This　paper　considers　a　nonparametric　M-estimator　of　a　regression　function　for　functional　stationary　ergodic　data.　More　precisely,　in　the　ergodic　data　setting,　we　consider　the　regression　of　a　real　random　variable　Y　over　an　explanatory　random　variable　X　taking　values　in　some　semi-metric　abstract　space.　Under　some　mild　conditions,　the　weak　consistency　and　the　asymptotic　normality　of　the　M-estimator　are　established.　Furthermore,　a　simulated　example　is　provided　to　examine　the　finite　sample　performance　of　the　M-estimator.