An approach of cooperative hunting for multiple mobile targets by multi-robot is presented in an unknown environment

which divides the pursuit process into creating the environment map

forming the pursuiting teams and capturing the targets.The abstract sensor model is designed to search obstacles for hunters.The data sets of attribute relationship is built by consulting all of factors about capturing evaders

then the association rule data mining is used to build the pursuit groups.Through doping out the positions of targets

the puisuit game can be transformed into multi-robot path planning problems.The best path can be found in the environment map.The simulation results show that the mobile evaders can be captured effectively and efficiently

and prove the feasibility and validity of the given algorithm under dynamic environment.