pith. sign in

arxiv: 2605.16115 · v1 · pith:KXAHDRQDnew · submitted 2026-05-15 · 💻 cs.RO

Beyond Collision Avoidance: Multi-Robot Yielding and Spatial Affordance in Emergency Evacuations

Ning Zhou , Edmund R. Hunt , Nikolai W.F. Bode This is my paper

Pith reviewed 2026-05-20 17:57 UTC · model grok-4.3

classification 💻 cs.RO
keywords multi-robot systemsyielding strategiesemergency evacuationspatial affordanceshuman-robot interactioncollision avoidancepsychological responsesrefuge niches
0
0 comments X

The pith

In confined emergencies, robots that hide in refuge niches to yield space are preferred by people over those that freeze or optimize for shortest paths.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper investigates how multi-robot systems should behave during emergency evacuations in confined spaces to ensure they are not only collision-free but also psychologically comfortable for humans. Through a virtual game experiment with 56 participants, it tests four yielding strategies and finds a clear preference order where actively using niches to get out of the way ranks highest. This matters because as service robots become common, their behavior in high-stress situations must match human expectations shaped by the environment to prevent discomfort or delays in perception. The findings show that environmental affordances like niches can enhance the benefits of good yielding or lead to violations if ignored.

Core claim

Our results establish a robust preference hierarchy (Hide > LineEscape > Freeze > ShortestPath), demonstrating that proactive space-yielding significantly outperforms freezing and efficiency-first approaches. Crucially, we found that environmental affordances heavily shape cognitive expectations. Actively utilising available niches amplifies the psychological comfort of proactive yielding (Hide). Conversely, failing to use an obvious niche (e.g., executing LineEscape) may trigger Expectation Violation. This is reflected in a drastically increased perceived cognitive delay, despite objectively unimpeded trajectories.

What carries the argument

The preference hierarchy among four yielding strategies (Hide, LineEscape, Freeze, ShortestPath) evaluated in corridors with and without refuge niches, showing how these strategies interact with human spatial expectations and affordances.

If this is right

  • Proactive yielding that uses available environmental features leads to greater human comfort than simply stopping or choosing efficient paths.
  • Failure to utilize obvious refuge spaces can increase perceived delays even when actual movement is not blocked.
  • Experience with robots improves the ability to interpret their social intentions during emergencies.
  • Safe human-robot interaction in crises requires navigation that is aware of semantic and environmental context beyond basic trajectory planning.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Robot path planning systems could incorporate models of human expectations about space usage in different environments to improve acceptance.
  • Testing these strategies in physical settings with real robots and larger groups could reveal how group dynamics affect the observed preferences.
  • Designing robots to detect and use affordances like niches might reduce the need for explicit communication of intent.

Load-bearing premise

Responses from participants in a game-based virtual evacuation accurately reflect how people would react to real robots in actual physical emergency situations.

What would settle it

Conducting the same experiment with physical robots in a real corridor and finding that participants rate Freeze or ShortestPath higher than Hide would falsify the preference hierarchy.

Figures

Figures reproduced from arXiv: 2605.16115 by Edmund R. Hunt, Nikolai W.F. Bode, Ning Zhou.

Figure 1
Figure 1. Figure 1: Schematic of the evaluated multi-robot navigation strategies. [PITH_FULL_IMAGE:figures/full_fig_p006_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: First-person perspective of the virtual evacuation simulation pipeline (left) [PITH_FULL_IMAGE:figures/full_fig_p007_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Subjective evaluation scores (Q1-Q8) and average strategy rankings across [PITH_FULL_IMAGE:figures/full_fig_p009_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Distribution of participants’ explicit preference rankings (1 = Best, 4 = [PITH_FULL_IMAGE:figures/full_fig_p010_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Movement paths of all 28 human participants (blue lines) and the robots [PITH_FULL_IMAGE:figures/full_fig_p010_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Radar charts comparing nine objective spatial-temporal trajectory met [PITH_FULL_IMAGE:figures/full_fig_p011_6.png] view at source ↗
read the original abstract

