This　paper　studies　control　strategies　of　intelligent　vehicles　at　unsignalized　intersections.　By　considering　the　interaction　among　multiple　vehicles　and　communication　disturbances,　the　problem　is　formulated　as　a　robust　differential　game　in　which　the　controlled　vehicle　computes　actions　using　disturbed　information　of　locally　neighboring　vehicles.　Both　cooperative　and　non-cooperative　differential　game　models　are　considered.　The　controlled　vehicle　optimizes　its　own　cost　in　the　non-cooperative　game　while　coordinates　its　strategy　with　other　vehicles　to　optimize　a　joint　cost　in　the　cooperative　game.　We　show　that　the　local　optimal　strategy　of　each　intelligent　vehicle　defined　by　a　single　optimization　problem　converges　to　global　robust　Nash　equilibrium　in　the　non-cooperative　game,　and　converges　to　the　global　robust　Pareto-Nash　equilibrium　in　the　cooperative　game.　The　effectiveness　of　the　robust　differential　game　method　is　verified　by　simulations　under　two　scenarios.　Results　show　that　under　the　proposed　differential　game　approach,　vehicles　pass　through　unsignalized　intersections　more　quickly　than　methods　using　traditional　discrete　game　approaches.　In　addition,　vehicles　can　avoid　colliding　with　each　other　and　obstacles　at　the　presence　of　communication　disturbances.　IEEE