This　study　investigates　a　desktop　robot　system　which　is　designed　with　adopting　the　embedded　technology.　The　size　of　the　robot　is　less　than　200cm　3.　The　system　collects　images　by　a　global　camera,　and　navigates　the　robot　with　wireless　communication　components.　The　research　focusing　on　autonomous　mapping　has　been　carried　out　on　the　desktop　robot　system.　The　autonomous　mapping　algorithm　in　this　paper　is　based　on　GSOM　(Growing　Self-organizing　Map)　algorithm.　By　continuously　increasing　new　neurons　in　the　growth　of　network　scale,　the　GSOM　mapping　algorithm　applies　a　small　number　of　neurons　to　generate　a　topological　map　describing　the　environmental　characteristics.　Through　testing　GSOM　mapping　algorithm　on　the　robot　system,　the　experimental　results　show　that　the　GSOM-based　mapping　method　is　feasible;　and　the　robot　system　shows　similar　biological　behaviors　of　autonomous　intelligence.　©　2009　IEEE.