pith. sign in

arxiv: 2603.19812 · v2 · pith:W7N35M2Jnew · submitted 2026-03-20 · 💻 cs.LG

Eye Gaze-Informed and Context-Aware Pedestrian Trajectory Prediction in Shared Spaces with Automated Shuttles: A Virtual Reality Study

Danya Li , Yan Feng , Rico Krueger This is my paper

Pith reviewed 2026-05-25 06:25 UTC · model grok-4.3

classification 💻 cs.LG
keywords pedestrian trajectory predictioneye gazevirtual realityautomated shuttlesmulti-modal fusionshared spacescontext-aware prediction
0
0 comments X

The pith

Eye gaze and situational context provide complementary information that reduces pedestrian trajectory prediction error by 8.47% in VR encounters with automated shuttles.

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

The paper reports a virtual reality experiment collecting motion, eye gaze, and head data as pedestrians interact with automated shuttles at various angles and traffic densities. A multi-modal model fuses these signals to predict future pedestrian positions, and ablations test the contribution of gaze versus context. Results show gaze value depends on approach angle and is best captured continuously rather than as fixation categories. The combination of gaze and context yields an error reduction nearly equal to the sum of separate gains, indicating they supply distinct predictive cues. This work supports adding human perceptual data to improve forecasts of pedestrian behavior around autonomous vehicles.

Core claim

In a virtual reality setup with pedestrians facing shuttles at 45, 90, and 135 degree approaches and varying traffic, eye gaze data fused with motion and context through modality-specific encoders improves trajectory prediction. Gaze information proves angle-dependent, with continuous orientation outperforming categorical labels, and the joint use of gaze and situational context cuts final displacement error by 8.47 percent, almost matching the additive effect of each alone.

What carries the argument

A multi-modal prediction model with modality-specific encoders that integrates eye gaze, head orientation, motion, and situational context for pedestrian trajectory forecasting.

Load-bearing premise

Virtual reality produces eye gaze and movement patterns that match real-world pedestrian interactions with automated shuttles.

What would settle it

A real-world field study measuring whether adding eye gaze tracking to shuttle prediction models achieves a similar 8.47% reduction in final displacement error.

Figures

Figures reproduced from arXiv: 2603.19812 by Danya Li, Rico Krueger, Yan Feng.

Figure 1
Figure 1. Figure 1: An overview of the paper. are absent or less informative in shared spaces. For instance, map-based or infrastructure-related features cannot be directly applied because shared spaces usually lack physical separation. These considerations motivate the need to identify and model alternative situational contexts that meaningfully influence pedestrian behavior in shared spaces. This paper addresses these gaps … view at source ↗
Figure 2
Figure 2. Figure 2: Model architecture. • LSTM motion encoder: Hm = LSTM(Ypast , V,Wm, ϕ) • LSTM distance encoder: Hd = LSTM(D,Wd, ϕ) • LSTM eye gaze encoder: He = LSTM(E,We, ϕ) • Hidden dense layers: Hh = fh([Hm, Hd, He, X,Wh, ϕ]) • Output layer: [µ, Σ] = fo([Hh,Wo, ϕ]) where Wm,Wd,We are the weights of LSTM layers, Wh and Wo are the weights of hidden dense and output layers, ϕ is the activation function with ReLU, and fh an… view at source ↗
Figure 3
Figure 3. Figure 3: Representation of eye and head direction in our model. The first row shows the eye representation, and the second row shows the corresponding head [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: An overview of the experiment setup. • eHMI presence: The eHMI was designed with a pedes￾trian sign displayed on the front window when it was activated, shown in [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Experiment procedure. The numbers in the VR experiment block represent the levels of each variable, while the numbers in the post-questionnaire [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Plot summary of the effects of experimental variables on errors. [PITH_FULL_IMAGE:figures/full_fig_p011_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Qualitative results comparison. The arrows show pedestrians’ eye orientation from the top-down view. [PITH_FULL_IMAGE:figures/full_fig_p012_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: An illustration of the design of interactions. [PITH_FULL_IMAGE:figures/full_fig_p016_8.png] view at source ↗
read the original abstract

To address this gap, we conduct a Virtual Reality experiment in which pedestrians interact with automated shuttles under varying approach angles (45{\deg}, 90{\deg}, 135{\deg}) and continuous-traffic conditions (single shuttle, two shuttles with 3 or 5-second gaps), collecting synchronized motion, eye gaze, and head orientation data. To investigate to what extent, under what conditions, and in what form fine-grained eye gaze is informative for pedestrian motion prediction, we develop a multi-modal prediction model that fuses these signals through modality-specific encoders, and systematically ablate gaze representations against head orientation and situational context. We report three main results. First, the predictive value of eye gaze is angle-dependent and tightly coupled with eye-head-body coordination: at acute angles where pedestrians actively redirect gaze to acquire the shuttle, eye gaze carries information that head orientation alone misses. Second, continuous gaze orientation outperforms categorical semantic fixation labels, with the optimal encoding frame (global or body-relative) depending on whether gaze is used alone or jointly with context. Third, eye gaze and situational context provide complementary predictive information: their combination reduces final displacement error (FDE) by 8.47%, close to the sum of their individual contributions. Together, these findings highlight the value of incorporating human perceptual signals into pedestrian behavior prediction and motivate a human-centered complement to vehicle-centric modeling approaches. Our code is available at https://github.com/danyayay/GazeX.git.

