pith. sign in

arxiv: 2606.30034 · v1 · pith:2X5Q64CBnew · submitted 2026-06-29 · 💻 cs.NI

Scalable Intention Sharing for ETSI VAMs

Felipe E. Valle , Oscar Amador , Johan Thunberg , Elena Haller , Alexey Vinel This is my paper

Pith reviewed 2026-06-30 04:00 UTC · model grok-4.3

classification 💻 cs.NI
keywords V2XETSI VAMintention sharinguncertainty ellipsesExtended Kalman Filtermaneuver coordinationGNSS trajectoriescomputational complexity
0
0 comments X

The pith

Uncertainty ellipses reduce V2X maneuver prediction complexity by an order of magnitude while keeping message size constant.

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

The paper shows that replacing trajectory vectors with uncertainty ellipses for sharing intended maneuvers in ETSI-compliant VAMs cuts computational load dramatically in dense V2X settings. Analysis and simulations confirm ellipses maintain fixed message sizes even as prediction horizons grow, unlike vector-based methods that scale poorly with neighborhood size. An EKF pipeline then converts real cyclist GNSS tracks into short-horizon ellipse predictions that remain reliable for multiple seconds.

Core claim

Encoding maneuvers as uncertainty ellipses instead of trajectory vectors or N-polygons yields an order-of-magnitude drop in computational complexity at constant message size; EKF-generated ellipse forecasts from GNSS data sustain reliable multisecond horizons suitable for scalable ETSI VAM intention sharing.

What carries the argument

Uncertainty ellipses as geometric encodings of predicted maneuvers, generated via an Extended Kalman Filter pipeline from GNSS trajectories.

If this is right

  • Message sizes stay fixed regardless of how far ahead the prediction horizon extends.
  • Neighborhood-scale coordination becomes feasible because per-vehicle compute no longer grows with the number of neighbors.
  • ETSI VAM implementations can adopt ellipse encoding without changing existing message formats or bandwidth budgets.
  • Multisecond reliable forecasts become available for cooperative maneuvers without proportional increases in processing load.

Where Pith is reading between the lines

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

  • The same ellipse encoding could be tested on car or truck trajectories to check whether cyclist-derived filter parameters transfer.
  • Integration with existing ETSI CAM or DENM messages might allow intention sharing without new VAM message types.
  • If ellipses prove robust under packet loss, they could reduce reliance on frequent retransmissions in congested channels.

Load-bearing premise

Simulated CPU measurements on controlled-track cyclist GNSS data will generalize to dense real-world V2X scenes that include mixed vehicle types, occlusions, and packet losses.

What would settle it

Measure CPU time and prediction accuracy when running the ellipse pipeline on live mixed-traffic urban GNSS traces with realistic communication dropouts; if complexity rises above vector methods or accuracy collapses before two seconds, the scalability claim fails.

Figures

Figures reproduced from arXiv: 2606.30034 by Alexey Vinel, Elena Haller, Felipe E. Valle, Johan Thunberg, Oscar Amador.

Figure 1
Figure 1. Figure 1: FIGURE 1 [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: , enables a VRU on-board device to share informa￾tion about its expected future trajectory. In the standard representation, this information is typically expressed as a sequence of predicted trajectory points (up to 15 plus confidence intervals). While this representation provides detailed information about the predicted motion, the number of transmitted trajectory points varies with the prediction horizon… view at source ↗
Figure 3
Figure 3. Figure 3: We argue that the uncertainty ellipse is particu￾larly well suited for V2X intention sharing for two main reasons. First, it provides a compact probabilistic description of the spatial dispersion of the predicted trajectory, allowing the maneuver to be summarized with a small set of parameters rather than a sequence of points. Second, our previous work [1] analytically showed that ellipse-based encoding ac… view at source ↗
Figure 5
Figure 5. Figure 5: FIGURE 5 [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 7
Figure 7. Figure 7: illustrates an example prediction block gen￾erated by the EKF with a horizon of T = 1.5 s (15 discrete steps). According to the ETSI specification, the path prediction container can transmit either up to 15 predicted points or 5 s of future intention, depending on the sampling interval, whichever limit is reached first. The predicted states closely follow the measured GNSS positions, while the associated u… view at source ↗
Figure 8
Figure 8. Figure 8: compares usable horizons for each maneuver set, including left-hand turns, start–stop motion, smooth cir￾cular trajectories, and zig-zag patterns. The maneuvers are ordered by increasing prediction difficulty, reflected by decreasing average usable horizons. Across all ma￾neuver types, the EKF-CTRV predictor maintains the most stable horizons, while the EKF-CV model degrades for turning behaviors and the L… view at source ↗
read the original abstract

