Automated Guided Vehicle (AGV), serving as an important tool for wide industrial applications, suffers many control problems for coupling impacts of rotation and shift moving. We present a decoupling controller to improve the kinematic performance of AGV in the paradigm of PID control. For adaptive tuning of PID, a heuristic optimization strategy, named Beetle Antennae Search (BAS), is employed to generate proper adjustment of parameter estimation. Finally, the effectiveness of the algorithm is proved by simulation and experimental results.