Physical Fidelity of Learned Nonlinear Vehicle Dynamics: Validation Selection, Observational Bias, and Architecture-Conditioned Inductive Bias

Abstract Learned vehicle-dynamics models can reproduce nominal trajectories while misrepresenting local tangent and finite-time behavior. We evaluate this discrepancy using analytical 3-, 7-, and 14-state nonlinear vehicle models with vector-field, Jacobian, directional-deformation, and frozen-local propagator metrics. Reference-based validation selectors substantially enrich critical-region coverage: at a 10\% budget, symmetric growth reaches macro recall 0.4338 versus 0.1011 for random sampling. In fresh-seed training, physics-inspired selection reduces 14-state Jacobian error by 2.09\%, below the predefined 5\% practical threshold, while the 5.80\% propagator reduction is not significant after Holm correction. A coverage-constrained Lagrangian selector improves Jacobian error by 16.5\% but worsens propagator error by 27.6\%, showing that better local derivative fidelity does not guarantee better finite-time response. Adaptive loss balancing and Adam-to-L-BFGS refinement provide no consistent gains, and architecture effects depend on learner parameterization. A post-hoc state-resolved analysis of 716 frozen checkpoints further shows that training interventions redistribute fidelity across physical states: M1 improves the longitudinal, pitch-rate, and wheel-spin equations while degrading lateral-velocity and roll-rate dynamics. These results support target-specific, coverage-aware training and validation rather than assuming that more physics-selected data or stronger physical priors improve all fidelity measures.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-16
DOI
https://doi.org/10.21203/rs.3.rs-11443334/v1
Primary Topic
Vehicle Dynamics and Control Systems
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Physical Fidelity of Learned Nonlinear Vehicle Dynamics: Validation Selection, Observational Bias, and Architecture-Conditioned Inductive Bias

Antônio Augusto Fröhlich, J. L. Ribeiro Filho
Research Square
Vehicle Dynamics and Control Systems
preprint

Physical Fidelity of Learned Nonlinear Vehicle Dynamics: Validation Selection, Observational Bias, and Architecture-Conditioned Inductive Bias

Antônio Augusto Fröhlich, J. L. Ribeiro Filho
preprint en

Abstract

Abstract Learned vehicle-dynamics models can reproduce nominal trajectories while misrepresenting local tangent and finite-time behavior. We evaluate this discrepancy using analytical 3-, 7-, and 14-state nonlinear vehicle models with vector-field, Jacobian, directional-deformation, and frozen-local propagator metrics. Reference-based validation selectors substantially enrich critical-region coverage: at a 10\% budget, symmetric growth reaches macro recall 0.4338 versus 0.1011 for random sampling. In fresh-seed training, physics-inspired selection reduces 14-state Jacobian error by 2.09\%, below the predefined 5\% practical threshold, while the 5.80\% propagator reduction is not significant after Holm correction. A coverage-constrained Lagrangian selector improves Jacobian error by 16.5\% but worsens propagator error by 27.6\%, showing that better local derivative fidelity does not guarantee better finite-time response. Adaptive loss balancing and Adam-to-L-BFGS refinement provide no consistent gains, and architecture effects depend on learner parameterization. A post-hoc state-resolved analysis of 716 frozen checkpoints further shows that training interventions redistribute fidelity across physical states: M1 improves the longitudinal, pitch-rate, and wheel-spin equations while degrading lateral-velocity and roll-rate dynamics. These results support target-specific, coverage-aware training and validation rather than assuming that more physics-selected data or stronger physical priors improve all fidelity measures.

Research Square
Universidade Federal de Santa Catarina (BR)
Vehicle Dynamics and Control Systems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon