Integrated optimization control strategy for vehicle longitudinal and lateral assisted driving

Abstract

In order to coordinate the control objectives of the longitudinal and lateral auxiliary driving system of the vehicle and the vehicle dynamics control requirements, this paper takes the four-wheel independent drive electric vehicle as the control object, and combines deep learning and model predictive control to establish the vehicle generalized control force prediction-dynamic optimization distribution control strategy. The upper-level algorithm calculates the generalized control force that meets the vehicle control requirements according to the reference objectives of the longitudinal and lateral auxiliary driving strategies; the middle-level module includes the vehicle expected generalized force neural network prediction model and the active set numerical solution algorithm; the lower level calculates the tire slip rate and sideslip angle according to the expected tire force, realizes the tire force control requirements by controlling the motor torque and the braking system, and adjusts the vehicle movement direction through the steering system. This paper uses simulation tests and hardware-in-the-loop tests to verify the algorithm. The results show that the established algorithm can simultaneously meet the longitudinal and lateral control requirements of the vehicle, with a lateral path following error of 0.0117 m and a vehicle speed error of 0.59 km/h.