Hybrid Control for Robotic Nut Tightening Task

TL;DR

This paper presents a hybrid control system for robotic nut tightening that combines force and position control, achieving faster tightening with less contact force and robustness to initial condition variations.

Contribution

It introduces a hierarchical motion-primitive planner and a control-switching scheme, with open-source implementation, advancing autonomous robotic screw tightening methods.

Findings

14% faster tightening compared to baseline

40 times less contact force applied

Robustness to initial condition variance

Abstract

An autonomous robotic nut tightening system for a serial manipulator equipped with a parallel gripper is proposed. The system features a hierarchical motion-primitive-based planner and a control-switching scheme that alternates between force and position control. Extensive simulations demonstrate the system's robustness to variance in initial conditions. Additionally, the proposed controller tightens threaded screws 14% faster than the baseline while applying 40 times less contact force on manipulands. For the benefit of the research community, the system's implementation is open-sourced.