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 / 1 minor

Summary. The manuscript describes a Virtual Reality study where pedestrians interact with automated shuttles in scenarios with varying approach angles (45°, 90°, 135°) and traffic conditions. Synchronized data on motion, eye gaze, and head orientation is collected. A multi-modal model fuses these signals via modality-specific encoders, and ablations are performed against head orientation and situational context. Three main findings are reported: angle-dependent value of eye gaze tied to coordination, superiority of continuous gaze orientation over categorical labels, and complementarity of gaze and context yielding an 8.47% FDE reduction approximately additive.

Significance. If the reported ablation outcomes are statistically robust, this work contributes to pedestrian trajectory prediction by demonstrating the utility of fine-grained eye gaze data, particularly its complementarity with context and dependence on interaction geometry. The public release of code at https://github.com/danyayay/GazeX.git supports reproducibility and is a positive aspect. The findings motivate incorporating human perceptual signals into models for shared spaces with automated vehicles.

major comments (2)
  1. [Abstract] Abstract: The quantitative claim that combining eye gaze and situational context reduces FDE by 8.47% (close to the sum of individual contributions) is presented without error bars, participant count, statistical significance tests, or details on the model architecture, training procedure, or ablation implementation, making it impossible to assess the reliability or robustness of this central numerical result.
  2. [Results paragraph] Results paragraph: The claim that the ablation results 'motivate a human-centered complement to vehicle-centric modeling approaches' for deployed shuttles assumes that VR gaze and movement patterns generalize to real-world pedestrian-shuttle encounters, yet no validation, sensitivity analysis, or discussion of differences due to absent physical threat or altered visual fidelity at the tested angles is provided.
minor comments (1)
  1. [Abstract] Abstract: The description of the model as using 'modality-specific encoders' and 'systematically ablate gaze representations' would benefit from a brief clarification of the fusion mechanism and the exact gaze encodings tested, even at the abstract level.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments. We address each major comment point-by-point below, indicating where revisions will be made to improve clarity and completeness.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The quantitative claim that combining eye gaze and situational context reduces FDE by 8.47% (close to the sum of individual contributions) is presented without error bars, participant count, statistical significance tests, or details on the model architecture, training procedure, or ablation implementation, making it impossible to assess the reliability or robustness of this central numerical result.

    Authors: We agree that the abstract would benefit from additional supporting details for the central 8.47% FDE claim. In the revised manuscript, we will add the participant count and explicitly reference the sections describing the model architecture, training procedure, ablation implementation, and statistical tests. Error bars and full numerical results with significance values are already reported in the results section and figures; we will note this in the abstract. Due to strict length constraints, we cannot embed the complete ablation tables or error bars directly in the abstract but will ensure the claim is properly contextualized. revision: partial

  2. Referee: [Results paragraph] Results paragraph: The claim that the ablation results 'motivate a human-centered complement to vehicle-centric modeling approaches' for deployed shuttles assumes that VR gaze and movement patterns generalize to real-world pedestrian-shuttle encounters, yet no validation, sensitivity analysis, or discussion of differences due to absent physical threat or altered visual fidelity at the tested angles is provided.

    Authors: We acknowledge that the manuscript would be strengthened by a more explicit discussion of VR-to-real-world generalizability. While a limitations section exists, we will expand it to address the absence of physical threat, potential differences in visual fidelity at the tested angles (45°, 90°, 135°), and the lack of direct real-world validation or sensitivity analysis. The study is positioned as a controlled VR investigation to isolate eye-gaze contributions; we will clarify that the motivational claim for deployed systems is forward-looking and contingent on future real-world confirmation. This addition will be made without overstating the current evidence. revision: yes

Circularity Check

0 steps flagged

Empirical ablation study with no circular derivation chain

full rationale

The paper reports results from a VR experiment and systematic ablations on a multi-modal trajectory prediction model. The key claim (8.47% FDE reduction from gaze+context fusion) is a measured empirical outcome on held-out data, not a quantity derived by construction from model definitions, fitted parameters renamed as predictions, or self-citation chains. No equations, uniqueness theorems, or ansatzes appear that reduce the reported complementarity to inputs internal to the same study. The work is self-contained against external benchmarks via code release and data collection protocol.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No free parameters, axioms, or invented entities are introduced; the work rests on standard supervised learning assumptions and the ecological validity of VR data collection.

pith-pipeline@v0.9.0 · 5805 in / 1012 out tokens · 32745 ms · 2026-05-25T06:25:14.135381+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

