pith. sign in

arxiv: 2604.25963 · v1 · submitted 2026-04-28 · 💻 cs.RO

A Scaled Three-Vehicle Platooning Platform

Kaiyue Lu , Qiaoxuan Zhang , Yukun Lu This is my paper

Pith reviewed 2026-05-07 16:21 UTC · model grok-4.3

classification 💻 cs.RO
keywords vehicle platooningscaled platformautonomous vehiclesleader-follower coordinationhuman-in-the-looppath trackingmulti-vehicle controlcooperative autonomy
0
0 comments X

The pith

A scaled three-vehicle platform with one human-operable lead and two autonomous followers enables controlled platooning experiments.

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

The paper introduces a physical test platform for vehicle platooning research that combines a human-driven lead vehicle with two autonomous followers. This setup supports repeatable studies of path tracking and platoon stability during maneuvers such as lane changes, where disturbances from the lead vehicle can affect the followers. The platform is positioned as a practical middle option that delivers physical vehicle interactions while avoiding the expense and safety issues of full-scale road tests. By allowing human-in-the-loop control of the leader, it also opens experiments on cooperative autonomy under realistic conditions.

Core claim

The central contribution is a scaled multi-vehicle platform consisting of one human-operable lead vehicle and two autonomous followers. This configuration is designed to conduct controlled and repeatable experiments on leader-follower coordination, longitudinal and lateral control, and disturbance propagation within a platoon during dynamic maneuvers.

What carries the argument

The scaled three-vehicle platooning platform that integrates human control of the lead vehicle with autonomous path-tracking followers to study cooperative coordination.

If this is right

  • Enables safer and lower-cost validation of longitudinal and lateral controllers before full-scale deployment.
  • Supports repeatable testing of how lateral deviations and heading errors propagate through a platoon during lane changes.
  • Provides a physical environment for multi-agent autonomy studies that include human-in-the-loop leader behavior.
  • Allows rapid prototyping and iteration on cooperative control algorithms with measurable physical outcomes.

Where Pith is reading between the lines

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

  • The platform could serve as a bridge for testing communication protocols or sensor fusion methods that later transfer to larger fleets.
  • Data collected here might inform simulation models by supplying empirical scaling relationships between small and full-size vehicle responses.
  • Similar scaled setups could be adapted to study mixed human-autonomous traffic beyond strict platooning formations.

Load-bearing premise

The dynamics and interactions observed on the scaled vehicles are sufficiently representative of full-scale platooning to validate controllers and stability properties.

What would settle it

An experiment that transfers a controller tuned on the scaled platform to full-size vehicles and measures whether platoon stability and tracking errors remain within acceptable bounds under comparable maneuvers.

Figures

Figures reproduced from arXiv: 2604.25963 by Kaiyue Lu, Qiaoxuan Zhang, Yukun Lu.

Figure 1
Figure 1. Figure 1: The scaled vehicle platform at the Intelligent Mobility view at source ↗
Figure 2
Figure 2. Figure 2: Lead vehicle hardware architecture. from -16° to +14°. Point-cloud data are transmitted to the Jetson Orin board via an Ethernet interface view at source ↗
Figure 3
Figure 3. Figure 3: Schematic of the lead vehicle with Ackermann steering view at source ↗
Figure 4
Figure 4. Figure 4: Follower vehicle hardware architecture. 640 × 480 at 30 fps and is transmitted using the driver-free UVC protocol. The horizontal and vertical fields of view of the RGB camera are 63.1° and 49.4°, respectively. The LiDAR sensor mounted on the follower vehicle is an LSLIDAR N10P, a single-line two-dimensional LiDAR unit. It supports scanning frequencies ranging from 6 to 12 Hz and provides a sampling rate o… view at source ↗
Figure 5
Figure 5. Figure 5: Schematic of the follower vehicle based on the view at source ↗
Figure 7
Figure 7. Figure 7: Schematic of the Stanley control method. view at source ↗
Figure 8
Figure 8. Figure 8: Experiment setup view at source ↗
Figure 9
Figure 9. Figure 9: Scaled multi-vehicle platform with ArUco markers view at source ↗
Figure 10
Figure 10. Figure 10: Experimental results using PID (longitudinal) and view at source ↗
Figure 11
Figure 11. Figure 11: Experimental results using PID (longitudinal) and view at source ↗
read the original abstract

Vehicle platooning has attracted increasing attention as a promising approach to improve traffic efficiency, energy consumption, and roadway safety through coordinated multi-vehicle operation. A key challenge in platooning lies in maintaining stable and accurate path tracking during dynamic maneuvers such as lane changes, where lateral deviations and heading disturbances generated by the lead vehicle may propagate downstream to following vehicles. Robust longitudinal and lateral control systems are therefore essential not only for individual vehicle tracking performance, but also for overall platoon stability. For experimental studies, the Intelligent Mobility and Robotics Lab (IMRL) develops a scaled multi-vehicle platform for autonomous platooning research, with a particular emphasis on cooperative control and human-in-the-loop autonomy. This platform consists of one human-operable lead vehicle and two autonomous followers, enabling controlled and repeatable experiments on leader-follower coordination. Compared with full-scale field testing, this scaled platform offers a safer, lower-cost, and more flexible environment for rapid prototyping, controller validation, and multi-agent autonomy studies, while providing stronger physical realism than purely simulation-based evaluations.

