails. In four missions, its real-robot performance was comparable to or better than manually designed and neuroevolutionary control software, with Habanero outranking all other design methods in aggregate.
Key findings
- Habanero produced effective pheromone-based behaviours across AGGREGATION, DECISION MAKING, RENDEZVOUS POINT, and STOP. A Friedman rank sum test on real-robot performance across the four missions indicated that Habanero outranked all other design methods with at least 95% confidence; Human-Designers performed significantly better than both EvoPheromone and Random-Walk.
- Per-mission real-robot results: in AGGREGATION, Habanero performed significantly better than all other design methods; in RENDEZVOUS POINT, Habanero performed significantly better than all other methods while EvoPheromone performed significantly worse than all others; in STOP, Habanero and Human-Designers performed similarly and significantly better than EvoPheromone; in DECISION MAKING, Habanero correctly selected the blue region in all runs, though real-robot performance was lower than simulation because some robots spilled out of the region.
- The automatically designed behaviours exhibited spatial organisation, external memory, and communication. Pheromone semantics were mission-specific: for example, in STOP the trail meant “stop where you are,” whereas in AGGREGATION it meant “come here.” These properties were not hand-coded in the modules but emerged from how Habanero combined them per mission.
- Habanero and Human-Designers used the same modules but combined them differently: Habanero used Exploration less, relied more on pheromone-reacting modules, used wall-colour modules less, and used the waggle module more than Human-Designers.
Methods
- Habanero is an AutoMoDe instance that assembles seven low-level behaviours and six transition conditions into probabilistic finite-state machines with at most 4 states and at most 4 outgoing transitions per state. It tunes 105 parameters using Iterated F-race in ARGoS3 with the argos3-epuck-phormica library, with a budget of 100,000 simulation runs per design execution.
- The robot platform was an extended e-puck with an Overo Gumstix Linux board, a UV-light module to lay artificial pheromone trails, an omnidirectional camera to detect them, and a ground sensor. The arena floor was coated with photochromic material—acrylic binder with 20% (w/w) photochromic pigments—which turns magenta under UV light and fades back to white in about 50 s; walls were modular RGB blocks, and an overhead tracking camera measured performance only.
- The empirical study used four missions (AGGREGATION, DECISION MAKING, RENDEZVOUS POINT, STOP) with N = 8 robots and T = 180 s. For each mission, 10 instances of control software were produced per method, giving 160 instances total; each was evaluated once in simulation and once with physical robots. Comparisons were Habanero vs. EvoPheromone (neuroevolution: 61 input nodes, 7 output nodes, no hidden layer, 427 real-valued weights), Human-Designers (10 human designers, 4 h per mission), and Random-Walk. Analysis used Wilcoxon paired rank sum tests and a Friedman rank sum test.
Limitations
- The paper states that the study leaves open whether automatic design can leverage pheromone intensity and decay time, since in these experiments a robot either did or did not sense pheromone in a binary fashion. It also leaves open whether automatic methods can select or combine direct and indirect communication.
- The paper states that the photochromic artificial pheromone system is only suitable for indoor applications where the environment can be prepared beforehand, and that no technology currently provides robots with a universally applicable ability to mark their environment. It also states that the experimental setup cannot adequately explain the rationale behind module selection, tuning, and combination, or its relationship to performance, and that the missions are not suitable for drawing conclusions about more complex missions or more complex stigmergy-based interactions.
- Evident from the text: the study is limited to four missions, a swarm of 8 robots, one simulation and one real-robot evaluation per control-software instance, a fixed design budget of 100,000 simulation runs, and comparisons against only EvoPheromone, Human-Designers, and Random-Walk. Real-robot performance was sometimes lower than simulation—for example, in DECISION MAKING—indicating a reality gap.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures






Verification
Claims the paper makes
10 Valid · 3 Not valid · 20 Not checked · 81 Own results and interpretations
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“It has been observed that the control software produced by AutoMoDe crosses the reality gap [44][45][46][47] better than traditional approaches based on neuroevolution 43,48 , in which robots are controlled by a neural network that is optimised using an evolutionary algorithm [49][50][51] .”
