Integrating Collision Avoidance, Lane Keeping, and Cruise Control With an Optimal Controller and Fuzzy Controller
This thesis presents collision avoidance integrated with lane keeping and adaptive cruise control for a car. Collision avoidance is the ability to avoid obstacles that are in the vehicle's path, without causing damage to the obstacle or car. There are three types of collision avoidance controllers, passive, active, and semi-active. This thesis is designed using active collision avoidance controllers.
There are two controllers developed for collision avoidance in this paper. They are an optimal controller and a fuzzy controller. The optimal vehicle trajectory, which maximizes the distance to an obstacle and changes lanes, is derived. The optimal collision avoidance controller is a closed loop controller; with the decisions based on the current state. The fuzzy controller makes decisions based on the system rules. A simulation environment was created to compare these two controllers as viable solutions for collision avoidance.
The environment uses MATLAB/Simulink for simulation of the vehicle as well as the optimal and fuzzy controllers. The simulation incorporates system blocks of the kinematics of a car, navigation, states, control law, and velocity controller. Once the controllers are fully developed and tested in the simulation environment, they are implemented and tested on the platform vehicle. This verifies the real world performance of the controllers.
The platform vehicle is a modified radio controlled car. This car is completely autonomous. The car has onboard sensors that allow it to follow a white piece of tape as well as detect obstacles.