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 scaled three-vehicle platooning platform developed by the Intelligent Mobility and Robotics Lab, consisting of one human-operable lead vehicle and two autonomous followers. It is intended to support experimental research on leader-follower coordination, cooperative control, and human-in-the-loop autonomy, with claimed advantages in safety, cost, flexibility, and physical realism over full-scale testing or pure simulation.

Significance. A functional platform of this type could serve as a practical testbed for validating platooning controllers in repeatable physical conditions, helping bridge the gap between simulation and full-scale deployment. The descriptive account is plausible and aligns with standard motivations in the field, but the absence of any performance metrics, validation experiments, or error analysis means the significance remains potential rather than demonstrated.

major comments (2)
  1. [Abstract] Abstract: the assertion that the platform 'enables controlled and repeatable experiments on leader-follower coordination' and supports 'controller validation' is not accompanied by any experimental results, tracking-error metrics, stability data, or example runs, leaving the central utility claim unsubstantiated.
  2. [Overall manuscript] Overall manuscript: no quantitative comparison is provided to support the claim of 'stronger physical realism than purely simulation-based evaluations,' such as side-by-side metrics on path-tracking accuracy or disturbance propagation under lane-change maneuvers.
minor comments (1)
  1. The manuscript would benefit from including hardware photographs, system diagrams, and at least one illustrative experimental trajectory or time-series plot to make the platform description more concrete.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript describing the scaled three-vehicle platooning platform. The comments correctly identify areas where the utility claims require better support or clarification. We have revised the manuscript to address these points while preserving its focus as a platform description paper.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the assertion that the platform 'enables controlled and repeatable experiments on leader-follower coordination' and supports 'controller validation' is not accompanied by any experimental results, tracking-error metrics, stability data, or example runs, leaving the central utility claim unsubstantiated.

    Authors: We agree that the original wording could imply demonstrated validation results. The manuscript is primarily a description of the platform's design, hardware, and software architecture to support future research. In revision, we have updated the abstract to state that the platform 'is intended to enable controlled and repeatable experiments' and added a brief new subsection (Section 4.3) with preliminary platform checkout data, including sample longitudinal and lateral tracking errors from initial follower runs under constant-speed conditions. revision: yes

  2. Referee: [Overall manuscript] Overall manuscript: no quantitative comparison is provided to support the claim of 'stronger physical realism than purely simulation-based evaluations,' such as side-by-side metrics on path-tracking accuracy or disturbance propagation under lane-change maneuvers.

    Authors: We acknowledge the absence of direct quantitative metrics. The claim of stronger physical realism is based on the platform incorporating unmodeled real-world effects (sensor noise, communication latency, tire-ground interaction, and human lead-vehicle variability) that simulations must approximate. We have expanded the discussion to provide qualitative examples drawn from the platform's specific sensors and actuators. A full side-by-side comparative study would require a separate experimental campaign and is outside the scope of this work; we have noted this as a suggested direction for future research. revision: partial

Circularity Check

0 steps flagged

No significant circularity: purely descriptive hardware platform

full rationale

The manuscript is a descriptive account of a scaled three-vehicle platooning platform with one human-operable lead vehicle and two autonomous followers. It contains no equations, derivations, fitted parameters, quantitative predictions, or load-bearing self-citations. All statements are factual descriptions of the hardware setup and the standard practical advantages of scaled testing (safety, cost, repeatability, physical realism). No step reduces by construction to its own inputs or to a self-referential claim.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No free parameters, axioms, or invented entities are involved because the paper is an engineering description of a physical test platform with no mathematical modeling or data fitting.

pith-pipeline@v0.9.0 · 5473 in / 1042 out tokens · 36832 ms · 2026-05-07T16:21:12.467395+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

18 extracted references · 18 canonical work pages

  1. [1]

    Automatic steering methods for autonomous automobile path tracking,

    J. M. Snider, “Automatic steering methods for autonomous automobile path tracking,” Robotics Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, Tech. Rep. CMU-RI-TR-09-08, February

    work page

  2. [2]

    Available: https://publications.ri.cmu.edu/storage/public ations/pub files/2009/2/Automatic Steering Methods for Autonomou s Automobile Path Tracking.pdf

    [Online]. Available: https://publications.ri.cmu.edu/storage/public ations/pub files/2009/2/Automatic Steering Methods for Autonomou s Automobile Path Tracking.pdf

    work page 2009

  3. [3]

    Development of lateral control system for autonomous vehicle based on adaptive pure pursuit algo- rithm,

