This paper presents an adaptive haptic shared control framework wherein a driver and an automation system are physically connected through a motorized steering wheel. The automation system is modeled as an intelligent agent that is not only capable of making decisions but also monitoring the human’s behavior and adjusting its behavior accordingly. To enable the automation system to smoothly exchange the control authority with the human partner, this paper introduces a novel self-regulating impedance controller for the automation system. To determine an optimal modulation policy, a cost function is defined. The terms of the cost function are assigned to minimize the performance error and reduce the disagreement between the human and automation system. To solve the optimal control problem, we employed a nonlinear model predictive approach and used the continuation generalized minimum residual method to solve the nonlinear cost function. To demonstrate the effectiveness of the proposed approach, simulation studies consider a scenario where the human and the automation system both detect an obstacle and negotiate on controlling the steering wheel so that the obstacle can be avoided safely. The simulations involve four interaction modes addressing the cooperation status (cooperative and uncooperative) and the desired direction of the control transfer (active safety and autopilot). The results of the numerical studies show that when the automation system acts as autopilot, using the proposed modulation method, the automation adopts smaller impedance controller gains, which results in a smaller disagreement between the human and automation systems. On the other hand, when the human’s control command is insufficient, by modulating and adopting larger values for the impedance controller parameters, the automation system gains the control authority and ensures the safety of the obstacle avoidance task.