§ Automatic design of stigmergy-based behaviours for robot swarms Check for updates > Abstract
What the sources say
- Not checked — no full text of the sourcecites [43] Francesca, G., Brambilla, M., Brutschy, A., Trianni, V. & Birattari, M. AutoMoDe: a novel approach to the automatic design of control software for robot swarms. Swarm Intell. 8, 89–112 (2014). source
- Supportedcites [48] Hasselmann, K., Ligot, A., Ruddick, J. & Birattari, M. Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms. Nat. Commun. 12, 4345 (2021). source
In Results (‘The impact of the reality gap’), Chocolate, an AutoMoDe method, had a smaller performance drop from simulation to real robots than every neuro-evolutionary method tested. The Discussion likewise says Chocolate crossed the reality gap successfully while the neuro-evolutionary methods under analysis did not. The comparison is supported for the methods and missions studied. (LLM, conf=0.92)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“EvoStick is the only neuroevolutionary method that has been tested in the automatic design of robot swarms for several missions, without undergoing any mission-specific modification 48 .”
§ Automatic design of stigmergy-based behaviours for robot swarms Check for updates > Comparisons
What the sources say
- Partly supportedcites [48] Hasselmann, K., Ligot, A., Ruddick, J. & Birattari, M. Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms. Nat. Commun. 12, 4345 (2021). sourceExperimental — accuracy not yet measured
The Methods section says that, to the authors’ knowledge, EvoStick was the only method previously tested on more than one mission without mission-specific modification. The claim omits that qualification and states exclusivity without a time limit. The Results (Experimental setup) also report that this study tested all methods on five missions without such modification. (LLM, conf=0.88)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In the swarm robotics literature, pheromone-based stigmergy has been predominantly designed manually, via trial and error, to address specific missions under specific conditions 26,34,35 .”
§ Automatic design of stigmergy-based behaviours for robot swarms Check for updates > Abstract
What the sources say
- Partly supportedcites [26] Talamali, M. S. et al. Sophisticated collective foraging with minimalist agents: a swarm robotics test. Swarm Intell. 14, 25–56 (2020). sourceExperimental — accuracy not yet measured
Section 2.2 describes several pheromone-based robot designs developed for particular tasks, including area coverage and guidance toward a source. It does not establish that such systems were predominantly designed manually or by trial and error, or that they generally worked only under specific conditions. (LLM, conf=0.76)
- Not checked — no full text of the sourcecites [34] Hamann, H. & Wörn, H. An analytical and spatial model of foraging in a swarm of robots. In Swarm Robotics: Second International Workshop, SAB 2006, vol. 4433 of Lecture Notes in Computer Science, 43–55 (Springer, Berlin, Germany, 2007). source
- Not checked — no full text of the sourcecites [35] Khaliq, A. A. & Saffiotti, A. Stigmergy at work: planning and navigation for a service robot on an RFID floor. In 2015 IEEE International Conference on Robotics and Automation (ICRA), 1085–1092 (IEEE, Piscataway, NJ, USA, 2015). source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“We do not consider more advanced neuroevolutionary methods (e.g., CMA-ES 70 , xNES 71 , and NEAT 72 ) as previous research has shown that they do not provide any performance advantage over EvoStick when applied off the shelf 48 .”
§ Automatic design of stigmergy-based behaviours for robot swarms Check for updates > Comparisons
What the sources say
- Supportedcites [48] Hasselmann, K., Ligot, A., Ruddick, J. & Birattari, M. Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms. Nat. Commun. 12, 4345 (2021). source
The Discussion (page unavailable) says that, on the robot-swarm missions studied, CMA-ES, xNES, and NEAT yielded no relevant improvement over EvoStick in simulation or real-robot experiments. The claim accurately reflects that finding in the context of applying the methods as tested; it should not be read as a conclusion about every possible application. (LLM, conf=0.93)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In all experimental runs, the robot swarm designed by Habanero correctly selected the blue region to congregate.”
§ Automatic design of stigmergy-based behaviours for robot swarms Check for updates > DECISION MAKING
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on 4 assumptions not shown here.
58 more claims
Create a free account to see all 114 claims and every source verdict.
