Safe and Transparent Robots for Human-in-the-Loop Meat Processing

TL;DR

This paper presents a safety and transparency framework for collaborative robots in meat processing, enabling safe, understandable, and flexible human-robot collaboration to address industry labor shortages.

Contribution

It introduces novel safety and transparency mechanisms, including hand detection, force sensing, and communication interfaces, for general-purpose meat processing robots working alongside humans.

Findings

The safety system effectively halts robots when humans are nearby.

The transparency interface successfully communicates robot uncertainty.

User study confirms improved safety and understanding in human-robot collaboration.

Abstract

Labor shortages have severely affected the meat processing sector. Automated technology has the potential to support the meat industry, assist workers, and enhance job quality. However, existing automation in meat processing is highly specialized, inflexible, and cost intensive. Instead of forcing manufacturers to buy a separate device for each step of the process, our objective is to develop general-purpose robotic systems that work alongside humans to perform multiple meat processing tasks. Through a recently conducted survey of industry experts, we identified two main challenges associated with integrating these collaborative robots alongside human workers. First, there must be measures to ensure the safety of human coworkers; second, the coworkers need to understand what the robot is doing. This paper addresses both challenges by introducing a safety and transparency framework for general-purpose meat processing robots. For safety, we implement a hand-detection system that continuously monitors nearby humans. This system can halt the robot in situations where the human comes into close proximity of the operating robot. We also develop an instrumented knife equipped with a force sensor that can differentiate contact between objects such as meat, bone, or fixtures. For transparency, we introduce a method that detects the robot's uncertainty about its performance and uses an LED interface to communicate that uncertainty to the human. Additionally, we design a graphical interface that displays the robot's plans and allows the human to provide feedback on the planned cut. Overall, our framework can ensure safe operation while keeping human workers in-the-loop about the robot's actions which we validate through a user study.