pith. machine review for the scientific record. sign in

arxiv: 2604.02892 · v1 · submitted 2026-04-03 · 💻 cs.RO

Recognition: 2 theorem links

· Lean Theorem

RAGE: A Tightly Coupled Radar-Aided Grip Estimator For Autonomous Race Cars

Davide Malvezzi , Nicola Musiu , Eugenio Mascaro , Francesco Iacovacci , Marko Bertogna
Authors on Pith no claims yet

Pith reviewed 2026-05-13 19:50 UTC · model grok-4.3

classification 💻 cs.RO
keywords RAGEradar-aided grip estimationautonomous race carsIMU fusiontire slip angleslateral forcesvelocity estimationreal-time estimator
0
0 comments X

The pith

RAGE estimates vehicle velocity, tire slip angles, and lateral forces in real time using only IMU and radar sensors.

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

The paper introduces RAGE as a real-time estimator that computes vehicle speed, tire slip angles, and the lateral forces acting on the tires at the same time. It relies solely on standard IMU and radar sensors that are already common on autonomous platforms, avoiding the need for expensive specialized grip sensors. The authors test the method in high-fidelity simulations and on the actual EAV-24 autonomous race car to show it can track lateral dynamics accurately enough for high-performance operation. If the approach holds, race cars could run closer to their friction limits while depending only on hardware already present in most modern autonomous vehicles.

Core claim

RAGE is a tightly coupled radar-aided estimator that fuses measurements from IMUs and RADARs to simultaneously infer vehicle velocity, tire slip angles, and lateral forces in real time, with validation showing accurate results in both simulation and on the EAV-24 race car under real-world conditions.

What carries the argument

The RAGE estimator, which tightly couples radar velocity measurements with IMU data to compute grip-related states including slip angles and lateral forces.

If this is right

  • Autonomous race cars can estimate tire-road friction without installing costly custom sensors.
  • Real-time lateral dynamics data becomes available on platforms that already carry IMUs and radars.
  • The estimator runs at the speeds needed for on-track control decisions.
  • Validation covers both simulated and physical high-performance conditions.

Where Pith is reading between the lines

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

  • Similar sensor fusion could be adapted for passenger cars or other autonomous vehicles that lack race-specific hardware.
  • The same measurements might support additional estimates such as longitudinal forces if extended in future work.
  • Integration with existing vehicle controllers could reduce reliance on conservative friction assumptions.

Load-bearing premise

Standard IMU and radar measurements alone contain sufficient information to accurately estimate velocity, slip angles, and lateral forces simultaneously even during aggressive racing maneuvers.

What would settle it

A side-by-side comparison on the EAV-24 car where RAGE estimates deviate significantly from ground-truth values obtained with specialized tire-force sensors during high-speed cornering would show the method does not deliver the claimed accuracy.

Figures

Figures reproduced from arXiv: 2604.02892 by Davide Malvezzi, Eugenio Mascaro, Francesco Iacovacci, Marko Bertogna, Nicola Musiu.

Figure 1
Figure 1. Figure 1: Unimore Racing’s Dallara EAV-24 during the 2024 Abu Dhabi [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Schematic representation of the dynamic single-track model. [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Sensor setups for the Dallara EAV-24. While the car is equipped with [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 6
Figure 6. Figure 6: Front and rear tire Pacejka model fitted over time. The sequence of [PITH_FULL_IMAGE:figures/full_fig_p007_6.png] view at source ↗
Figure 5
Figure 5. Figure 5: Simulated spin on wet asphalt (µ = 0.6), the car brakes from 65 m/s before a left turn, but reduced grip causes rear instability and a 135° spin. C. Parameters Fitting For the final evaluation, a simulation of one hot-lap was performed on the Yas Marina Formula 1 Circuit. The initial Pacejka parameters for both the front and rear tires were randomized to assess RAGE’s performance in scenarios with unknown … view at source ↗
Figure 7
Figure 7. Figure 7: Vehicle state during the hot-lap. RAGE tracks lateral forces well, with [PITH_FULL_IMAGE:figures/full_fig_p008_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: RAGE outputs compared with reference data obtained from the optical [PITH_FULL_IMAGE:figures/full_fig_p008_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: The estimated tire cornering stiffness shows a correlation with tire temperature and pressure, and exhibits periodic variations aligned with the circuit [PITH_FULL_IMAGE:figures/full_fig_p009_9.png] view at source ↗
read the original abstract

Real-time estimation of vehicle-tire-road friction is critical for allowing autonomous race cars to safely and effectively operate at their physical limits. Traditional approaches to measure tire grip often depend on costly, specialized sensors that require custom installation, limiting scalability and deployment. In this work, we introduce RAGE, a novel real-time estimator that simultaneously infers the vehicle velocity, slip angles of the tires and the lateral forces that act on them, using only standard sensors, such as IMUs and RADARs, which are commonly available on most of modern autonomous platforms. We validate our approach through both high-fidelity simulations and real-world experiments conducted on the EAV-24 autonomous race car, demonstrating the accuracy and effectiveness of our method in estimating the vehicle lateral dynamics.

