Service　robots　have　already　been　able　to　implement　explicit　and　simple　tasks　assigned　by　human　beings,　but　they　still　lack　the　ability　to　act　like　humans　who　can　analyze　the　assigned　task　and　ask　questions　to　acquire　supplementary　information　to　resolve　ambiguities　from　the　environment.　Inspired　by　this　point,　we　fuse　verbal　language　and　pointing　gesture　information　to　enable　a　robot　to　execute　a　vague　task,　such　as　＇bring　me　the　book＇.　In　this　paper,　we　propose　a　system　integrating　human-robot　dialogue,　mapping　and　action　execution　planning　in　unknown　3D　environments.　We　consider　grounding　natural　language　commands　to　a　sequence　of　low-level　instructions　that　can　be　executed　by　the　robot.　To　express　the　targets　location　which　is　pointed　to　by　the　user　in　a　global　fixed　frame,　we　use　a　SLAM　approach　to　build　the　environment　map.　Experimental　results　demonstrate　that　a　humanoid　robot　NAO　can　acquire　the　skill　based　on　our　proposed　approach　in　unknown　environment.　©　2016　IEEE.