As mobile service robots increasingly coexist with pedestrians, ensuring passively safe behaviour during confined emergency evacuations is critical. Existing multi-robot yielding strategies often focus solely on collision avoidance and macroscopic flow optimisation, overlooking environmental affordances and human spatial expectations. To bridge the gap between macroscopic theory and micro-level perception, we conducted a game-based virtual evacuation experiment (N=56). We investigated individual psychological responses to four multi-robot yielding strategies (Hide, LineEscape, Freeze, ShortestPath) across confined corridors with and without refuge niches. Our results establish a robust preference hierarchy (Hide > LineEscape > Freeze > ShortestPath), demonstrating that proactive space-yielding significantly outperforms freezing and efficiency-first approaches. Crucially, we found that environmental affordances heavily shape cognitive expectations. Actively utilising available niches amplifies the psychological comfort of proactive yielding (Hide). Conversely, failing to use an obvious niche (e.g., executing LineEscape) may trigger Expectation Violation. This is reflected in a drastically increased perceived cognitive delay, despite objectively unimpeded trajectories. Furthermore, prior robot interaction experience helps users decode complex social intents. Ultimately, this research demonstrates that safe human-robot interaction during emergencies must evolve from pure trajectory optimisation to semantically aware navigation. Future work will extend this framework to investigate complex interactions between robot swarms and pedestrian crowds.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript reports results from a game-based virtual evacuation experiment (N=56) comparing four multi-robot yielding strategies—Hide, LineEscape, Freeze, and ShortestPath—in confined corridors with and without refuge niches. It claims a clear preference hierarchy (Hide > LineEscape > Freeze > ShortestPath), that proactive yielding outperforms freezing and efficiency-focused approaches, and that environmental affordances shape cognitive expectations, with niche utilization amplifying comfort and unused niches triggering expectation violations that increase perceived cognitive delay despite clear paths. Prior robot experience is noted as aiding intent decoding, with the work advocating a shift from trajectory optimization to semantically aware navigation.

Significance. If the empirical hierarchy and affordance effects hold under more realistic conditions, the work would meaningfully advance HRI by showing how spatial niches and proactive yielding can reduce cognitive load in emergencies beyond standard collision avoidance. The virtual experiment supplies concrete preference data that could guide robot behavior design, though its contribution is tempered by the lack of physical validation.

major comments (2)
  1. [Abstract / Results] Abstract and results description: the stated 'robust preference hierarchy' from the N=56 experiment is asserted without any reported statistical tests, p-values, effect sizes, confidence intervals, or analysis of variance across the with/without-niche conditions, leaving the ordering's reliability and the claim of 'significantly outperforms' unsupported by the provided information.
  2. [Discussion / Limitations] The central claim that the observed hierarchy and niche effects apply to real multi-robot yielding in physical emergency evacuations rests on untested generalization from the virtual game setting; no discussion of ecological validity, physical risk, embodied robot presence, or time pressure appears, which directly affects whether the preference ordering and expectation-violation findings transfer.
minor comments (2)
  1. [Methods] Clarify the exact questionnaire items or scales used to measure 'perceived cognitive delay' and 'psychological comfort' so readers can assess how these map to the reported hierarchy.
  2. [Methods] Expand the description of participant demographics, recruitment, exclusion criteria, and how prior robot interaction experience was quantified and analyzed.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive and detailed feedback, which has prompted us to strengthen the statistical reporting and limitations discussion in the manuscript. We address each major comment below.

read point-by-point responses

  1. Referee: [Abstract / Results] Abstract and results description: the stated 'robust preference hierarchy' from the N=56 experiment is asserted without any reported statistical tests, p-values, effect sizes, confidence intervals, or analysis of variance across the with/without-niche conditions, leaving the ordering's reliability and the claim of 'significantly outperforms' unsupported by the provided information.