Efficient maneuver coordination in dense V2X environments requires accurate short-term prediction while maintaining low communication and computational overhead. Current European Telecommunications Standards Institute (ETSI)-compliant approaches rely on intention detection and trajectory vector transmission, which scale poorly with neighborhood size and prediction horizon. This paper revisits maneuver coordination from an intention sharing perspective and investigates geometric encodings that enable scalable communication. First, we analyze three ETSI-compliant encodings, trajectory vectors, N-polygons, and uncertainty ellipses, through complexity analysis and simulation-based CPU measurements. Results show that uncertainty ellipses reduce computational complexity by an order of magnitude compared with trajectory vectors while maintaining a constant message size. Building on this, an Extended Kalman Filter is used to generate short-horizon predictions, which are encoded as uncertainty ellipses to represent the intended maneuver. The prediction pipeline is evaluated using real-world GNSS trajectories collected from cyclist maneuvers on a controlled test track, demonstrating that the approach achieves reliable multisecond prediction horizons while maintaining scalability for dense V2X environments.

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

3 major / 2 minor

Summary. The paper analyzes three ETSI-compliant encodings for VAM intention sharing (trajectory vectors, N-polygons, uncertainty ellipses) via complexity analysis and CPU simulations, claiming ellipses achieve an order-of-magnitude complexity reduction at constant message size. It then applies an EKF to predict short-horizon maneuvers encoded as uncertainty ellipses and evaluates the pipeline on real GNSS cyclist trajectories from a controlled test track, reporting reliable multisecond prediction horizons and overall scalability for dense V2X.

Significance. If the complexity reduction and prediction reliability hold under broader conditions, the work could support more scalable maneuver coordination in ETSI V2X systems by replacing variable-length trajectory vectors with fixed-size geometric encodings. The simulation-based CPU comparison and use of real GNSS data are concrete strengths; however, the absence of mixed-traffic or lossy-channel experiments limits immediate applicability claims.

major comments (3)
  1. [§4] §4 (Simulation results): The reported ~10× CPU reduction for ellipses versus trajectory vectors is measured in a single-class, lossless setting; no ablation varies neighborhood size, prediction horizon, or packet-loss rate, so the scalability claim for dense V2X environments rests on an untested extrapolation.
  2. [§5] §5 (EKF evaluation): The multisecond prediction reliability is demonstrated only on controlled-track cyclist GNSS traces; the manuscript provides neither dataset cardinality, cross-validation procedure, nor quantitative error metrics (e.g., mean ellipse overlap or position RMSE with confidence intervals), making the “reliable” claim difficult to assess.
  3. [Abstract & §6] Abstract & §6 (Conclusions): The assertion that the method “maintains scalability for dense V2X environments” is not supported by any experiment that includes mixed vehicle/pedestrian classes, occlusions, or communication losses—the weakest assumption identified in the stress-test note.
minor comments (2)
  1. Notation for the three encodings is introduced without a consolidated table; a single comparison table listing message size, complexity order, and prediction method would improve readability.
  2. The EKF state vector and measurement model are described only at high level; explicit equations for the ellipse covariance propagation would allow readers to reproduce the prediction step.

Simulated Author's Rebuttal

3 responses · 1 unresolved

We thank the referee for the constructive comments, which help clarify the scope and limitations of our work. We respond point-by-point to the major comments below.

read point-by-point responses

  1. Referee: [§4] §4 (Simulation results): The reported ~10× CPU reduction for ellipses versus trajectory vectors is measured in a single-class, lossless setting; no ablation varies neighborhood size, prediction horizon, or packet-loss rate, so the scalability claim for dense V2X environments rests on an untested extrapolation.

