The invention provides a robot system-oriented human-in-the-loop decision modeling and control method. The method comprises the steps of robot task design, human decision information selection, human decision behavior modeling, human decision task design and fixed time sliding mode adaptive behavior controller design. The method comprises the steps: firstly acquiring an output information value after a robot executes a task, then selecting robot position deviation information and speed deviation information as decision information of a person, using a human decision drift diffusion model as a modeling method, modeling decision behaviors of the person according to the decision information of the person, after a decision threshold value is reached, selecting to execute a human intervention behavior, designing a human decision task, finally designing an adaptive behavior controller based on a fixed time sliding mode control method, and when the robot cannot autonomously control to complete the task, executing the human decision task to complete the work task in finite time, According to the method, the man-machine composite task can be completed within limited time, and man-machine task co-fusion is realized.