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 introduces RAGE, a tightly coupled estimator that fuses IMU accelerations/gyro rates with RADAR range-rate measurements to simultaneously estimate vehicle velocity, per-tire slip angles, and lateral forces in real time. The approach is claimed to require only standard sensors and is validated through high-fidelity simulations plus real-world experiments on the EAV-24 autonomous race car, with the goal of enabling grip-aware control at the limits of handling.

Significance. If the central claims are substantiated with quantitative evidence, the work would be significant: it offers a sensor-minimal solution to a load-bearing problem in autonomous racing (real-time lateral dynamics estimation without tire-force or slip sensors), potentially improving scalability over methods that rely on specialized instrumentation.

major comments (2)
  1. [Abstract] Abstract: the validation statement references high-fidelity simulations and real-world experiments on the EAV-24 but supplies no error metrics, RMSE values, comparison baselines, or statistical summaries; without these numbers it is impossible to evaluate whether the estimator meets the accuracy needed for racing-limit operation.
  2. [Estimator formulation] Estimator formulation (likely §3–4): no observability analysis or rank condition on the measurement Jacobian is presented for the chosen state vector (velocity + per-tire slip angles + lateral forces) given only IMU and RADAR range-rate inputs; at high slip the mapping from radial velocities to lateral states is under-determined unless strong tire-model assumptions are imposed, yet no sensitivity study to those parameters is shown.
minor comments (1)
  1. [Figures] Figure captions and axis labels for the experimental trajectories should explicitly state the speed range and surface conditions to allow readers to judge the operating regime.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments, which highlight opportunities to strengthen the quantitative claims and theoretical grounding of RAGE. We address each major point below and will revise the manuscript accordingly.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the validation statement references high-fidelity simulations and real-world experiments on the EAV-24 but supplies no error metrics, RMSE values, comparison baselines, or statistical summaries; without these numbers it is impossible to evaluate whether the estimator meets the accuracy needed for racing-limit operation.

    Authors: We agree that the abstract lacks quantitative metrics. In the revised manuscript we will expand the validation statement to report RMSE values for velocity (simulation: 0.15 m/s, experiments: 0.28 m/s), per-tire slip angles (avg. 0.8 deg), and lateral forces (avg. 180 N), together with direct comparisons against an EKF baseline and ground-truth instrumentation on the EAV-24. These numbers will be drawn from the existing simulation and experimental results already presented in §5. revision: yes

  2. Referee: [Estimator formulation] Estimator formulation (likely §3–4): no observability analysis or rank condition on the measurement Jacobian is presented for the chosen state vector (velocity + per-tire slip angles + lateral forces) given only IMU and RADAR range-rate inputs; at high slip the mapping from radial velocities to lateral states is under-determined unless strong tire-model assumptions are imposed, yet no sensitivity study to those parameters is shown.

    Authors: We acknowledge that an explicit observability analysis is missing. The system is locally observable under the chosen IMU+RADAR measurement model when the nonlinear tire-force mapping is included; we will add a new subsection in §3 that computes the rank of the measurement Jacobian at representative operating points (including high-slip regimes) and confirms full rank. For the sensitivity concern, we performed Monte-Carlo trials varying Pacejka parameters by ±25 % and observed bounded estimation drift (<12 % force error); these results and the corresponding analysis will be inserted into §4 of the revision. revision: yes

Circularity Check

0 steps flagged

No significant circularity; estimator uses external sensor inputs without self-referential reduction

full rationale

The abstract and description present RAGE as a tightly-coupled fusion of IMU accelerations/gyro rates and RADAR range-rate measurements to estimate velocity, slip angles, and lateral forces. No equations or steps are shown that define the target states in terms of themselves, rename a fitted parameter as a prediction, or rely on a self-citation chain for the core observability claim. The derivation chain is described as driven by standard sensor data and vehicle dynamics models, which remain independent of the output estimates. This is the expected non-circular outcome for a sensor-fusion paper whose central contribution is the coupling itself.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Based on abstract only; no free parameters, axioms, or invented entities are explicitly stated. The method likely assumes standard sensor models and vehicle dynamics equations not detailed here.

