Prediction of users trajectories to mimic / avoid the customer behaviour during mapping tasks of an autonomous robot in retail environment

Stores today are complex spaces where the availability of information related to the behaviours of shoppers plays a key role to optimize the sales. It is also strategic to gather data in order to monitor the availability and right placement of products on the shelves. In this context, mobile robotics could support the retailers to map the current status of a store using autonomous platforms. Of course full mapping strategies could be easily implemented considering well consolidated approaches. Regarding this context, we explore the capability to mimic / avoid the customer behaviour during mapping tasks of an autonomous robot. Mapping tasks are designed to get images from cameras installed on the mobile platforms to check the planogram integrity also identifying out-of-stock issues. We propose a strategy to predict the trajectory of shoppers inside a store that could be used by the navigation planner of a robot to map highly visited areas. The approach could be also used to avoid the user(s) during their shopping in order to minimize the bother caused by the presence of a mobile platform.