Process parameters are the key factors determining the quality of laser welding aluminum alloys. Therefore, to ensure good weld morphology quality, a combined response surface methodology and particle-swarm optimization (RSM-PSO) algorithm was proposed to explore the optimal process parameters to laser weld 2 mm-thick 6061 aluminum alloy sheets. The experimental design of the fiber laser welding was performed using Desk-Expert 10.0 software. In response to weld collapse and sheet bending, multiple linear regression of the welding parameters was established. The effects of various process parameters on the welding quality were analyzed, and the particle-swarm intelligence algorithm was used for optimization. The results show that under the experimental conditions of this study, the scanning speed and defocusing have a strong influence on the weld collapse, and the laser power and scanning speed have a great influence on the sheet deformation. The optimal process parameters are laser power, scanning speed, and defocusing amount of 2629 W, 6.85 mm/s, and -0.18 mm, respectively. Under these parameters, the collapse depth and bending of the 6061 aluminum alloy sheet are only 85.66 μm and 1.2 mm, respectively, indicating that the parameters obtained via this algorithm can effectively improve the welding quality.