SCCRUB: Surface Cleaning Compliant Robot Utilizing Bristles

TL;DR

This paper presents a soft robotic arm capable of effectively scrubbing surfaces by exerting continuous torque, achieved through a neural network-based inverse kinematics model, enabling safe and efficient cleaning of adhered residues.

Contribution

The work introduces a neural network trained to control a soft robot arm's force and position, enabling it to perform scrubbing tasks traditionally difficult for soft robots.

Findings

Successfully scrubbed burnt food residue and sticky substances with 99.7% contamination removal

Demonstrated soft robot's ability to exert continuous torque safely around humans

Neural network enabled open-loop force and position control for effective scrubbing

Abstract

Scrubbing surfaces is a physically demanding and time-intensive task. Removing adhered contamination requires substantial friction generated through pressure and torque or high lateral forces. Rigid robotic manipulators, while capable of exerting these forces, are usually confined to structured environments isolated from humans due to safety risks. In contrast, soft robot arms can safely work around humans and adapt to environmental uncertainty, but typically struggle to transmit the continuous torques or lateral forces necessary for scrubbing. Here, we demonstrate a soft robotic arm scrubbing adhered residues using torque and pressure, a task traditionally challenging for soft robots. We train a neural network to learn the arm's inverse kinematics and elasticity, which enables open-loop force and position control. Using this learned model, the robot successfully scrubbed burnt food residue from a plate and sticky fruit preserve from a toilet seat, removing an average of 99.7% of contamination. This work demonstrates how soft robots, capable of exerting continuous torque, can effectively and safely scrub challenging contamination from surfaces.