Many activities in laboratories at Purdue require user movement that cannot be carefully orchestrated or planned out, e.g., in our hardware, manufacturing, or propulsion labs. In such environments, it is challenging for users to consciously maintain the required safe social distance. This project provides a technical approach to proactively monitor the distance between users utilizing the Bluetooth transmission-reception signal strength (RSSI). We use a lightweight machine learning model to map the signal strength to the distance and infer the direction of motion between any two users. The technology builds on a long line of research in the area of wireless signals, some of which has been carried out in our lab. It is lightweight (can be easily carried as a lanyard worn by users), low cost (less than $15 when produced in bulk), privacy preserving (no data need to be shared to any other organizations), proactive (provides warning messages prior to approaching unsafe distance). We have shown its effectiveness in our preliminary experiments.

Abstract We use a network model to choose retail prices in a grocery logistics system consisting of a warehouse (managed by a manufacturer) that supplies stores (managed by a retailer). We model retail prices as endogenous decisions that respond to store‐level cost and demand parameters. The retail prices are chosen to maximize the retailer's expected profits. The retail environment is captured by a three‐segment retail customer model where segments differ in their reservation price, size, and propensity to stockpile. The resulting network model chooses retail prices each period to optimize profits across the horizon. Retail price variation across time is profit‐maximizing because of the promotion sensitivity of the retail environment. We also model the impact of retail price variation on the manufacturer costs, warehouse inventory levels, and associated manufacturer expected profit. The suggested model is fit to a dataset consisting of retail prices and associated sales of canned soup. The model parameters as well as the residual variance are included in the decision model that generates the optimal retail prices that maximize the expected retail profit. We use model runs from the empirical dataset to show that (i) retail price variation can be profit‐maximizing for the retailer, (ii) retail market‐share constraints can decrease both manufacturer and retailer profits, and (iii) manufacturer price variation can be beneficial for the manufacturer and the retailer. The results show that manufacturer and retailer price variation can play a valuable role in improving logistics system performance in promotional retail environments. © 2001 John Wiley & Sons, Inc.