Nonlinear Coordinated Steering and Braking Control of Vision-Based Autonomous Vehicles in Emergency Obstacle Avoidance

Abstract

The main aim of the project is to dynamic control design for automated driving of vision-based autonomous vehicles, with a particular focus on the coordinated steering and braking control in emergency obstacle avoidance. An autonomous vehicle uses a complex multi-input and multi-output structure, which possesses the features of parameter uncertainties and strong nonlinearities, and the fixed phenomena of lateral and longitudinal dynamics are clear in a combined cornering and braking movement. The effective coordinated control system for automated driving is wished-for to deal with these coupled and nonlinear features and eliminate the disturbances. First, a vision algorithm is constructed to detect the orientation path and offer the local location information between vehicles and reference path in real time. Then, a novel coordinated steering and braking control approach is proposed based on the nonlinear back stepping control theory and the adaptive fuzzy sliding-mode control method.

Finally, experimental tests evident that the proposed control strategy possesses encouraging tracking performance and enhances the riding comfort and constancy of autonomous vehicles.