An Intelligent AI Alternative To Warehouse Robots
As e-commerce accelerated, distribution centres increased hiring and many are considering robotics to supplement their human workforce and ensure fast, efficient and accurate fulfilment. But robots are not always the best solution. Most DCs need a mix of strategies to keep up.
Many DCs are turning to smart software that uses Artificial Intelligence to optimise warehouse processes and make picking easier and faster for hourly associates. A number of facilities have doubled productivity and dramatically increased throughput using AI, without making any changes to picking processes or adding new automation or infrastructure.
AI-based optimisation attacks a major component of inefficiency by reducing travel. This is the same principal that underlies robotic picking systems, making AI a natural complement – and in many cases an alternative – to robots.
Read on to learn more, or request information about simulating the potential travel savings using AI in your DC.
Reducing Travel Time With Robots
In a conventional, non-automated picking process, travel often represents the majority of the time in a DC associate’s day – ranging from 40-70 percent in most operations. Like earlier goods-to-person automation systems, robotic goods-to-person systems like those used by Amazon eliminate travel in the picking process. (Read about other robotic picking strategies here.)
Robotic picking systems are groundbreaking, but they are not a good fit for all DCs or for all products and customer types. For example, autonomous robots are generally not feasible for traditional grocery DCs supporting retail stores, or for B2B distributors serving a mix of retailers, wholesalers, and direct-to-consumer customers.
This is where AI-based software comes in, both as a complement to optimise robotic processes or as an alternative to robots for non-automated picking.
Double Picking Productivity With Artificial Intelligence
In most DCs, order picking systems use simple business rules to plan, organise and execute order picking. By applying AI to the problem, DCs can evaluate travel alongside other factors to determine how to most efficiently organise, group (or batch) and sequence picks to reduce travel time.
In each picking areas the AI algorithms create optimal batches for picking items to trolleys. Likewise, the algorithms can create optimal pallets of cases or group together pre-defined pallets in two or three pallet assignments of work. In simulations with dozens of DCs, intelligent batching alone demonstrated travel savings up to 40 percent per assignment.
The second element of this is to optimise travel paths. Traditional picking systems use simple pick sequences that direct workers up one aisle and down the next in a snaking pattern. AI-based tools can map out an ideal travel path to ensure workers travel the shortest distance to complete their assignments, whether that is picking, replenishment, or another task.
Several facilities have doubled productivity using AI-based travel optimisation tools, making tasks easier and better for hourly staff. This approach doesn’t require new hardware or changes to picking processes. It is a non-disruptive technology that can nevertheless transform warehouse operations and efficiency.
Interested in reducing travel time in your DC? Get information about simulating your travel savings or view an on-demand demonstration.