    Authors: We appreciate the referee drawing attention to the need for explicit statistical support. The hierarchy reflects aggregated participant preference rankings from the N=56 sample, with the Hide strategy receiving the highest ratings in niche-present conditions. We agree that formal tests are required to substantiate claims of robustness and significant outperformance. In the revised manuscript we have added a repeated-measures ANOVA, pairwise post-hoc comparisons with Bonferroni correction, p-values, partial eta-squared effect sizes, and 95% confidence intervals for the key contrasts between strategies and across niche conditions. These analyses confirm the statistical reliability of the reported ordering. The abstract has been updated to reference the statistical evidence. revision: yes

  2. Referee: [Discussion / Limitations] The central claim that the observed hierarchy and niche effects apply to real multi-robot yielding in physical emergency evacuations rests on untested generalization from the virtual game setting; no discussion of ecological validity, physical risk, embodied robot presence, or time pressure appears, which directly affects whether the preference ordering and expectation-violation findings transfer.

    Authors: We concur that the manuscript would benefit from a more explicit treatment of ecological validity. Although the study is framed as a virtual experiment and future physical work is mentioned, we acknowledge that dedicated discussion of physical risk, embodied robot presence, and real-world time pressure was limited. The revised Discussion and Limitations sections now include a dedicated paragraph addressing these factors: we note that the absence of physical danger may reduce perceived urgency relative to actual evacuations, that screen-based interaction differs from embodied co-presence, and that the observed expectation-violation effects could be amplified or attenuated under genuine time pressure. We retain the position that the virtual results supply actionable design insights while clearly bounding their generalizability, and we outline concrete steps for physical validation in future studies. revision: yes

Circularity Check

0 steps flagged

No circularity; central claims derived from new empirical experiment data

full rationale

The paper's core results—a preference hierarchy among yielding strategies and the role of environmental affordances—are obtained directly from a newly conducted game-based virtual evacuation experiment with N=56 participants. No mathematical derivations, fitted parameters, self-citations, or ansatzes are invoked to generate these findings; the claims rest on participant responses collected for this study. This constitutes an independent empirical benchmark external to any prior author work or internal definitions, satisfying the criteria for a self-contained analysis with score 0.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claims depend on the validity of mapping virtual responses to real emergency behavior and on standard assumptions in human-robot interaction studies about participant interpretation of robot intent.

axioms (1)
  • domain assumption Virtual game-based experiments elicit psychological responses representative of real emergency situations
    The study design relies on this to interpret the N=56 preference data as relevant to physical evacuations.

pith-pipeline@v0.9.0 · 5772 in / 1218 out tokens · 88674 ms · 2026-05-20T17:57:55.299155+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

35 extracted references · 35 canonical work pages

  1. [1]

    Applied Sciences14(1), 89 (2023)

    Alqobali, R., Alshmrani, M., Alnasser, R., Rashidi, A., Alhmiedat, T., Alia, O.M.: A survey on robot semantic navigation systems for indoor environments. Applied Sciences14(1), 89 (2023). https://doi.org/doi.org/10.3390/app14010089

    work page doi:10.3390/app14010089 2023

  2. [2]

    In: 2021 30th IEEE In- ternational Conference on Robot & Human Interactive Communication (RO-MAN)

    Asavanant, C., Umemuro, H.: Personal space violation by a robot: An application of expectation violation theory in human-robot interaction. In: 2021 30th IEEE In- ternational Conference on Robot & Human Interactive Communication (RO-MAN). pp. 1181–1188. IEEE (2021). https://doi.org/10.1109/ro-man50785.2021.9515472

    work page doi:10.1109/ro-man50785.2021.9515472 2021

  3. [3]

    Thermal effects and their compen- sation in advanced virgo.Journal of Physics: Confer- ence Series, 363:012016, jun 2012

    Bahamid, A., Ibrahim, A.M., Ibrahim, A., Zahurin, I.Z., Wahid, A.N.: Intelli- gent robot-assisted evacuation: A review. In: Journal of Physics: Conference Se- ries. vol. 1706, p. 012159. IOP Publishing (2020). https://doi.org/10.1088/1742- 6596/1706/1/012159

    work page doi:10.1088/1742- 2020

  4. [4]

    Measurement instruments for the anthro- pomorphism, animacy, likeability, perceived intelligence, and perceived safety of robots

    Bartneck, C., Kulić, D., Croft, E., Zoghbi, S.: Measurement instruments for the anthropomorphism, animacy, likeability, perceived intelligence, and perceived safety of robots. International Journal of Social Robotics1(1), 71–81 (2009). https://doi.org/10.1007/s12369-008-0001-3

    work page doi:10.1007/s12369-008-0001-3 2009

  5. [5]

