The　dynamic　control　problem　for　coordinated　motion　of　a　free-floating　dual-arm　space　robot　system　was　discussed.　According　to　the　momentum　conservation　law,　the　dynamic　equations　of　dual-arm　space　robot　system　were　established　through　Lagrange　equation　of　the　second　kind.　Based　on　the　above　results,　a　fuzzy　wavelet　based　neural　network　scheme　was　designed　for　dual-arm　space　robot　system　with　unknown　system　parameters.　The　scheme　achieves　the　coordinated　motion　of　the　base　attitude　and　the　joint　angle　in　joint　space.　The　control　scheme　needs　neither　to　parameterize　the　dynamic　equations　of　the　system　linearly,　nor　knows　any　system　parameters.　Further　more,　its　network　parameters　are　updating　on-line　by　back　propagation　algorithm　so　that　fuzzy　neural　network　has　strong　ability　of　self-learning　and　self-adapting.　Thus　time-consuming　off-line　training　process　is　not　required.　Simulation　results　of　a　planar　dual-arm　space　robot　system　confirms　that　the　proposed　control　scheme　is　effective　and　feasible.