94 extracted references · 94 canonical work pages

  1. [1]

    Pedestrian- vehicle interaction in shared space: Insights for autonomous vehicles,

    Y . Wang, L. Hespanhol, S. Worrall, and M. Tomitsch, “Pedestrian- vehicle interaction in shared space: Insights for autonomous vehicles,” inProceedings of the 14th International Conference on Automotive User Interfaces and Interactive Vehicular Applications, 2022, pp. 330–339

    work page 2022

  2. [2]

    Pedes- trian trajectory prediction in pedestrian-vehicle mixedenvironments: A systematic review,

    M. Golchoubian, M. Ghafurian, K. Dautenhahn, and N. L. Azad, “Pedes- trian trajectory prediction in pedestrian-vehicle mixedenvironments: A systematic review,”IEEE Transactions on Intelligent Transportation Systems, 2023

    work page 2023

  3. [3]

    Does another pedestrian matter? a virtual reality study on the interaction between multiple pedes- trians and autonomous vehicles in shared space,

    Y . Feng, Z. Xu, H. Farah, and B. van Arem, “Does another pedestrian matter? a virtual reality study on the interaction between multiple pedes- trians and autonomous vehicles in shared space,”IEEE Transactions on Intelligent Transportation Systems, vol. 26, no. 1, pp. 196–209, 2025

    work page 2025

  4. [4]

    Top-view trajectories: A pedestrian dataset of vehicle-crowd interaction from controlled ex- periments and crowded campus,

    D. Yang, L. Li, K. Redmill, and Ü. Özgüner, “Top-view trajectories: A pedestrian dataset of vehicle-crowd interaction from controlled ex- periments and crowded campus,” in2019 IEEE Intelligent Vehicles Symposium (IV). IEEE, 2019, pp. 899–904

    work page 2019

  5. [5]

    Analyzing the behaviors of pedestrians and cyclists in interactions with autonomous systems using controlled experiments: A literature review,

    D. Li, W. Mao, F. C. Pereira, Y . Xiao, X. Su, and R. Krueger, “Analyzing the behaviors of pedestrians and cyclists in interactions with autonomous systems using controlled experiments: A literature review,” Transportation Research Part F: Traffic Psychology and Behaviour, vol. 114, pp. 270–307, 2025. 14

    work page 2025

  6. [6]

    Interact or counteract? Behavioural observation of interactions between vulnerable road users and autonomous shuttles in Oslo, Norway,

    T. De Ceunynck, B. Pelssers, T. Bjørnskau, O. Aasvik, A. Fyhri, A. Lau- reshyn, C. Johnsson, M. Hagenzieker, and H. Martensen, “Interact or counteract? Behavioural observation of interactions between vulnerable road users and autonomous shuttles in Oslo, Norway,”Traffic Safety Research, vol. 2, August 2022

    work page 2022

  7. [7]

    Gap acceptance study of pedestrians crossing between pla- tooning autonomous vehicles in a virtual environment,

    R. Woodman, K. Lu, M. D. Higgins, S. Brewerton, P. A. Jennings, and S. Birrell, “Gap acceptance study of pedestrians crossing between pla- tooning autonomous vehicles in a virtual environment,”Transportation Research Part F: Traffic Psychology and Behaviour, Nov. 2019

    work page 2019

  8. [8]

    Application of LargeSpace for investigating pedestrians’ behaviors when interacting with autonomous vehicles in shared spaces,

    A. Andrijanto, Z. Chen, T. Kodama, H. Yano, and M. Itoh, “Application of LargeSpace for investigating pedestrians’ behaviors when interacting with autonomous vehicles in shared spaces,” inProceedings - 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2022, 2022

    work page 2022

  9. [9]

    Data collec- tion methods for studying pedestrian behaviour: A systematic review,

    Y . Feng, D. Duives, W. Daamen, and S. Hoogendoorn, “Data collec- tion methods for studying pedestrian behaviour: A systematic review,” Building and Environment, vol. 187, p. 107329, 2021

    work page 2021

  10. [10]

    Land and B

    M. Land and B. Tatler,Looking and acting: vision and eye movements in natural behaviour. Oxford University Press, 2009

    work page 2009

  11. [11]

    How far ahead do we look when required to step on specific locations in the travel path during locomotion?