    In: 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

    Bera, A., Randhavane, T., Prinja, R., Manocha, D.: Sociosense: Robot navigation amongst pedestrians with social and psychological constraints. In: 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 7018–7025. IEEE (2017). https://doi.org/10.1109/IROS.2017.8206628 Beyond Collision Avoidance: Multi-Robot Emergency Evacuatio...

    work page doi:10.1109/iros.2017.8206628 2017

  6. [6]

    Journal of Language and Social Psychology12(1-2), 30–48 (Mar 1993)

    Burgoon, J.K.: Interpersonal Expectations, Expectancy Violations, and Emotional Communication. Journal of Language and Social Psychology12(1-2), 30–48 (Mar 1993). https://doi.org/10.1177/0261927X93121003

    work page doi:10.1177/0261927x93121003 1993

  7. [7]

    Human Communication Research2(2), 131–146 (1976)

    Burgoon, J.K., Jones, S.B.: Toward a theory of personal space expectations and their violations. Human Communication Research2(2), 131–146 (1976). https://doi.org/10.1111/j.1468-2958.1976.tb00706.x

    work page doi:10.1111/j.1468-2958.1976.tb00706.x 1976

  8. [8]

    In: Proceedings of the 2017 ACM/IEEE International Conference on Human-Robot Interaction

    Carpinella, C.M., Wyman, A.B., Perez, M.A., Stroessner, S.J.: The robotic social attributes scale (RoSAS) development and validation. In: Proceedings of the 2017 ACM/IEEE International Conference on Human-Robot Interaction. pp. 254–262 (2017). https://doi.org/10.1145/2909824.3020208

    work page doi:10.1145/2909824.3020208 2017

  9. [9]

    Crowd Dynamics, Volume 5: From Human Complexity to Scientific Machine Learning pp

    Chatagnon, T., Tordeux, A., Chraibi, M.: Exploring dense crowd dynam- ics: State of the art and emerging paradigms. Crowd Dynamics, Volume 5: From Human Complexity to Scientific Machine Learning pp. 9–36 (2025). https://doi.org/doi.org/10.1007/978-3-032-02221-9_2

    work page doi:10.1007/978-3-032-02221-9_2 2025

  10. [10]

    Christensen, R.H.B.: ordinal—Regression Models for Ordinal Data (2025),https: //CRAN.R-project.org/package=ordinal, r package version 2025.12-29

    work page 2025

  11. [11]

    In: 2013 8th ACM/IEEE International Conference on Human-Robot Inter- action (HRI)

    Dragan, A.D., Lee, K.C., Srinivasa, S.S.: Legibility and predictability of robot motion. In: 2013 8th ACM/IEEE International Conference on Human-Robot Inter- action (HRI). pp. 301–308. IEEE (2013). https://doi.org/10.1109/hri.2013.6483603

    work page doi:10.1109/hri.2013.6483603 2013

  12. [12]

    Frontiers in Robotics and AI8, 721317 (2022)

    Gao, Y., Huang, C.M.: Evaluation of socially-aware robot navigation. Frontiers in Robotics and AI8, 721317 (2022). https://doi.org/10.3389/frobt.2021.721317

    work page doi:10.3389/frobt.2021.721317 2022

  13. [13]

    Hilldale, USA1(2), 67–82 (1977)

    Gibson, J.J.: The theory of affordances. Hilldale, USA1(2), 67–82 (1977). https://doi.org/10.1215/9781478023876-006

    work page doi:10.1215/9781478023876-006 1977

  14. [14]

    In: 2nd Intl

    Gómez, J.V., Mavridis, N., Garrido, S.: Social path planning: Generic human-robot interaction framework for robotic navigation tasks. In: 2nd Intl. Workshop on Cognitive Robotics Systems: Replicating Human Actions and Activities. pp. 17–18 (2013),https://jvgomez.github.io/files/pubs/IROS2013_workshop.pdf

    work page 2013

  15. [15]

