According　to　the　two-dimensional　coordinate　of　users　body　gravity　center,　a　motion　control　method　was　proposed　for　the　omni-directional　intelligent　wheelchair.　Fuzzy　Kohonen　clustering　neural　network　was　used　in　the　clustering　process　of　human　gravity　center　in　order　to　judge　the　occupants　driving　direction　intention.　To　reduce　the　effect　caused　by　abnormal　clustering　center　data　points　which　were　generated　by　malfunction,　the　improvements　on　fuzzy　membership　function　and　learning　rate　of　fuzzy　Kohonen　clustering　neural　network　were　proposed　in　this　paper.　At　the　same　time,　this　motion　control　method　of　omni-directional　intelligent　wheelchair　was　combined　with　similarity　theory,　which　was　focus　on　eliminating　the　isolated　points　generated　by　malfunction　in　the　application　phase.　Comparative　experiments　confirmed　that　the　improved　fuzzy　Kohonen　clustering　neural　network　algorithm　was　with　lower　error　rate　than　the　traditional　one.　Physical　experiments　proved　that　this　algorithm　could　remove　the　isolated　gravity　center　points　that　were　generated　by　malfunction,　and　it　could　reduce　the　error　between　the　desired　moving　directions　and　the　actual　moving　directions.　The　simulation　results　further　demonstrated　the　practical　feasibility　and　validity　of　the　proposed　control　algorithm,　and　the　motion　control　precision　was　also　improved　for　omni-directional　intelligent　wheelchair.　©　2013　IEEE.