Due　to　the　current　focus　of　research　on　ankle　rehabilitation　robots　on　structural　design,　there　is　still　limited　research　on　ankle　human-machine　interaction　technology.　In　order　to　enable　rehabilitation　robots　to　conduct　personalized　rehabilitation　training　based　on　patients＇　ankle　movement　intentions,　we　propose　a　new　ankle　motion　recognition　method　based　on　plantar　pressure.　First,　we　designed　a　plantar　pressure　collection　system　based　on　array　sensors.　Then,　we　collected　nine　types　of　ankle　joint　motion　pressure　data　from　five　volunteers　and　conducted　algorithm　selection,　data　processing,　and　algorithm　optimization.　Finally,　we　proposed　a　small　sample　optimization　algorithm　based　on　support　vector　machine,　with　an　average　recognition　rate　of　93.16%.　The　recognition　method　proposed　in　this　paper　can　be　combined　with　ankle　rehabilitation　robots　to　achieve　active　rehabilitation　functions,　laying　the　foundation　for　the　clinical　application　of　active　rehabilitation　technology.