    M.-W. Park, S.-W. Lee, and W.-Y . Han, “Development of lateral control system for autonomous vehicle based on adaptive pure pursuit algo- rithm,” in2014 14th International Conference on Control, Automation and Systems (ICCAS 2014), 2014, pp. 1443–1447. 8

    work page 2014

  4. [4]

    Vehicle lateral control for intelligent driving based on dynamic compensation of stanley algorithm,

    C. Sun, H. Liu, W. Xiao, and X. Wen, “Vehicle lateral control for intelligent driving based on dynamic compensation of stanley algorithm,” in2025 5th International Conference on Robotics, Automation, and Artificial Intelligence (RAAI), 2025, pp. 878–884

    work page 2025

  5. [5]

    Design of an autonomous vehicle speed control system based on a pid controller,

    Y . Zhang, Z. Tian, and H. Hua, “Design of an autonomous vehicle speed control system based on a pid controller,” in2025 International Confer- ence on Advances in Electrical Engineering and Computer Applications (AEECA), 2025, pp. 491–495

    work page 2025

  6. [6]

    Rationale behind human-led autonomous truck platooning,

    Y . Lu, C. Li, X. Jiang, and Q. Zhang, “Rationale behind human-led autonomous truck platooning,”arXiv preprint arXiv:2603.13296, 2026

    work page arXiv 2026

  7. [7]

    Simulation and real-world de- ployment of game theory in autonomous driving,

    K. Shu, Y . Lu, and A. Khajepour, “Simulation and real-world de- ployment of game theory in autonomous driving,” inGame Theory in Autonomous Driving: Safe Interaction and Decision Making for Real- World Mobility. Springer, 2026, pp. 81–93

    work page 2026

  8. [8]

    Ros 2 documentation: Humble,

    Open Robotics, “Ros 2 documentation: Humble,” https://docs.ros.org/e n/humble/index.html, 2026, accessed: 2026-04-10

    work page 2026

  9. [9]

    Freertos official website,

    Amazon Web Services, “Freertos official website,” https://www.freertos .org/, 2026, accessed: 2026-04-10

    work page 2026

  10. [10]

    R. N. Jazar,Steering Dynamics. Cham: Springer International Publishing, 2017, pp. 379–446. [Online]. Available: https://doi.org/10.1 007/978-3-319-53441-1 6

    work page 2017

  11. [11]

    Differential speed steering control for four-wheel independent driving electric vehicle,

    X. Wu, M. Xu, and L. Wang, “Differential speed steering control for four-wheel independent driving electric vehicle,” in2013 IEEE International Symposium on Industrial Electronics, 2013, pp. 1–6

    work page 2013

  12. [12]

    Path tracking based on improved pure pursuit model and pid,

    Y . Huang, Z. Tian, Q. Jiang, and J. Xu, “Path tracking based on improved pure pursuit model and pid,” in2020 IEEE 2nd International Conference on Civil Aviation Safety and Information Technology (ICCASIT, 2020, pp. 359–364

    work page 2020

  13. [13]

    Model-based hybrid control of pure pursuit and stanley methods for vehicle path tracking,

    H. Jung, “Model-based hybrid control of pure pursuit and stanley methods for vehicle path tracking,”Sensors, vol. 25, no. 20, p. 6491, 2025

    work page 2025

  14. [14]

    An optimal goal point determination algorithm for automatic navigation of agricultural machinery: Improving the tracking accuracy of the pure pursuit algorithm,

    Y . Yang, Y . Li, X. Wen, G. Zhang, Q. Ma, S. Cheng, J. Qi, L. Xu, and L. Chen, “An optimal goal point determination algorithm for automatic navigation of agricultural machinery: Improving the tracking accuracy of the pure pursuit algorithm,”Computers and Electronics in Agriculture, vol. 194, p. 106760, 2022. [Online]. Available: https://www.sciencedirect...

    work page 2022

  15. [15]

    Safety of the stanley controller with curved lanes and noisy perception,

    H. Li and S. Mitra, “Safety of the stanley controller with curved lanes and noisy perception,” in2023 62nd IEEE Conference on Decision and Control (CDC), 2023, pp. 8628–8634

    work page 2023

  16. [16]

    Detection of aruco markers,

    S. Garrido and A. Panov, “Detection of aruco markers,” https://docs.ope ncv.org/4.x/d5/dae/tutorial aruco detection.html, accessed: 2026-04-16

    work page 2026

  17. [17]

    Communication resource-efficient vehicle platooning control with various spacing poli- cies,

    X. Ge, Q.-L. Han, X.-M. Zhang, and D. Ding, “Communication resource-efficient vehicle platooning control with various spacing poli- cies,”IEEE/CAA Journal of Automatica Sinica, vol. 11, no. 2, pp. 362– 376, 2023

    work page 2023

  18. [18]

    Collaborative lane change of heterogeneous truck platoon based on mec control architecture with constant communication delay,

    G. Yang, W. Chu, X. Tang, D. Cao, and K. Li, “Collaborative lane change of heterogeneous truck platoon based on mec control architecture with constant communication delay,”IEEE Transactions on Vehicular Technology, 2026

    work page 2026