Saved in:
Bibliographic Details
Main Authors: Yu, Yinan, Scheidegger, Samuel
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.15522
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914164402814976
author Yu, Yinan
Scheidegger, Samuel
author_facet Yu, Yinan
Scheidegger, Samuel
contents Runtime geofencing for ground vehicles is rapidly emerging as a critical technology for enforcing Operational Design Domains (ODDs). However, existing solutions struggle to reconcile high-fidelity learning with the structural requirements of verifiable control. We address this by introducing PCARNN-DCBF, a novel pipeline integrating a Physics-encoded Control-Affine Residual Neural Network with a preview-based Discrete Control Barrier Function. Unlike generic learned models, PCARNN explicitly preserves the control-affine structure of vehicle dynamics, ensuring the linearity required for reliable optimization. This enables the DCBF to enforce polygonal keep-in constraints via a real-time Quadratic Program (QP) that handles high relative degree and mitigates actuator saturation. Experiments in CARLA across electric and combustion platforms demonstrate that this structure-preserving approach significantly outperforms analytical and unstructured neural baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2511_15522
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PCARNN-DCBF: Minimal-Intervention Geofence Enforcement for Ground Vehicles
Yu, Yinan
Scheidegger, Samuel
Machine Learning
Robotics
Runtime geofencing for ground vehicles is rapidly emerging as a critical technology for enforcing Operational Design Domains (ODDs). However, existing solutions struggle to reconcile high-fidelity learning with the structural requirements of verifiable control. We address this by introducing PCARNN-DCBF, a novel pipeline integrating a Physics-encoded Control-Affine Residual Neural Network with a preview-based Discrete Control Barrier Function. Unlike generic learned models, PCARNN explicitly preserves the control-affine structure of vehicle dynamics, ensuring the linearity required for reliable optimization. This enables the DCBF to enforce polygonal keep-in constraints via a real-time Quadratic Program (QP) that handles high relative degree and mitigates actuator saturation. Experiments in CARLA across electric and combustion platforms demonstrate that this structure-preserving approach significantly outperforms analytical and unstructured neural baselines.
title PCARNN-DCBF: Minimal-Intervention Geofence Enforcement for Ground Vehicles
topic Machine Learning
Robotics
url https://arxiv.org/abs/2511.15522