Learning-Based Safety-Aware Task Scheduling for Efficient Human-Robot Collaboration

TL;DR

This paper introduces a deep learning-based safety-aware task scheduling method for human-robot collaboration that reduces cycle times without prior safety logic knowledge, improving efficiency and safety.

Contribution

It presents a novel framework that models safety-induced speed reductions directly from data, enabling efficient task scheduling without explicit safety logic prediction.

Findings

Significant reduction in cycle times in experiments

Model effectively captures safety interaction effects

Framework generalizes across different safety logics

Abstract

Ensuring human safety in collaborative robotics can compromise efficiency because traditional safety measures increase robot cycle time when human interaction is frequent. This paper proposes a safety-aware approach to mitigate efficiency losses without assuming prior knowledge of safety logic. Using a deep-learning model, the robot learns the relationship between system state and safety-induced speed reductions based on execution data. Our framework does not explicitly predict human motions but directly models the interaction effects on robot speed, simplifying implementation and enhancing generalizability to different safety logics. At runtime, the learned model optimizes task selection to minimize cycle time while adhering to safety requirements. Experiments on a pick-and-packaging scenario demonstrated significant reductions in cycle times.