- Probably not a substantial claim. 21
- It may state two separate claims as one. 35
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Automatic design of stigmergy-based behaviours for robot swarms Check for updates > DECISION MAKING
“Halfway through each run of the experiment, the blue and green RGB blocks are switched off”
§ Automatic design of stigmergy-based behaviours for robot swarms Check for updates > Missions
“Both green and blue light signals disappear after a random amount of time, which is uniformly sampled between 70 and 90 s.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Automatic design of stigmergy-based behaviours for robot swarms Check for updates > RENDEZVOUS POINT
“The score is given by the number of robots that, at the end of the experimental run, are positioned in the green region.”
§ Automatic design of stigmergy-based behaviours for robot swarms Check for updates > Missions
“F r ¼ K in À K out ;ð3Þ where K in is the number of robots inside the green region at the end of the mission, and K out is the number of robots outside.”
Citations
Cites
Optimization by Simulated Annealing
Kirkpatrick, S., Gelatt, C. D., & Vecchi, M. P. (1983) · Science · doi:10.1126/science.220.4598.671 · Cited by 45,134 · cited 1×
“Recent studies have shown that other optimisation algorithms are suitable for the AutoMoDe family (e.g., simulated annealing 65 and sequential model-based algorithm con fi guration 66,67 ).”
BackgroundSwarm Intelligence: From Natural to Artificial Systems
Bonabeau, E., Dorigo, M., & Theraulaz, G. (1999) · Oxford University Press eBooks · doi:10.1093/oso/9780195131581.001.0001 · Cited by 6,435
Completely Derandomized Self-Adaptation in Evolution Strategies
Hansen, N., & Ostermeier, A. (2001) · Evolutionary Computation · doi:10.1162/106365601750190398 · Cited by 4,397 · cited 1×
“We do not consider more advanced neuroevolutionary methods (e.g., CMA-ES 70 , xNES 71 , and NEAT 72 ) as previous research has shown that they do not provide any performance advantage over EvoStick when applied off the shelf 48 .”
MethodEvolving Neural Networks through Augmenting Topologies
Stanley, K. O., & Miikkulainen, R. (2002) · Evolutionary Computation · doi:10.1162/106365602320169811 · Cited by 3,258 · cited 1×
“We do not consider more advanced neuroevolutionary methods (e.g., CMA-ES 70 , xNES 71 , and NEAT 72 ) as previous research has shown that they do not provide any performance advantage over EvoStick when applied off the shelf 48 .”
MethodSequential Model-Based Optimization for General Algorithm Configuration
Hutter, F., Hoos, H. H., & Leyton-Brown, K. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-25566-3_40 · Cited by 2,469 · cited 1×
“Recent studies have shown that other optimisation algorithms are suitable for the AutoMoDe family (e.g., simulated annealing 65 and sequential model-based algorithm con fi guration 66,67 ).”
BackgroundSwarm robotics: a review from the swarm engineering perspective
Brambilla, M., Ferrante, E., Birattari, M., & Dorigo, M. (2013) · Swarm Intelligence · doi:10.1007/s11721-012-0075-2 · Cited by 1,762 · cited 1×
“Even without using stigmergy, designing any collective behaviour for a robot swarm is already complex: individuals are autonomous and loosely coupled, and the interactions between individuals and between them and the environment become fully de fi ned only at run time 32,33 .”
MethodSelf-citationThe irace package: Iterated racing for automatic algorithm configuration
López-Ibáñez, M., Dubois-Lacoste, J., Pérez Cáceres, L., Birattari, M., & Stützle, T. (2016) · Operations Research Perspectives · doi:10.1016/j.orp.2016.09.002 · Cited by 1,761
Self-citationGrassé, P.-P. (1959) · Insectes Sociaux · doi:10.1007/bf02223791 · Cited by 1,236
Swarm Robotics: From Sources of Inspiration to Domains of Application
Şahin, E. (2005) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-30552-1_2 · Cited by 951 · cited 1×
“In a robot swarm, which operates similarly to a colony of social insects 11 , a collective behaviour emerges due to local interactions between individual robots and between the robots and the environment 12 .”
BackgroundSelf-organized shortcuts in the Argentine ant
Goss, S., Aron, S., Deneubourg, J. L., & Pasteels, J. M. (1989) · Naturwissenschaften · doi:10.1007/bf00462870 · Cited by 919 · cited 9×
“6 and Supplementary Video 1.”
