An observer robustified control barrier function filter for vehicle control at the limits of handling

Vehicles capable of operating up to the limits-of-handling can improve safety in emergency maneuvers. In light of this, this work proposes a method to robustly anticipate when a vehicle approaches its limits-of-handling and safely contain the vehicle dynamics to within these limits. First, input-to-state stable nonlinear observers are designed to estimate errors in the dynamics of a nominal vehicle model. These errors are translated into improved estimates of tire-road forces for real-time detection of tire saturation. Next, a robustifed control barrier function based quadratic program (RCBF-QP) is designed to filter control commands of a nonlinear model predictive controller that uses the nominal vehicle model for prediction. The observed model errors are incorporated into the RCBF-QP to create robustified safety-critical constraints that maintain the vehicle dynamics within the limits-of-handling. The observers and the RCBF-QP are experimentally validated on a full-scale vehicle and demonstrate the ability to retain motion control at the handling limits despite modeling errors.