Application of the Smith-Åström Predictor to robot force control

Input/output transport delay is prevalent in process control, causing performance degradation and even instability. This paper focuses on input and measurement delays in robot force control with stiff environments which tend to be susceptible to modeling error and disturbances. Traditional remedies include increasing the sampling rate, adding passive compliance, or modifying the feedback algorithm, e.g., using integral force feedback instead of proportional feedback. For force control using industrial robots, the problem is even more severe, as the loop closure is done at the outer kinematic loop through setpoint modification, which typically has long actuation latency, in addition to force measurement delay. In this paper, we apply two types of delay compensation to force control for a spring-type environment via direct cancellation: Smith Predictor, and its variant Åström Predictor. We show through simulation, and experimental validation on an industrial robot arm, that both methods significantly improve the stability margin as compared to the typical integral force control, with the Åström Predictor further improving the dynamical response by decoupling delay compensation and tracking response.

I. Introduction

When a robot interacts with its environment through contacts, e.g., in grasping, assembly, polishing, opening a door, or other physical tasks, the regulation of the contact force is important to ensure proper task execution and safety to parts, tools, environment, and the robot itself. If the contact force can be measured, such as through a wrist-mounted force/torque sensor, robot joint torque sensors, or tactile sensors, it may be fed back to the robot motion control for active contact force regulation. The stability of force control has long been studied. It is noted that the stability of direct force feedback in either position/force control or impedance control is sensitive to the input/output delays due to the sample data implementation or force measurements. The problem is particularly pronounced for stiff environments. In such situations, common remedies include increasing the sampling rate (reduce delay), adding passive compliance (reduce contact stiffness), or modifying the control algorithm to increase delay robustness. In [4], integral force control is demonstrated to enhance robustness compared to proportional feedback. Integral force feedback gain scheduling further improves robustness and performance. In teleoperation with bilateral force feedback, frequency domain damping can also enhance delay robustness [5].