    A. E. Patla and J. N. Vickers, “How far ahead do we look when required to step on specific locations in the travel path during locomotion?” Experimental brain research, vol. 148, no. 1, pp. 133–138, 2003

    work page 2003

  12. [12]

    The where, what and when of gaze allocation in the lab and the natural environment,

    T. Foulsham, E. Walker, and A. Kingstone, “The where, what and when of gaze allocation in the lab and the natural environment,”Vision research, vol. 51, no. 17, pp. 1920–1931, 2011

    work page 1920

  13. [13]

    MX-LSTM: Mixing tracklets and vislets to jointly forecast trajectories and head poses,

    I. Hasan, F. Setti, T. Tsesmelis, A. Del Bue, F. Galasso, and M. Cristani, “MX-LSTM: Mixing tracklets and vislets to jointly forecast trajectories and head poses,” in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT: IEEE, Jun. 2018, pp. 6067–6076

    work page 2018

  14. [14]

    Understanding pedestrian-vehicle interactions with vehicle mounted vision: An LSTM model and empirical analysis,

    D. A. Ridel, N. Deo, D. Wolf, and M. Trivedi, “Understanding pedestrian-vehicle interactions with vehicle mounted vision: An LSTM model and empirical analysis,” in2019 IEEE Intelligent Vehicles Sym- posium (IV), Jun. 2019, pp. 913–918

    work page 2019

  15. [15]

    Pedestrian behavior prediction for automated driving: Requirements, metrics, and relevant features,

    M. Herman, J. Wagner, V . Prabhakaran, N. Möser, H. Ziesche, W. Ahmed, L. Bürkle, E. Kloppenburg, and C. Gläser, “Pedestrian behavior prediction for automated driving: Requirements, metrics, and relevant features,”IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 9, pp. 14 922–14 937, Sep. 2022

    work page 2022

  16. [16]

    Multi-agent trajectory prediction with heterogeneous edge-enhanced graph attention network,

    X. Mo, Z. Huang, Y . Xing, and C. Lv, “Multi-agent trajectory prediction with heterogeneous edge-enhanced graph attention network,”IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 7, pp. 9554–9567, 2022

    work page 2022

  17. [17]

    Are they going to cross? A benchmark dataset and baseline for pedestrian crosswalk behavior,

    A. Rasouli, I. Kotseruba, and J. K. Tsotsos, “Are they going to cross? A benchmark dataset and baseline for pedestrian crosswalk behavior,” inProceedings of the IEEE international conference on computer vision workshops, 2017, pp. 206–213

    work page 2017

  18. [18]

    Do pedestrians pay attention? Eye contact detection in the wild,

    Y . Belkada, L. Bertoni, R. Caristan, T. Mordan, and A. Alahi, “Do pedestrians pay attention? Eye contact detection in the wild,” Dec. 2021, arXiv:2112.04212 [cs]

    work page arXiv 2021

  19. [19]

    Pedestrian’s gaze object detection in traffic scene,

    H. Murakami, J. Chen, D. Deguchi, T. Hirayama, Y . Kawanishi, and H. Murase, “Pedestrian’s gaze object detection in traffic scene,” in Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. Rome, Italy: SCITEPRESS - Science and Technology Publications, 2024, pp. 333–340

    work page 2024

  20. [20]

    Collaborative motion prediction via neural motion message passing,

    Y . Hu, S. Chen, Y . Zhang, and X. Gu, “Collaborative motion prediction via neural motion message passing,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 6319– 6328

    work page 2020

  21. [21]

    Motion style transfer: Modular low-rank adaptation for deep motion forecasting,

    P. Kothari, D. Li, Y . Liu, and A. Alahi, “Motion style transfer: Modular low-rank adaptation for deep motion forecasting,” inConference on Robot Learning. PMLR, 2023, pp. 774–784

    work page 2023

  22. [22]

    Socialcvae: Predicting pedestrian trajectory via interaction conditioned latents,

    W. Xiang, Y . Haoteng, H. Wang, and X. Jin, “Socialcvae: Predicting pedestrian trajectory via interaction conditioned latents,” inProceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 6, 2024, pp. 6216–6224

    work page 2024

  23. [23]

    GroupNet: Multiscale hypergraph neural networks for trajectory prediction with relational reasoning,

    C. Xu, M. Li, Z. Ni, Y . Zhang, and S. Chen, “GroupNet: Multiscale hypergraph neural networks for trajectory prediction with relational reasoning,” Apr. 2022, arXiv:2204.08770 [cs]

    work page arXiv 2022

  24. [24]

    From goals, waypoints & paths to long term human trajectory forecasting,

    K. Mangalam, Y . An, H. Girase, and J. Malik, “From goals, waypoints & paths to long term human trajectory forecasting,” inProceedings of the IEEE/CVF international conference on computer vision, 2021, pp. 15 233–15 242

    work page 2021

  25. [25]

    Context-aware multi-task learning for pedestrian intent and trajectory prediction,

    F. Munir and T. P. Kucner, “Context-aware multi-task learning for pedestrian intent and trajectory prediction,”Transportation Research Part C: Emerging Technologies, vol. 178, p. 105203, 2025

    work page 2025

  26. [26]

    A context-aware pedestrian trajectory prediction framework for automated vehicles,

    A. Kalatian and B. Farooq, “A context-aware pedestrian trajectory prediction framework for automated vehicles,”Transportation Research Part C: Emerging Technologies, vol. 134, January 2022

    work page 2022

  27. [27]

