Jeff Christensen, vice president of product with Seegrid, talks about how users of autonomous mobile robots can combine the units with analytics capabilities, to see, measure and improve material flow in the warehouse.

The adoption of any new technology tool requires the setting of a baseline, defining the user’s expectations of how it will perform. It’s no different for AMRs, says Christensen. Once that exercise is carried out, “you can start doing more interesting things.” But it’s crucial for the resulting data to be usable “within the timeframe of action.” Historical information showing what happened in a previous quarter is of no value in addressing current problems. If a warehouse operation identifies performance problems in a particular shift, for example, it needs to be able to take action before the shift is over.

Managers at the receiving end of all that data also need to know how it will lead to informed actions that can improve operations. AMRs are still “in their early days” with respect to their ability to provide a description of the current state. But as the technology matures, it will be able to deliver data in a prescriptive mode, providing guidance on actions that need to be taken. “It’s a lifecycle journey that data is on,” says Christensen. “We’ve seen this play out in other technologies. AMRs are on the same path.”

“Prescriptive” data requires, of course, artificial intelligence. AI is especially well-suited to discover patterns within large data sets, then use that insight to generate recommendations for action. For now, humans remain in the equation to make ultimate decisions, “and will be around for a long time.” But as the system learns, it becomes more trusted by human managers in its ability to output useful decisions.