[Paper Review] Automatic Routing System for Intelligent Warehouses

Kelen Cristiane Teixeira Vivaldini, Jorge P. M. Galdames+5 more|arXiv (Cornell University)|Jul 13, 2023

Advanced Manufacturing and Logistics Optimization13 citations

TL;DR

A router system for intelligent warehouses computes conflict-free, optimized paths using Dijkstra’s shortest path and time-window approaches, prevents jams and collisions, and adapts task priorities in real time, validated through simulations.

ABSTRACT

Automation of logistic processes is essential to improve productivity and reduce costs. In this context, intelligent warehouses are becoming a key to logistic systems thanks to their ability of optimizing transportation tasks and, consequently, reducing costs. This paper initially presents briefly routing systems applied on intelligent warehouses. Then, we present the approach used to develop our router system. This router system is able to solve traffic jams and collisions, generate conflict-free and optimized paths before sending the final paths to the robotic forklifts. It also verifies the progress of all tasks. When a problem occurs, the router system can change the task priorities, routes, etc. in order to avoid new conflicts. In the routing simulations, each vehicle executes its tasks starting from a predefined initial pose, moving to the desired position. Our algorithm is based on Dijkstra's shortest path and the time window approaches and it was implemented in C language. Computer simulation tests were used to validate the algorithm efficiency under different working conditions. Several simulations were carried out using the Player/Stage Simulator to test the algorithms. Thanks to the simulations, we could solve many faults and refine the algorithms before embedding them in real robots.

Motivation & Objective

• Motivate automation of logistic processes to improve productivity and reduce costs in warehouses.
• Propose a routing system that generates conflict-free, optimized paths for robotic forklifts.
• Enable real-time task and route adjustment to avoid new conflicts when issues arise.
• Validate the routing algorithm through computer simulations and robotics-oriented test environments.

Proposed method

• Base the routing algorithm on Dijkstra’s shortest path for pathfinding.
• Incorporate time-window approaches to handle scheduling and precedence constraints.
• Implement the routing solution in the C programming language.
• Use simulations to verify efficiency under varying working conditions.
• Employ the Player/Stage Simulator to test the algorithms before real-robot deployment.

Experimental results

Research questions

• RQ1 Can a routing system generate conflict-free, optimized paths for multiple robotic forklifts in an intelligent warehouse?
• RQ2 How effectively can time-window approaches reduce jams and collisions in warehouse routing?
• RQ3 To what extent can the router adapt task priorities and routes to avoid new conflicts when problems occur?
• RQ4 Do simulation-based validations support the efficiency of the routing algorithm under different workloads?

Key findings

• The router system can solve traffic jams and collisions by generating conflict-free and optimized paths before dispatching final paths to forklifts.
• It verifies progress of all tasks and can adjust priorities or routes when problems occur to avoid new conflicts.
• Simulations demonstrate efficiency of the algorithm under different working conditions.
• The approach was tested using the Player/Stage Simulator to refine algorithms prior to real-robot embedding.