Robotic warehousing operations: a learn-then-optimize approach to large-scale neighborhood search

TL;DR

This paper introduces a learn-then-optimize large-scale neighborhood search method for robotic warehousing, improving efficiency and congestion management in large robotic fleets through a novel machine learning-guided optimization approach.

Contribution

It presents a new learn-then-optimize algorithm for large-scale neighborhood search, integrating machine learning with optimization for robotic warehousing operations.

Findings

Outperforms state-of-the-art methods in practical warehouse problems.

Enhances robotic fleet utilization and coordination.

Reduces congestion and improves throughput.

Abstract

The rapid deployment of robotics technologies requires dedicated optimization algorithms to manage large fleets of autonomous agents. This paper supports robotic parts-to-picker operations in warehousing by optimizing order-workstation assignments, item-pod assignments and the schedule of order fulfillment at workstations. The model maximizes throughput, while managing human workload at the workstations and congestion in the facility. We solve it via large-scale neighborhood search, with a novel learn-then-optimize approach to subproblem generation. The algorithm relies on an offline machine learning procedure to predict objective improvements based on subproblem features, and an online optimization model to generate a new subproblem at each iteration. In collaboration with Amazon Robotics, we show that our model and algorithm generate much stronger solutions for practical problems than state-of-the-art approaches. In particular, our solution enhances the utilization of robotic fleets by coordinating robotic tasks for human operators to pick multiple items at once, and by coordinating robotic routes to avoid congestion in the facility.