The　phenomenon　of　population　aging　is　escalating,　and　China　is　rapidly　reaching　100　million　empty-nesters　as　a　result　of　the　country＇s　uneven　regional　economic　development　and　declining　population　growth.　We　created　an　emergency　robot　system　for　detecting　geriatric　behavior　due　to　the　issue　that　empty-nesters　may　experience　acute　disease　or　other　emergency　situation　without　prompt　medical　attention.　To　accomplish　our　goals,　we　employ　the　YOLO　V3　algorithm　to　recognize　persons　in　a　complicated　setting.　Meanwhile　we　use　the　AlphaPose　model　firstly　in　order　to　detect　the　joint　points　of　the　elderly.　And　at　that　basis,　we　use　the　ST-GCN　models　to　complete　the　posture　estimation　and　detection,　finish　the　categorization　of　postures.　In　this　way,　we　could　determine　whether　the　elderly　are　in　an　emergency　scenario　or　not.　Also,　the　M5StickC　open-source　bracelets　are　used　to　improve　the　accuracy　of　the　emergency　detection.　They　were　used　concurrently　to　measure　information　including　acceleration　to　assist　in　determining　whether　the　elderly　person　is　in　emergency　at　the　same　time.　Once　the　emergency　situation　has　been　verified,　a　robot　car　will　be　sent　to　quickly　bring　first　aid　supplies　to　the　elderly.　This　approach　can　prevent　losing　the　initial　opportunity　to　perform　first　aid.　©　The　Author(s),　under　exclusive　license　to　Springer　Nature　Switzerland　AG　2024.