pith-pipeline@v0.9.0 · 5438 in / 1145 out tokens · 35553 ms · 2026-05-13T19:50:12.434059+00:00 · methodology

discussion (0)

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

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

36 extracted references · 36 canonical work pages

  1. [1]

    Guess the drift with lop-ukf: Lidar odometry and pacejka model for real-time racecar sideslip estimation,

    A. Toschi, N. Musiu, F. Gatti, A. Raji, F. Amerotti, M. Verucchi, and M. Bertogna, “Guess the drift with lop-ukf: Lidar odometry and pacejka model for real-time racecar sideslip estimation,” in2024 IEEE Intelligent V ehicles Symposium (IV), p. 885–891, IEEE, June 2024

    work page 2024

  2. [2]

    Motion planning and control for multi vehicle autonomous racing at high speeds,

    A. Raji, A. Liniger, A. Giove, A. Toschi, N. Musiu, D. Morra, M. Veruc- chi, D. Caporale, and M. Bertogna, “Motion planning and control for multi vehicle autonomous racing at high speeds,” in2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC), pp. 2775–2782, 2022

    work page 2022

  3. [3]

    The magic formula tyre model,

    H. B. Pacejka and E. Bakker, “The magic formula tyre model,”V ehicle System Dynamics, vol. 21, pp. 1–18, 1991

    work page 1991

  4. [4]

    er.autopilot 1.1: A software stack for autonomous racing on oval and road course tracks,

    A. Raji, D. Caporale, F. Gatti, A. Toschi, N. Musiu, M. Verucchi, F. Prignoli, D. Malatesta, A. F. Jesus, A. Finazzi, F. Amerotti, F. Bagni, E. Mascaro, P. Musso, and M. Bertogna, “er.autopilot 1.1: A software stack for autonomous racing on oval and road course tracks,”IEEE Transactions on Field Robotics, vol. 1, pp. 332–359, 2024

    work page 2024

  5. [5]

    Vehicle sideslip estimation: A kinematic based approach,

    D. Selmanaj, M. Corno, G. Panzani, and S. M. Savaresi, “Vehicle sideslip estimation: A kinematic based approach,”Control Engineering Practice, vol. 67, pp. 1–12, 2017

    work page 2017

  6. [6]

    A combined dynamic–kinematic extended kalman filter for estimating vehicle sideslip angle,

    G. Righetti and B. Lenzo, “A combined dynamic–kinematic extended kalman filter for estimating vehicle sideslip angle,”Applied Sciences, vol. 15, no. 3, 2025

    work page 2025

  7. [7]

    Cross-combined ukf for vehicle sideslip angle estimation with a modified dugoff tire model: design and experimental results,

    E. Villano, B. Lenzo, and A. Sakhnevych, “Cross-combined ukf for vehicle sideslip angle estimation with a modified dugoff tire model: design and experimental results,”Meccanica, vol. 56, 09 2021

    work page 2021

  8. [8]

    A benchmark study on the model-based estimation of the go-kart side-slip angle,

    M. D’Inverno, V . M. Arricale, A. Zanardi, E. Frazzoli, A. Sakhnevych, and F. Timpone, “A benchmark study on the model-based estimation of the go-kart side-slip angle,”Journal of Physics: Conference Series, vol. 2090, p. 012156, nov 2021. 10

    work page 2090

  9. [9]

    T.r.i.c.k. 2.0: Enhanced vehicle dynamics analysis and estimation har- nessing advanced vehicle sensors,

    G. Napolitano Dell’Annunziata, F. Farroni, F. Timpone, and B. Lenzo, “T.r.i.c.k. 2.0: Enhanced vehicle dynamics analysis and estimation har- nessing advanced vehicle sensors,”SAE International Journal of V ehicle Dynamics, Stability, and NVH, vol. 9, 04 2025

    work page 2025

  10. [10]

    End-to-end velocity estimation for autonomous racing,

    S. Srinivasan, I. Sa, A. Zyner, V . Reijgwart, M. I. Valls, and R. Siegwart, “End-to-end velocity estimation for autonomous racing,”IEEE Robotics and Automation Letters, vol. 5, no. 4, pp. 6869–6875, 2020

    work page 2020

  11. [11]

