Machine Learning Warehouse Picking Optimisation
Budget: $3,000 – $5,000 AUD
To optimise picking batches in a warehouse with up to 8,000 SKUs, we need to split picking orders into small segements of orders which would each fit into a plastic tote. The segments of orders can be grouped together to be picked in a single zone of a warehouse, with each order split across multiple warehouse zones.
Given a map of a warehouse, SKU data, location information and order data, split a batch of orders into the most optimal configuration, based on factors including tote utilisation and route optimisation.
The expected outcome is a Sagemaker (or equivalent) model, and an API gateway endpoint which will reply to REST queries to create picking batches.
Given a map of a warehouse, SKU data, location information and order data, split a batch of orders into the most optimal configuration, based on factors including tote utilisation and route optimisation.
The expected outcome is a Sagemaker (or equivalent) model, and an API gateway endpoint which will reply to REST queries to create picking batches.