    Cross or wait? Predicting pedestrian interaction outcomes at unsignalized crossings,

    C. Zhang, A. H. Kalantari, Y . Yang, Z. Ni, G. Markkula, N. Merat, and C. Berger, “Cross or wait? Predicting pedestrian interaction outcomes at unsignalized crossings,” in2023 IEEE Intelligent Vehicles Symposium (IV). IEEE, 2023, pp. 1–8

    work page 2023

  28. [28]

    Research on a pedestrian crossing intention recognition model based on natural observation data,

    H. Zhang, Y . Liu, C. Wang, R. Fu, Q. Sun, and Z. Li, “Research on a pedestrian crossing intention recognition model based on natural observation data,”Sensors, vol. 20, no. 6, p. 1776, 2020

    work page 2020

  29. [29]

    INTERACTION dataset: An international, adversarial and cooperative motion dataset in interactive driving scenarios with semantic maps,

    W. Zhan, L. Sun, D. Wang, H. Shi, A. Clausse, M. Naumann, J. Küm- merle, H. Königshof, C. Stiller, A. de La Fortelle, and M. Tomizuka, “INTERACTION dataset: An international, adversarial and cooperative motion dataset in interactive driving scenarios with semantic maps,” arXiv:1910.03088 [cs, eess], Sep. 2019

    work page arXiv 1910

  30. [30]

    Large scale interactive motion forecasting for autonomous driving: The waymo open motion dataset,

    S. Ettinger, S. Cheng, B. Caine, C. Liu, H. Zhao, S. Pradhan, Y . Chai, B. Sapp, C. R. Qi, Y . Zhouet al., “Large scale interactive motion forecasting for autonomous driving: The waymo open motion dataset,” inProceedings of the IEEE/CVF international conference on computer vision, 2021, pp. 9710–9719

    work page 2021

  31. [31]

    nuscenes: A multimodal dataset for autonomous driving,

    H. Caesar, V . Bankiti, A. H. Lang, S. V ora, V . E. Liong, Q. Xu, A. Krishnan, Y . Pan, G. Baldan, and O. Beijbom, “nuscenes: A multimodal dataset for autonomous driving,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 11 621–11 631

    work page 2020

  32. [32]

    PIE: A large-scale dataset and models for pedestrian intention estimation and trajectory prediction,

    A. Rasouli, I. Kotseruba, T. Kunic, and J. K. Tsotsos, “PIE: A large-scale dataset and models for pedestrian intention estimation and trajectory prediction,” inInternational Conference on Computer Vision (ICCV), 2019

    work page 2019

  33. [33]

    A discrete choice model for solving conflict situations between pedestrians and vehicles in shared space,

    F. Pascucci, N. Rinke, C. Schiermeyer, V . Berkhahn, and B. Friedrich, “A discrete choice model for solving conflict situations between pedestrians and vehicles in shared space,” Sep. 2017

    work page 2017

  34. [34]

    Developing and testing robust autonomy: The university of sydney campus data set,

    W. Zhou, J. S. Berrio, C. De Alvis, M. Shan, S. Worrall, J. Ward, and E. Nebot, “Developing and testing robust autonomy: The university of sydney campus data set,”IEEE Intelligent Transportation Systems Magazine, vol. 12, no. 4, pp. 23–40, 2020

    work page 2020

  35. [35]

    Robotic etiquette: Results from user studies involving a fetch and carry task,

    M. L. Walters, K. Dautenhahn, S. N. Woods, and K. L. Koay, “Robotic etiquette: Results from user studies involving a fetch and carry task,” in Proceedings of the ACM/IEEE international conference on Human-robot interaction, 2007, pp. 317–324

    work page 2007

  36. [36]

    Proac- tive behavior of an autonomous mobile robot for human-assisted learn- ing,

    A. Garrell, M. Villamizar, F. Moreno-Noguer, and A. Sanfeliu, “Proac- tive behavior of an autonomous mobile robot for human-assisted learn- ing,” in2013 IEEE RO-MAN. IEEE, 2013, pp. 107–113

    work page 2013

  37. [37]

    Pedestrian behavior in shared spaces with autonomous vehicles: An integrated framework and review,

    M. Prédhumeau, A. Spalanzani, and J. Dugdale, “Pedestrian behavior in shared spaces with autonomous vehicles: An integrated framework and review,”IEEE Transactions on Intelligent Vehicles, vol. 8, no. 1, January 2023

    work page 2023

  38. [38]

    Studying pedestrians’ crossing behavior when interacting with auto- mated vehicles using virtual reality,

    J. P. Nuñez Velasco, H. Farah, B. van Arem, and M. P. Hagenzieker, “Studying pedestrians’ crossing behavior when interacting with auto- mated vehicles using virtual reality,”Transportation Research Part F: Traffic Psychology and Behaviour, vol. 66, October 2019

    work page 2019

  39. [39]

