Synthesis and prototyping of a backdrivable parallel robot for metal finishing tasks

摘要

This article presents the synthesis, control and experimental validation of a backdrivable three-degree-of-freedom translational mini robot used to control the interaction between a robot and a machined part during finishing tasks, such as polishing, sanding and deburring without requiring the use of a force/torque sensor. The mini robot acts as an active contact flange, allowing an industrial robot (the macro robot) to adapt to a part using an impedance control algorithm. Firstly, different three-degree-of-freedom parallel robot architectures are compared and the most suitable architecture is selected. Geometrical properties are chosen for the robot and the physical capabilities of the architecture are predicted to ensure that the design criteria are satisfied. An impedance control algorithm is then developed for the mini robot. The macro-mini system is formed by installing the mini robot on a gantry robot. Sanding tests are carried out in order to validate the performance of the system and the mini robot is compared to other contact flanges already available on the market. Finally, a method allowing the determination of the magnitude of the friction forces in the mini robot is presented and a preliminary friction compensation algorithm is developed. As opposed to existing tools, the novel mini robot proposed in this work is based on a compact parallel architecture, which makes it possible to ensure the backdrivability of the system in three directions. An impedance control algorithm can therefore be implemented thereby providing stability even with stiff environments and eliminating the need for a force/torque sensor. • Synthesis and design of a 3-dof backdrivable robot for sensorless force control. • Design of a prototype and implementation of a customized impedance controller. • Experimental validation using a macro-mini approach. • Experimental determination of the force control capability. • Development of a friction estimation model and validation.