English

Container Unloading via Reinforcement Learning: Picking Order, Deadlock Avoidance, and Proof-of-Concept Simulation

Systems and Control 2026-05-27 v1 Systems and Control

Abstract

Unloading containers in the courier, express and parcel industry is a physically demanding and labor-intensive work. Automatizing this process is an important step towards increasing the efficiency of parcel-handling systems. This work investigates the potential of reinforcement learning to learn a policy for item selection in container unloading scenarios. For that, a simulation environment is created and a masked deep Q-learning with a specially designed neural network architecture is implemented. The results indicate that the agent can learn to select items with an average success rate of 60 %, which is significantly better than a random policy at a random chance of 20 %. The findings suggest that RL could be a promising approach for automatizing item unloading tasks in the future.

Keywords

Cite

@article{arxiv.2605.27143,
  title  = {Container Unloading via Reinforcement Learning: Picking Order, Deadlock Avoidance, and Proof-of-Concept Simulation},
  author = {Jan Rüdiger and Max Schenke and Daniel Weber},
  journal= {arXiv preprint arXiv:2605.27143},
  year   = {2026}
}
R2 v1 2026-07-22T07:34:50.089Z