    Long short-term memory,

    S. Hochreiter and J. Schmidhuber, “Long short-term memory,”Neural computation, vol. 9, no. 8, pp. 1735–1780, 1997

    work page 1997

  40. [40]

    A conceptual model of conflicts in shared spaces,

    S. Hossain, F. T. Johora, J. P. Müller, and S. Hartmann, “A conceptual model of conflicts in shared spaces,” inProceedings of the 6th Inter- national Conference on Industrial and Business Engineering, 2020, pp. 228–235

    work page 2020

  41. [41]

    Agent- based modeling for predicting pedestrian trajectories around an au- tonomous vehicle,

    M. Prédhumeau, L. Mancheva, J. Dugdale, and A. Spalanzani, “Agent- based modeling for predicting pedestrian trajectories around an au- tonomous vehicle,”Journal of Artificial Intelligence Research, vol. 73, pp. 1385–1433, 2022

    work page 2022

  42. [42]

    Simulation of pedestrian interaction with autonomous vehicles via social force model,

    M. M. Rashid, M. Seyedi, and S. Jung, “Simulation of pedestrian interaction with autonomous vehicles via social force model,”Simulation modelling practice and theory, vol. 132, p. 102901, 2024

    work page 2024

  43. [43]

    Off the beaten sidewalk: Pedestrian prediction in shared spaces for autonomous vehi- cles,

    C. Anderson, R. Vasudevan, and M. Johnson-Roberson, “Off the beaten sidewalk: Pedestrian prediction in shared spaces for autonomous vehi- cles,”IEEE Robotics and Automation Letters, vol. 5, no. 4, pp. 6892– 6899, Oct. 2020

    work page 2020

  44. [44]

    Shared space multi-modal traffic modeling using lstm networks with repulsion map and an intention-based multi-loss function,

    E. P. Kampitakis, P. Fafoutellis, G.-M. Oprea, and E. I. Vlahogianni, “Shared space multi-modal traffic modeling using lstm networks with repulsion map and an intention-based multi-loss function,”Transporta- tion Research Part C: Emerging Technologies, vol. 150, p. 104104, 2023

    work page 2023

  45. [45]

    Modeling mixed traffic in shared space using LSTM with probability density mapping,

    H. Cheng and M. Sester, “Modeling mixed traffic in shared space using LSTM with probability density mapping,” in2018 21st International Conference on Intelligent Transportation Systems (ITSC). IEEE, 2018, pp. 3898–3904. 15

    work page 2018

  46. [46]

    A deep learning framework for modeling pedestrian-vehicle interactions in shared space,

    P. Fafoutellis, E. P. Kampitakis, and E. I. Vlahogianni, “A deep learning framework for modeling pedestrian-vehicle interactions in shared space,” in2023 8th International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS). IEEE, 2023, pp. 1–6

    work page 2023

  47. [47]

    Prediction based trajec- tory planning for safe interactions between autonomous vehicles and moving pedestrians in shared spaces,

    B. Yang, S. Yan, Z. Wang, and K. Nakano, “Prediction based trajec- tory planning for safe interactions between autonomous vehicles and moving pedestrians in shared spaces,”IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 10, pp. 10 513–10 524, 2023

    work page 2023

  48. [48]

    An agent-based model for trajectory modelling in shared spaces: A combination of expert-based and deep learning approaches,

    F. T. Johora, H. Cheng, J. P. Müller, and M. Sester, “An agent-based model for trajectory modelling in shared spaces: A combination of expert-based and deep learning approaches,” inProceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems, 2020, pp. 1878–1880

    work page 2020

  49. [49]

    A hierarchical forecasting model of pedestrian crossing behavior for autonomous vehicle,

    G. Yang, E. J. L. Pulgarin, and G. Herrmann, “A hierarchical forecasting model of pedestrian crossing behavior for autonomous vehicle,”IEEE Access, vol. 12, pp. 9025–9037, 2024

    work page 2024

  50. [50]

    Eye tracking in virtual reality: A broad review of applications and challenges,

    I. B. Adhanom, P. MacNeilage, and E. Folmer, “Eye tracking in virtual reality: A broad review of applications and challenges,”Virtual Reality, vol. 27, no. 2, pp. 1481–1505, 2023

    work page 2023

  51. [51]

    Modeling eye gaze velocity trajectories using GANs with spectral loss for enhanced fidelity,

    S. Bhandari, P. Lencastre, R. Mathema, A. Szorkovszky, A. Yazidi, and P. G. Lind, “Modeling eye gaze velocity trajectories using GANs with spectral loss for enhanced fidelity,”Scientific Reports, vol. 15, no. 1, p. 19929, 2025

    work page 2025

  52. [52]

    Eye- tracking training improves the learning and memory of children with learning difficulty,

    A. S. Chan, T.-L. Lee, S. L. Sze, N. S. Yang, and Y . M. Han, “Eye- tracking training improves the learning and memory of children with learning difficulty,”Scientific Reports, vol. 12, no. 1, p. 13974, 2022

    work page 2022

  53. [53]

