Welding　is　a　major　manufacturing　process　that　joins　two　or　more　pieces　of　materials　together　through　heating/　mixing　them,　with　or　without　pressure,　as　they　cool　and　solidify.　The　goal　of　welding　manufacturing　is　to　join　materials　together　to　meet　service　requirements　at　the　lowest　costs.　Advanced　welding　manufacturing　(AWM)　is　to　use　scientific　methods　to　realize　this　goal.　It　involves　three　steps:　(1)　pre-design　that　selects　process　and　joint　design　based　on　available　processes　(properties,　capabilities,　and　costs);　(2)　design　that　uses　models　to　predict　the　result　from　a　given　set　of　welding　parameters　and　minimizes　a　cost　function　for　optimizing　the　welding　parameters;　(3)　real-time　sensing　and　control　that　overcome　the　deviations　of　welding　conditions　from　their　nominal　ones　used　in　optimizing　the　welding　parameters　by　adjusting　the　welding　parameters　based　on　such　realtime　sensing　and　feedback　control.　While　step　(1)　and　(2)　are　pre-manufacturing　designs,　step　(3)　is　the　step　during　manufacturing　that　must　be　addressed　by　manufacturers.　This　report　reviews　and　analyzes　the　state-ofthe-art　in　real-time　sensing　of　the　gas　metal　arc　welding,　that　is　the　most　widely　used　robotic　welding　process,　including　seam　tracking,　machine　vision,　weld　pool　monitoring,　machine　learning,　etc.