In　this　article,　the　problem　of　human　intervention　and　autonomous　controller　design　for　human-agent　interaction　systems　is　addressed.　In　particular,　a　human　drift　diffusion　model　is　developed　for　second-order　linear　multiagent　systems　subject　to　unknown　external　disturbances.　The　proposed　human　drift　diffusion　model　can　model　human　decision-making　behavior　using　multiple　sources　of　human　decision-making　information.　Accurate　human　intervention　timing　is　obtained　by　setting　varying　thresholds　for　different　decision-making　information.　In　addition,　a　fixed-time　sliding　mode　adaptive　behavioural　controller　is　developed　to　execute　human　decisions　in　the　framework　of　the　null-space　based　behavioral　control　method.　The　controller　guarantees　that　agents　can　follow　human　commands　given　an　arbitrary　initial　task　error　and　can　finish　tasks　in　fixed　time.　A　simulation　under　various　scenarios　shows　that　the　proposed　human　drift　diffusion　model　is　able　to　provide　appropriate　human　intervention　and　the　proposed　controller　can　guarantee　human　command　fulfillment　within　fixed　time.