    The impact of online reviews on consumers’ purchasing decisions: Evidence from an eye-tracking study,

    T. Chen, P. Samaranayake, X. Cen, M. Qi, and Y .-C. Lan, “The impact of online reviews on consumers’ purchasing decisions: Evidence from an eye-tracking study,”Frontiers in Psychology, vol. 13, p. 865702, 2022

    work page 2022

  54. [54]

    Understanding which cues people use to identify influencer marketing on instagram: An eye tracking study and experiment,

    S. C. Boerman and C. M. Müller, “Understanding which cues people use to identify influencer marketing on instagram: An eye tracking study and experiment,”International Journal of Advertising, vol. 41, no. 1, pp. 6–29, 2022

    work page 2022

  55. [55]

    The effectiveness of eye tracking in the diagnosis of cognitive disorders: A systematic review and meta-analysis,

    Z. Liu, Z. Yang, Y . Gu, H. Liu, and P. Wang, “The effectiveness of eye tracking in the diagnosis of cognitive disorders: A systematic review and meta-analysis,”PloS one, vol. 16, no. 7, p. e0254059, 2021

    work page 2021

  56. [56]

    Pedestrian intention prediction for autonomous driving using a multiple stakeholder perspec- tive model,

    K. Kim, Y . K. Lee, H. Ahn, S. Hahn, and S. Oh, “Pedestrian intention prediction for autonomous driving using a multiple stakeholder perspec- tive model,” in2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Oct. 2020, pp. 7957–7962

    work page 2020

  57. [57]

    Interaction effects of pedestrian behavior, smartphone distraction and external communication of automated vehicles on crossing and gaze behavior,

    M. Lanzer, I. Koniakowsky, M. Colley, and M. Baumann, “Interaction effects of pedestrian behavior, smartphone distraction and external communication of automated vehicles on crossing and gaze behavior,” inProceedings of the 2023 CHI Conference on Human Factors in Computing Systems, April 2023

    work page 2023

  58. [58]

    Two-step communication for the interaction between automated vehicles and pedestrians,

    J. Bindschädel, I. Krems, and A. Kiesel, “Two-step communication for the interaction between automated vehicles and pedestrians,”Transporta- tion Research Part F: Traffic Psychology and Behaviour, vol. 90, 2022

    work page 2022

  59. [59]

    Active vehicle pitch motion for communication in automated driving,

    J. Bindschädel, I. Krems, and A. Kiesel, “Active vehicle pitch motion for communication in automated driving,”Transportation Research Part F: Traffic Psychology and Behaviour, vol. 87, May 2022

    work page 2022

  60. [60]

    Cell phone conversations and child pedestrian’s crossing behavior: A simulator study,

    H. Tapiro, T. Oron-Gilad, and Y . Parmet, “Cell phone conversations and child pedestrian’s crossing behavior: A simulator study,”Safety Science, vol. 89, November 2016

    work page 2016

  61. [61]

    Pedestrian distraction: the effects of road environment complexity and age on pedestrian’s visual attention and crossing behavior,

    ——, “Pedestrian distraction: the effects of road environment complexity and age on pedestrian’s visual attention and crossing behavior,”Journal of Safety Research, vol. 72, February 2020

    work page 2020

  62. [62]

    Does crossing the road in a group in- fluence pedestrians’ gaze behavior?

    M. Lanzer and M. Baumann, “Does crossing the road in a group in- fluence pedestrians’ gaze behavior?”Proceedings of the Human Factors and Ergonomics Society Annual Meeting, vol. 64, no. 1, December 2020

    work page 2020

  63. [63]

    Impact of smartphone distraction on pedes- trians’ crossing behaviour: An application of head-mounted immersive virtual reality,

    A. Sobhani and B. Farooq, “Impact of smartphone distraction on pedes- trians’ crossing behaviour: An application of head-mounted immersive virtual reality,”Transportation Research Part F: Traffic Psychology and Behaviour, vol. 58, October 2018

    work page 2018

  64. [64]

    Predicting locomotion intention using eye movements and EEG with LSTM and Transformers,

    G. Bremer and M. Lappe, “Predicting locomotion intention using eye movements and EEG with LSTM and Transformers,” in2024 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), Oct. 2024, pp. 21–30

    work page 2024

  65. [65]

    Predicting future position from natural walking and eye movements with machine learning,

    G. Bremer, N. Stein, and M. Lappe, “Predicting future position from natural walking and eye movements with machine learning,” in2021 IEEE international conference on artificial intelligence and virtual reality (AIVR). IEEE, 2021, pp. 19–28

    work page 2021

  66. [66]

    Eye tracking-based LSTM for locomotion prediction in VR,

    N. Stein, G. Bremer, and M. Lappe, “Eye tracking-based LSTM for locomotion prediction in VR,” in2022 IEEE conference on virtual reality and 3D user interfaces (VR). IEEE, 2022, pp. 493–503

    work page 2022

  67. [67]