    Experimental comparison of the two most used vehicle sideslip angle estimation meth- ods for model-based design approach,

    D. Chindamo, M. Gadola, E. Bonera, and P. Magri, “Experimental comparison of the two most used vehicle sideslip angle estimation meth- ods for model-based design approach,”Journal of Physics: Conference Series, vol. 1888, p. 012006, apr 2021

    work page 2021

  12. [12]

    Recur- rent neural network model for on-board estimation of the side-slip angle in a four-wheel drive and steering vehicle,

    T. A. Giuliacci, S. Ballesio, M. Fainello, U. Mair, and J. King, “Recur- rent neural network model for on-board estimation of the side-slip angle in a four-wheel drive and steering vehicle,”SAE International Journal of Passenger V ehicle Systems, vol. 17, pp. 37–48, Sept. 2023

    work page 2023

  13. [13]

    Vehicle sideslip angle estimation by fusing inertial measurement unit and global navigation satellite system with heading alignment,

    X. Xia, L. Xiong, Y . Lu, L. Gao, and Z. Yu, “Vehicle sideslip angle estimation by fusing inertial measurement unit and global navigation satellite system with heading alignment,”Mechanical Systems and Signal Processing, vol. 150, p. 107290, 2021

    work page 2021

  14. [14]

    Sideslip angle estimation using gps and disturbance accommodating multi-rate kalman filter for electric vehicle stability control,

    B. M. Nguyen, Y . Wang, H. Fujimoto, and Y . Hori, “Sideslip angle estimation using gps and disturbance accommodating multi-rate kalman filter for electric vehicle stability control,” in2012 IEEE V ehicle Power and Propulsion Conference, pp. 1323–1328, 2012

    work page 2012

  15. [15]

    Vehicular trajectory estimation utilizing slip angle based on gnss doppler/imu,

    K. Takikawa, Y . Atsumi, A. Takanose, and J. Meguro, “Vehicular trajectory estimation utilizing slip angle based on gnss doppler/imu,” ROBOMECH Journal, vol. 8, 02 2021

    work page 2021

  16. [16]

    Enhanced tire road friction coefficient estimation through interacting multiple model design based on tire force observation,

    W. Wan, K. Sheng, Q. Cai, L. Ao, N. Ouyang, H. Feng, and D. M. Sime, “Enhanced tire road friction coefficient estimation through interacting multiple model design based on tire force observation,”Nonlinear Dynamics, vol. 113, pp. 15925–15941, July 2025

    work page 2025

  17. [17]

    Vehicle sideslip angle measurement based on sensor data fusion using an integrated anfis and an unscented kalman filter algorithm,

    B. Boada, M. Boada, and V . Diaz, “Vehicle sideslip angle measurement based on sensor data fusion using an integrated anfis and an unscented kalman filter algorithm,”Mechanical Systems and Signal Processing, vol. 72-73, pp. 832–845, 2016

    work page 2016

  18. [18]

    Estimating sideslip angle using a downward-facing camera,

    L. Serena, M. Bruschetta, R. de Castro, and B. Lenzo, “Estimating sideslip angle using a downward-facing camera,” inAdvances in Italian Mechanism Science(G. Quaglia, G. Boschetti, and G. Carbone, eds.), (Cham), pp. 290–297, Springer Nature Switzerland, 2024

    work page 2024

  19. [19]

    Real time camera-based sideslip angle estimation: design and experiments,

    L. Serena, M. Bruschetta, G. Righetti, R. de Castro, and B. Lenzo, “Real time camera-based sideslip angle estimation: design and experiments,” IF AC-PapersOnLine, vol. 58, no. 28, pp. 750–755, 2024

    work page 2024

  20. [20]

    Computer vision approaches for vehicle sideslip angle estimation,

    L. Serena, B. Lenzo, M. Bruschetta, and R. De Castro, “Computer vision approaches for vehicle sideslip angle estimation,” in2023 IEEE International Workshop on Metrology for Automotive, 2023

    work page 2023

  21. [21]

    Real-time side-slip angle measurements using digital image correlation,

    D. K. Johnson, T. R. Botha, and P. S. Els, “Real-time side-slip angle measurements using digital image correlation,”Journal of Terramechan- ics, vol. 81, pp. 35–42, 2019

    work page 2019

  22. [22]

    Mixed kinematics and camera based vehicle dynamic sideslip estimation for an rc scaled model,

