In order to facilitate a precise collision avoidance scheme capability for ships under low speed in constrict water, a novel intelligent coordinate control approach of ship steering and main propulsion is proposed. In the research an innovative self-training optimizing search method is presented. The optimizing process is based on particle swarm optimization algorithm and off-line training data. The training data is obtained from trial manoeuvres based on computer simulation. This support system has been developed to help ship operators make a precise collision avoidance decision, whilst simultaneously reducing the burden of bridge data processing. The application results show that the designed intelligent coordinate controller performed well to implement the optimizing control of ship collision avoidance.