    Gaitway: Gait data-vased VR locomotion prediction system robust to visual distraction,

    Y . Kim, S. Hwang, J. Oh, and S. Kim, “Gaitway: Gait data-vased VR locomotion prediction system robust to visual distraction,” inExtended Abstracts of the CHI Conference on Human Factors in Computing Systems, 2024, pp. 1–8

    work page 2024

  68. [68]

    F-RDW: Redirected walking with forecasting future position,

    S.-B. Jeon, J. Jung, J. Park, and I.-K. Lee, “F-RDW: Redirected walking with forecasting future position,”IEEE Transactions on Visualization and Computer Graphics, vol. 31, no. 4, pp. 1970–1984, Apr. 2025

    work page 1970

  69. [69]

    Effect of ehmi on pedestrian road crossing behavior in shared space with automated vehicles-a virtual reality study,

    Y . Feng, H. Farah, and B. van Arem, “Effect of ehmi on pedestrian road crossing behavior in shared space with automated vehicles-a virtual reality study,” in2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC). IEEE, 2023, pp. 2038–2043

    work page 2023

  70. [70]

    External hmi for self- driving vehicles: Which information shall be displayed?

    S. M. Faas, L.-A. Mathis, and M. Baumann, “External hmi for self- driving vehicles: Which information shall be displayed?”Transportation research part F: traffic psychology and behaviour, vol. 68, pp. 171–186, 2020

    work page 2020

  71. [71]

    Autonomous vehicles that interact with pedestrians: A survey of theory and practice,

    A. Rasouli and J. K. Tsotsos, “Autonomous vehicles that interact with pedestrians: A survey of theory and practice,”IEEE Transactions on Intelligent Transportation Systems, vol. 21, no. 3, pp. 900–918, Mar. 2020

    work page 2020

  72. [72]

    A comparison of three methods for selecting values of input variables in the analysis of output from a computer code,

    M. D. McKay, R. J. Beckman, and W. J. Conover, “A comparison of three methods for selecting values of input variables in the analysis of output from a computer code,”Technometrics, 1979

    work page 1979

  73. [73]

    Simulator sickness questionnaire: An enhanced method for quantifying simulator sickness,

    R. S. Kennedy, N. E. Lane, K. S. Berbaum, and M. G. Lilienthal, “Simulator sickness questionnaire: An enhanced method for quantifying simulator sickness,”The International Journal of Aviation Psychology, vol. 3, no. 3, pp. 203–220, Jul. 1993

    work page 1993

  74. [74]

    The factor structure of the presence questionnaire,

    B. G. Witmer, C. J. Jerome, and M. J. Singer, “The factor structure of the presence questionnaire,”Presence: Teleoperators and Virtual Environments, vol. 14, no. 3, pp. 298–312, Jun. 2005

    work page 2005

  75. [75]

    Development and validation of a questionnaire to assess pedestrian receptivity toward fully autonomous vehicles,

    S. Deb, L. Strawderman, D. W. Carruth, J. DuBien, B. Smith, and T. M. Garrison, “Development and validation of a questionnaire to assess pedestrian receptivity toward fully autonomous vehicles,”Transportation Research Part C: Emerging Technologies, Nov. 2017

    work page 2017

  76. [76]

    Fully automated driving: Impact of trust and practice on manual control recovery,

    W. Payre, J. Cestac, and P. Delhomme, “Fully automated driving: Impact of trust and practice on manual control recovery,”Human Factors, vol. 58, no. 2, pp. 229–241, Mar. 2016

    work page 2016

  77. [77]

    Interaction between pedes- trians and automated vehicles: Exploring a motion-based approach for virtual reality experiments,

    J. Bindschädel, I. Krems, and A. Kiesel, “Interaction between pedes- trians and automated vehicles: Exploring a motion-based approach for virtual reality experiments,”Transportation Research Part F: Traffic Psychology and Behaviour, vol. 82, pp. 316–332, 2021

    work page 2021

  78. [78]

    Uncovering and ad- dressing blink-related challenges in using eye tracking for interactive systems,

    J. W. Grootjen, H. Weingärtner, and S. Mayer, “Uncovering and ad- dressing blink-related challenges in using eye tracking for interactive systems,” inProceedings of the 2024 CHI Conference on Human Factors in Computing Systems, ser. CHI ’24. New York, NY , USA: Association for Computing Machinery, May 2024, pp. 1–23

    work page 2024

  79. [79]

    Identifying fixations and saccades in eye-tracking protocols,

    D. D. Salvucci and J. H. Goldberg, “Identifying fixations and saccades in eye-tracking protocols,” inProceedings of the 2000 symposium on Eye tracking research & applications, 2000, pp. 71–78

    work page 2000

  80. [80]

    H. R. Schiffman,Sensation and perception: An integrated approach. John Wiley & Sons, 1990

    work page 1990

Showing first 80 references.