Currently, the bionic robotic fish is primarily devoted to the bionic appearance of fish and rarely involves the bionic swimming posture. However, biological studies have proved that fish have extraordinary swimming ability, so it is necessary to imitate the swimming posture of fish. This paper introduces a manta ray robot driven by three fin rays, with its pectoral fins being structurally simulated using silicone rubber. According to the manta ray’s integrated gliding and flapping propulsion characteristics, we established a central-pattern-generator-based (CPG-based) biomimetic-motion-control method to realize the manta ray robot’s integrated gliding and flapping propulsion control. We designed an evaluation method of motion–posture similarity for the manta ray robot and optimized the control parameters to enhance the resemblance to the manta ray robot. The experimental results show that the online similarity-optimization method based on particle swarm optimization enhances the resemblance to 86.93%, and its swimming stability is also improved to some extent, which verifies the effectiveness of the optimization method. This study provides a new idea for optimizing motion control of the manta ray robot and realizing environmental affinity.