Improving dynamic decision making through RFID: A partially observable Markov decision process (POMDP) for RFID-enhanced warehouse search operations

Scope and method of study. Misplaced items contribute significantly (2-10%) to the operational expense of a typical warehouse. In this work we develop a Partially Observable Markov Decision Process (POMDP) model for RFID directed search to detect misplaced items within a storage environment. A forklift operator (FLO) equipped with an RFID reader is assigned to search for a misplaced item in a warehouse. A FLO does not know the location of the tagged misplaced item and is guided by the imperfect variations in the strength of the signal received from the RFID tag (active or passive). The model considers five actions, five observations in scenarios with different RFID signal strength distributions namely, excellent, good and poor. An extensive simulation study has been conducted to evaluate the performance of RFID-driven POMDP search method. Specifically, the effects of signal strength distributions, initial beliefs at the start of the search and, the discount factor have been studied.; Findings and conclusions. The POMDP provides shortest path to locate the tag in the excellent observation scenario. As the observation probabilities decrease, i.e., there is more random imperfections in the nature of signals received (observations), the number of steps to reach the tag increases considerably. The expected reward from a 20-step POMDP with reasonable observation probabilities (varying between 70 and 90%) was 56% higher than that for a no-RFID case. This result implies that a significant (∼56%) reduction in search times and efforts for locating a misplaced item are possible using RFID in the tested scenarios. These results, we anticipate, will spur further research on using RFID signals as beacons for searching (perhaps multiple) missing items in more complicated warehouse layouts, through appropriate decomposition algorithms and local, near-optimal policies. Our ongoing research is focuses on achieving these advancements.