    Hall, E.T., Hall, E.T.: The Hidden Dimension, vol. 609. Anchor (1966). https://doi.org/10.2307/1572461

    work page doi:10.2307/1572461 1966

  16. [16]

    Hart and Lowell E

    Hart, S.G., Staveland, L.E.: Development of NASA-TLX (task load index): Results of empirical and theoretical research. In: Advances in Psychology, vol. 52, pp. 139–183. Elsevier (1988). https://doi.org/10.1016/s0166-4115(08)62386-9

    work page doi:10.1016/s0166-4115(08)62386-9 1988

  17. [17]

    Multi-robot task planning under individual and collaborative temporal logic specifications

    Hetherington, N.J., Lee, R., Haase, M., Croft, E.A., Van der Loos, H.M.: Mobile robot yielding cues for human-robot spatial interaction. In: 2021 IEEE/RSJ In- ternational Conference on Intelligent Robots and Systems (IROS). pp. 3028–3033. IEEE (2021). https://doi.org/10.1109/iros51168.2021.9636367

    work page doi:10.1109/iros51168.2021.9636367 2021

  18. [18]

    A simple sequentially rejective multiple test procedur e

    Holm, S.: A simple sequentially rejective multiple test procedure. Scandinavian Journal of Statistics6(2), 65–70 (1979),http://www.jstor.org/stable/4615733

    work page arXiv 1979

  19. [19]

    World Scientific (2011)

    Hori, M.: Introduction to Computational Earthquake Engineering. World Scientific (2011). https://doi.org/10.1142/9781848163997

    work page doi:10.1142/9781848163997 2011

  20. [20]

    Robotics and Autonomous Systems66, 86–103 (2015)

    Kostavelis, I., Gasteratos, A.: Semantic mapping for mobile robotics tasks: A survey. Robotics and Autonomous Systems66, 86–103 (2015). https://doi.org/doi.org/10.1016/j.robot.2014.12.006

    work page doi:10.1016/j.robot.2014.12.006 2015

  21. [21]

    Artificial Life and Robotics25(4), 529–536 (2020)

    Koyama, S., Inoue, D., Okada, A., Yoshida, H.: Separation of pedestrian counter flows with an array of obstacles. Artificial Life and Robotics25(4), 529–536 (2020). https://doi.org/10.1007/s10015-020-00648-w

    work page doi:10.1007/s10015-020-00648-w 2020

  22. [22]

    International Journal of Social Robotics5(2), 291–308 (2013)

    Leite, I., Martinho, C., Paiva, A.: Social robots for long-term interaction: A survey. International Journal of Social Robotics5(2), 291–308 (2013). https://doi.org/10.1007/s12369-013-0178-y 18 N. Zhou et al

    work page doi:10.1007/s12369-013-0178-y 2013

  23. [23]

    Robotics and Autonomous Systems145, 103837 (2021)

    Möller, R., Furnari, A., Battiato, S., Härmä, A., Farinella, G.M.: A survey on human-aware robot navigation. Robotics and Autonomous Systems145, 103837 (2021). https://doi.org/10.1016/j.robot.2021.103837

    work page doi:10.1016/j.robot.2021.103837 2021

  24. [24]

    In2021 30th IEEE international conference on robot & human interactive communication (RO-MAN)

    Nayyar, M., Wagner, A.R.: Effective robot evacuation strategies in emergencies. In: 2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN). pp. 1–6. IEEE (2019). https://doi.org/10.1109/ro- man46459.2019.8956307

    work page doi:10.1109/ro- 2019

  25. [25]

    In: 2016 11th ACM/IEEE Interna- tional Conference on Human-Robot Interaction (HRI)

    Robinette, P., Li, W., Allen, R., Howard, A.M., Wagner, A.R.: Overtrust of robots in emergency evacuation scenarios. In: 2016 11th ACM/IEEE Interna- tional Conference on Human-Robot Interaction (HRI). pp. 101–108. IEEE (2016). https://doi.org/10.1109/hri.2016.7451740

    work page doi:10.1109/hri.2016.7451740 2016

  26. [26]

    Physical Review Fluids7(3), 034302 (2022)