    Authors: The complexity analysis in §4 is general and shows that uncertainty ellipses yield constant message size (O(1)) independent of neighborhood size or horizon length, unlike trajectory vectors whose size scales with these factors. The CPU simulations confirm an order-of-magnitude reduction in a representative setting. We agree that the simulations were performed without packet loss or multi-class variation and that explicit ablations would strengthen the dense-V2X claim. We will add discussion in §4 and §6 explicitly stating the modeling assumptions and noting that future lossy-channel evaluations are needed. revision: partial

  2. Referee: [§5] §5 (EKF evaluation): The multisecond prediction reliability is demonstrated only on controlled-track cyclist GNSS traces; the manuscript provides neither dataset cardinality, cross-validation procedure, nor quantitative error metrics (e.g., mean ellipse overlap or position RMSE with confidence intervals), making the “reliable” claim difficult to assess.

    Authors: We acknowledge the need for more rigorous reporting. The revised §5 will report the exact dataset cardinality, describe the cross-validation procedure, and include quantitative metrics such as position RMSE with confidence intervals together with ellipse-overlap statistics across the prediction horizon. These additions will make the reliability assessment reproducible. revision: yes

  3. Referee: [Abstract & §6] Abstract & §6 (Conclusions): The assertion that the method “maintains scalability for dense V2X environments” is not supported by any experiment that includes mixed vehicle/pedestrian classes, occlusions, or communication losses—the weakest assumption identified in the stress-test note.

    Authors: The scalability claim rests on the analytical complexity reduction and constant message size, which are class-agnostic. The cyclist GNSS evaluation is presented as a representative vulnerable-road-user case. We agree that the absence of mixed-class and lossy-channel experiments limits applicability statements. We will revise the abstract and §6 to moderate the language, replace the broad claim with a statement grounded in the presented analysis, and add an explicit limitations paragraph discussing the assumptions and required future work on mixed traffic and channel losses. revision: partial

standing simulated objections not resolved
  • New experiments involving mixed vehicle/pedestrian classes, occlusions, and lossy communication channels cannot be performed within the current revision scope without additional data collection.

Circularity Check

0 steps flagged

No circularity detected in derivation chain

full rationale

The paper's claims rest on complexity analysis of three encodings, simulation-based CPU measurements comparing uncertainty ellipses to trajectory vectors, and EKF-based predictions evaluated on external real-world GNSS cyclist trajectories from a controlled test track. No equations, fitted parameters, or self-citations are described that reduce any prediction or result to its own inputs by construction. The derivation chain is self-contained against external benchmarks and does not invoke self-citation load-bearing uniqueness theorems, ansatzes smuggled via citation, or renaming of known results.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review; no free parameters, axioms, or invented entities are identifiable from the provided text.

pith-pipeline@v0.9.1-grok · 5710 in / 997 out tokens · 41664 ms · 2026-06-30T04:00:22.627293+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

17 extracted references · 1 canonical work pages

  1. [1]

    V2X Intention Sharing for Cooperative Electrically Power- Assisted Cycles,

    F. Valle, J. Elfing, J. Pålsson, E. Haller, and O. Amador, “V2X Intention Sharing for Cooperative Electrically Power- Assisted Cycles,” in F AST-zero’25 - Future Active Safety Technology toward zero traffic accidents. Arles, France: Laboratory of Accident Mechanisms Analysis of Gustave VOLUME , 9 Author Valle et al.: Scalable Intention Sharing for ETSI V A...

    2025

  2. [2]

    Cellular-V2X for Vulner- able Road User Protection in Cooperative ITS,

    A. Hegde, S. Lobo, and A. Festag, “Cellular-V2X for Vulner- able Road User Protection in Cooperative ITS,” in 2022 18th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob), 2022, pp. 118– 123

    2022

  3. [3]

    Hastie, R

    T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer, 2009

    2009

  4. [4]

    Intelligent Transport System (ITS); Vulnerable Road Users (VRU) awareness; Part 2: Functional Architecture and Re- quirements definition; Release 2 ,

    European Telecommunications Standards Institute (ETSI), “Intelligent Transport System (ITS); Vulnerable Road Users (VRU) awareness; Part 2: Functional Architecture and Re- quirements definition; Release 2 ,” ETSI, Standard TS 103 300-2 V2.1.1, May 2020

    2020

  5. [5]

    Pedestrian intention recogni- tion using latent-dynamic conditional random fields,

    D. Schulz and R. Stiefelhagen, “Pedestrian intention recogni- tion using latent-dynamic conditional random fields,” in IEEE Intelligent Vehicles Symposium (IV). IEEE, 2015, pp. 622– 627

