In　this　paper,　a　novel　adaptive　neural　network　(NN)　controller　is　proposed　for　trajectory　tracking　of　autonomous　underwater　vehicles　(AUVs)　in　the　presence　of　model　errors　and　external　disturbance.　A　command　filtered　technique　is　used　to　tackle　the　problem　of　＂explosion　of　complexity＂　inherent　in　the　conventional　backstepping　method.　Furthermore,　the　norm　of　the　ideal　weighting　vector　in　neural　network　systems　is　considered　as　the　estimation　parameter,　such　that　only　one　parameter　is　adjusted.　It　is　also　shown　that　the　proposed　NN　based　adaptive　robust　controller　can　guarantee　the　uniformly　ultimately　bounded　of　the　AUV　systems.　Finally　a　numerical　example　is　given　to　demonstrate　the　validity　of　the　results.