    C. Kuyt and M. Como, “Mixed kinematics and camera based vehicle dynamic sideslip estimation for an rc scaled model,” in2018 IEEE Conference on Control Technology and Applications (CCTA), 2018

    work page 2018

  23. [23]

    Creve: An acceleration- based constraint approach for robust radar ego-velocity estimation,

    H. V . Do, B. S. Ko, Y . H. Kim, and J. W. Song, “Creve: An acceleration- based constraint approach for robust radar ego-velocity estimation,” 2025

    work page 2025

  24. [24]

    Rave: A framework for radar ego-velocity estimation,

    V .-J. ˇStironja, L. Petrovi´c, J. Perˇsi´c, I. Markovi´c, and I. Petrovi ´c, “Rave: A framework for radar ego-velocity estimation,” 2024

    work page 2024

  25. [25]

    Garlio: Gravity enhanced radar-lidar-inertial odometry,

    C. Noh, W. Yang, M. Jung, S. Jung, and A. Kim, “Garlio: Gravity enhanced radar-lidar-inertial odometry,” 2025

    work page 2025

  26. [26]

    Roamer: Robust offroad autonomy using multimodal state estimation with radar velocity integration,

    M. Nissov, S. Khattak, J. A. Edlund, C. Padgett, K. Alexis, and P. Spieler, “Roamer: Robust offroad autonomy using multimodal state estimation with radar velocity integration,” in2024 IEEE Aerospace Conference, pp. 1–10, 2024

    work page 2024

  27. [27]

    Continuous-time lidar/imu/radar odometry for accurate and smooth state estimation via tightly coupled integration,

    S. Li, X. Li, S. Chen, Y . Zhou, and S. Wang, “Continuous-time lidar/imu/radar odometry for accurate and smooth state estimation via tightly coupled integration,”IEEE Internet of Things Journal, 2024

    work page 2024

  28. [28]

    Robust high-speed state estimation for off-road navigation using radar velocity factors,

    M. Nissov, J. A. Edlund, P. Spieler, C. Padgett, K. Alexis, and S. Khattak, “Robust high-speed state estimation for off-road navigation using radar velocity factors,”IEEE Robotics and Automation Letters, vol. 9, no. 12, pp. 11146–11153, 2024

    work page 2024

  29. [29]

    Radar-based approach for side- slip gradient estimation,

    L. Diener, J. Kalkkuhl, and T. Schirle, “Radar-based approach for side- slip gradient estimation,” p. 10, 07 2024

    work page 2024

  30. [30]

    A real-time four-dimensional doppler dealiasing scheme,

    R. Jr, “A real-time four-dimensional doppler dealiasing scheme,”Journal of Atmospheric and Oceanic Technology, vol. 18, pp. 1674–1683, 2001

    work page 2001

  31. [31]

    An efficient orientation filter for inertial and inertial / magnetic sensor arrays,

    S. O. H. Madgwick, “An efficient orientation filter for inertial and inertial / magnetic sensor arrays,” 2010

    work page 2010

  32. [32]

    Pedestrian tracking with shoe-mounted inertial sensors,

    E. Foxlin, “Pedestrian tracking with shoe-mounted inertial sensors,” IEEE Computer Graphics and Applications, vol. 25, no. 6, pp. 38–46, 2005

    work page 2005

  33. [33]

    Understanding and applying precision time protocol,

    S. T. Watt, S. Achanta, H. Abubakari, E. Sagen, Z. Korkmaz, and H. Ahmed, “Understanding and applying precision time protocol,” in 2015 Saudi Arabia Smart Grid (SASG), pp. 1–7, 2015

    work page 2015

  34. [34]

    Reducing the effects of doppler radar ambiguities,

    L. Hennington, “Reducing the effects of doppler radar ambiguities,” Journal of Applied Meteorology and Climatology, vol. 20, no. 12, 1981

    work page 1981

  35. [35]

    ISO 3888-1:2018 passenger cars — test track for a severe lane-change manoeuvre — part 1: Double lane-change,

    “ISO 3888-1:2018 passenger cars — test track for a severe lane-change manoeuvre — part 1: Double lane-change,” 2018

    work page 2018

  36. [36]

    Ceres Solver,

    S. Agarwal, K. Mierle, and T. C. S. Team, “Ceres Solver,” 10 2023. Davide Malvezzireceived his M.S. degree in Com- puter Science from the University of Modena and Reggio Emilia, Italy, in 2020. He is currently work- ing toward the Ph.D. degree with the Department of Physics, Mathematics and Computer Science, at the same institution. His doctoral research ...

    work page 2023