    2015

  6. [6]

    A controlled interactive multiple model filter for com- bined pedestrian intention recognition and path prediction,

    ——, “A controlled interactive multiple model filter for com- bined pedestrian intention recognition and path prediction,” in IEEE Intelligent Transportation Systems (ITSC). IEEE, 2015, pp. 173–178

    2015

  7. [7]

    Pedestrian intention and pose prediction using dynamical models and behavior classifi- cation,

    R. Quintero and D. M. Gavrila, “Pedestrian intention and pose prediction using dynamical models and behavior classifi- cation,” in IEEE Intelligent Vehicles Symposium (IV). IEEE, 2015, pp. 529–534

    2015

  8. [8]

    Road topology aware pedestrian trajectory prediction via graph-based pooling,

    E. Pool, J. F. Kooij, and D. M. Gavrila, “Road topology aware pedestrian trajectory prediction via graph-based pooling,” in IEEE Intelligent Vehicles Symposium (IV). IEEE, 2017, pp. 431–436

    2017

  9. [9]

    Lane-change intention prediction using machine learning,

    A. Benterki et al., “Lane-change intention prediction using machine learning,” in IEEE IDAACS. IEEE, 2019, pp. 617– 622

    2019

  10. [10]

    Towards cooperative vrus: Optimal positioning sampling for pedestrian awareness messages,

    J. Martín-Pérez, O. Amador, M. Rydeberg, L. Olsson, and A. Vinel, “Towards cooperative vrus: Optimal positioning sampling for pedestrian awareness messages,” 2023. [Online]. A vailable:https://arxiv.org/abs/2312.14072

    work page arXiv 2023

  11. [11]

    Adaptive message pri- oritization: How to prioritize vru awareness messages in a congested v2x network,

    S. Lobo, A. Festag, and C. Facchi, “Adaptive message pri- oritization: How to prioritize vru awareness messages in a congested v2x network,” in 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), 2024, pp. 423–430

    2024

  12. [12]

    V2X intention sharing for e-bikes and e-scooters: Design and implementation of a vehicular network protocol for vulnerable road users intention sharing,

    J. Elfing and J. Pålsson, “V2X intention sharing for e-bikes and e-scooters: Design and implementation of a vehicular network protocol for vulnerable road users intention sharing,” Master’s thesis, Halmstad University, School of Information Technology, Halmstad, Sweden, 2024. [Online]. A vailable: https://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-53613

    2024

  13. [13]

    Intelligent Transport Systems (ITS); Vulnerable Road Users (VRU) awareness; Part 3: Specification of VRU aware- ness basic service; Release 2,

    ETSI, “Intelligent Transport Systems (ITS); Vulnerable Road Users (VRU) awareness; Part 3: Specification of VRU aware- ness basic service; Release 2,” European Telecommunications Standards Institute (ETSI), Technical Specification (TS) 103- 300-3 v2.1.1, 11 2020

    2020

  14. [14]

    Sensor fusion for predicting vehicles’ path for collision avoidance systems,

    A. Polychronopoulos, M. Tsogas, A. J. Amditis, and L. An- dreone, “Sensor fusion for predicting vehicles’ path for collision avoidance systems,” IEEE Transactions on Intelligent Trans- portation Systems, vol. 8, no. 3, pp. 549–562, 2007

    2007

  15. [15]

    Nesterov and A

    Y. Nesterov and A. Nemirovskii, Interior-Point Polynomial Algorithms in Convex Programming, ser. SIAM Studies in Applied Mathematics. SIAM, 1994

    1994

  16. [16]

    Artery: Extending Veins for V ANET Applications,

    R. Riebl, H. Günther, C. Facchi, and L. Wolf, “Artery: Extending Veins for V ANET Applications,” in 2015 Interna- tional Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS), 2015, pp. 450–456

    2015

  17. [17]

    ITS; Vehicular Communications; Geographical Area Definition; Release 2,

    ETSI, “ITS; Vehicular Communications; Geographical Area Definition; Release 2,” ETSI, Tech. Rep. TS 103 899 V2.1.1, 2025. Felipe Valle received the M.Sc. degree in electrical engineering from the University of Chile, in 2019. He is currently pursuing a Ph.D. degree with Halmstad University, Sweden. His research interests include coop- erative automated an...

    2025