Learning Efficient and Fair Policies for Uncertainty-Aware Collaborative Human-Robot Order Picking

TL;DR

This paper introduces a multi-objective Deep Reinforcement Learning method for optimizing human-robot order picking, balancing efficiency and fairness in stochastic warehouse environments, with policies outperforming benchmarks and transferring well across scenarios.

Contribution

It proposes a novel DRL approach with a graph-based warehouse state model for effective allocation policies in collaborative order picking systems.

Findings

Policies outperform benchmarks in efficiency and fairness.

Policies demonstrate good transferability across different warehouse sizes.

The approach finds non-dominated trade-off policies.

Abstract

In collaborative human-robot order picking systems, human pickers and Autonomous Mobile Robots (AMRs) travel independently through a warehouse and meet at pick locations where pickers load items onto the AMRs. In this paper, we consider an optimization problem in such systems where we allocate pickers to AMRs in a stochastic environment. We propose a novel multi-objective Deep Reinforcement Learning (DRL) approach to learn effective allocation policies to maximize pick efficiency while also aiming to improve workload fairness amongst human pickers. In our approach, we model the warehouse states using a graph, and define a neural network architecture that captures regional information and effectively extracts representations related to efficiency and workload. We develop a discrete-event simulation model, which we use to train and evaluate the proposed DRL approach. In the experiments, we demonstrate that our approach can find non-dominated policy sets that outline good trade-offs between fairness and efficiency objectives. The trained policies outperform the benchmarks in terms of both efficiency and fairness. Moreover, they show good transferability properties when tested on scenarios with different warehouse sizes. The implementation of the simulation model, proposed approach, and experiments are published.