BackgroundMethodInfluential
Research works printed but not linked: 5
- Wilson, E. O. Sociobiology: The New Synthesis. (Harvard University Press, Cambridge, MA, USA, 1975).
- Goss, S., Deneubourg, J.-L., Bourgine, P. & Varela, E. Harvesting by a group of robots. In Toward a Practice of Autonomous Systems, Proceedings of the First European Conference on Artificial Life, Complex adaptive systems, 195–2054 (MIT Press, Cambridge, MA, USA, 1992).
- Brooks, R. A. Artificial life and real robots. In Varela, F. J. & Bourgine, P. (eds.) Towards a Practice of Autonomous Systems: Proceedings of the First European Conference on Artificial Life, 3–10 (MIT Press, Cambridge, MA, USA, 1992).
- Kuckling, J. Optimization in the automatic modular design ofcontrol software for robot swarms. (Ph.D. thesis, Université libre de Bruxelles, Brussels, Belgium 2023).
- Chambers, J. M., Cleveland, W. S., Kleiner, B. & Tukey, P. A. Graphical Methods For Data Analysis. (CRC Press, Belmont, CA, USA, 1983).
Cited by
Robo-Matter towards reconfigurable multifunctional smart materials
Wang, J., Gao, W., Chen, H., Liu, Y., Wang, P., Yuan, D., Ma, X., Xu, X., Cheng, Z., Ji, B., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-53123-6 · Cited by 37
“Regulation of robot swarms via environmental cues, e.g., indirect information transduction in the stigmergic systems 43,44 hasalsobeenexplored.”
BackgroundSelf-organizing nervous systems for robot swarms
Zhu, W., Oğuz, S., Heinrich, M. K., Allwright, M., Wahby, M., Christensen, A. L., Garone, E., & Dorigo, M. (2024) · Science Robotics · doi:10.1126/scirobotics.adl5161 · Cited by 43
Towards applied swarm robotics: current limitations and enablers
Kegeleirs, M., & Birattari, M. (2025) · Frontiers in Robotics and AI · doi:10.3389/frobt.2025.1607978 · Cited by 33
Self-citationHeterogeneous foraging swarms can be better
Kaminka, G. A., & Douchan, Y. (2025) · Frontiers in Robotics and AI · doi:10.3389/frobt.2024.1426282 · Cited by 13
Thang, D. V., Volkov, A., Muthanna, A., Koucheryavy, A., Ateya, A. A., & Jayakody, D. N. K. (2025) · Sensors · doi:10.3390/s25113488 · Cited by 7
“Pheromones are already used to transmit information, but their reception so far could only be carried out by living organisms [45].”
Metadata
- Authors
- Salman, M., Garzón Ramos, D., & Birattari, M.
- Affiliations
- Université Libre de Bruxelles (BE)
- Corresponding author
- Birattari, Mauro
- Venue
- Communications Engineering
- Published
- 2024-02-14
- Volume
- 3
- Issue
- 1
- ISSN
- 2731-3395 (ISSN-L)
- PMC
- PMC10956014
- OpenAlex
- W4391808535
- Cited by
- 26
- References
- 66
- Citations by year
- 2026: 8 · 2025: 9 · 2024: 9
- FWCI
- 3.48
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Communications Engineering (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- Dépôt institutionnel de l'Université libre de Bruxelles (Université Libre de Bruxelles) (submittedVersion, other-oa)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- EC | Horizon 2020 Framework Programme (681872)
- Topics
- Physical Sciences › Engineering › Mechanical Engineering › Modular Robots and Swarm Intelligence
- Physical Sciences › Computer Science › Artificial Intelligence › Metaheuristic Optimization Algorithms Research
- Physical Sciences › Engineering › Control and Systems Engineering › Distributed Control Multi-Agent Systems
- Keywords
- stigmergy, swarm robotics, artificial pheromone, collective behavior, multi-robot systems, combinatorial optimization, spatial organization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-01, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-01 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Automatic design of stigmergy-based behaviours for robot swarms. https://app.cochat.ai/papers/10.1038/s44172-024-00175-7
- The paper
- Salman, M., Garzón Ramos, D., & Birattari, M. (2024). Automatic design of stigmergy-based behaviours for robot swarms. Communications Engineering. https://doi.org/10.1038/s44172-024-00175-7
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.