    Seguin, A.: Forces on an intruder combining translation and rota- tion in granular media. Physical Review Fluids7(3), 034302 (2022). https://doi.org/10.1103/PhysRevFluids.7.034302

    work page doi:10.1103/physrevfluids.7.034302 2022

  27. [27]

    In: 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems

    Trautman, P., Krause, A.: Unfreezing the robot: Navigation in dense, interacting crowds. In: 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems. pp. 797–803. IEEE (2010). https://doi.org/10.1109/iros.2010.5654369

    work page doi:10.1109/iros.2010.5654369 2010

  28. [28]

    Physica A: Statistical Mechanics and its Applications562, 125369 (2021)

    Wang, X., Liu, Z., Wang, J., Loughney, S., Yang, Z., Gao, X.: Experimental study on individual walking speed during emergency evacuation with the influence of ship motion. Physica A: Statistical Mechanics and its Applications562, 125369 (2021). https://doi.org/10.1016/j.physa.2020.125369

    work page doi:10.1016/j.physa.2020.125369 2021

  29. [29]

    In: Proc

    Webb, N., Huang, Z., Milivojevic, S., Baber, C., Hunt, E.R.: When robots say no: Temporal trust recovery through explanation. In: International Conference on Social Robotics. pp. 424–436. Springer (2025). https://doi.org/doi.org/10.1007/978- 981-95-2379-5_29

    work page doi:10.1007/978- 2025

  30. [30]

    Australian Journal of Scientific Research Series A: Physical Sciences 2(2), 149–168 (1949)

    Williams, E.J.: Experimental designs balanced for the estimation of residual effects of treatments. Australian Journal of Scientific Research Series A: Physical Sciences 2(2), 149–168 (1949). https://doi.org/10.1071/ch9490149

    work page doi:10.1071/ch9490149 1949

  31. [31]

    The aligned rank transform for nonparametric factorial analyses us- ing only anova procedures,

    Wobbrock, J.O., Findlater, L., Gergle, D., Higgins, J.J.: The aligned rank transform for nonparametric factorial analyses using only anova procedures. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. p. 143–146. CHI ’11, Association for Computing Machinery, New York, NY, USA (2011). https://doi.org/10.1145/1978942.1978963

    work page doi:10.1145/1978942.1978963 2011

  32. [32]

    https://doi.org/10.1038/nrn1411

    Wolfe, J.M., Horowitz, T.S.: What attributes guide the deployment of visual attention and how do they do it? Nature Reviews Neuroscience5(6), 495–501 (2004). https://doi.org/10.1038/nrn1411

    work page doi:10.1038/nrn1411 2004

  33. [33]

    Journal of Statistical Mechanics: Theory and Experiment2022(2), 023407 (2022)

    Xu, H., Zhang, J., Song, W., Hu, Y., Li, X., Ren, X., Yang, L., Yu, H., Jiang, K.: The effect of moving obstacle on regulation of pedestrian flow in a single exit room. Journal of Statistical Mechanics: Theory and Experiment2022(2), 023407 (2022). https://doi.org/10.1088/1742-5468/ac4c3f

    work page doi:10.1088/1742-5468/ac4c3f 2022

  34. [34]

    ACM Transactions on Human-Robot Interaction14(3), 1–27 (2025)

    Zhang, Q., Tsoi, N., Nagib, M., Choi, B., Tan, J., Chiang, H.T.L., Vázquez, M.: Predicting human perceptions of robot performance during navigation tasks. ACM Transactions on Human-Robot Interaction14(3), 1–27 (2025). https://doi.org/10.1145/3719020

    work page doi:10.1145/3719020 2025

  35. [35]

    In: 2022 IEEE 61st Conference on Decision and Control (CDC)

    Zheng, T., Yuan, Z., Nayyar, M., Wagner, A.R., Zhu, M., Lin, H.: Multi-robot- assisted human crowd evacuation using navigation velocity fields. In: 2022 IEEE 61st Conference on Decision and Control (CDC). pp. 2061–2066. IEEE (2022). https://doi.org/10.1109/CDC51059.2022.9993368

    work page doi:10.1109/cdc51059.2022.9993368 2022