PCARNN-DCBF: Minimal-Intervention Geofence Enforcement for Ground Vehicles
This addresses the challenge of reconciling high-fidelity learning with verifiable control for enforcing operational design domains in ground vehicles, representing a domain-specific incremental improvement.
The paper tackles the problem of runtime geofencing for ground vehicles by introducing PCARNN-DCBF, a pipeline that integrates a physics-encoded neural network with a control barrier function to enforce constraints while maintaining verifiable control, and experiments in CARLA show it significantly outperforms analytical and unstructured neural baselines.
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.