Learning-based Safe Motion Control of Vehicle Ski-Stunt Maneuvers

This paper presents a safety guaranteed control method for an autonomous vehicle ski-stunt maneuver, i.e., a vehicle moving with two side wheels. To capture the vehicle dynamics precisely, a Gaussian process model is used as additional correction. We construct a probabilistic exponential control barrier function (CBF) to guarantee the planar motion safety. The CBF and the balance equilibrium manifold are enforced as the constraints into a safety critical control. Under the proposed control method, the vehicle can avoid the collision and safely maintain the balance for autonomous ski-stunt maneuvers. We conduct numerical simulation validation to demonstrate the control design. Preliminary experiments are also presented to confirm the learning-based motion control using a scaled truck for autonomous ski-stunt maneuvers.