Multienvironment performance comparison of robot‐assisted indoor location estimation system

Many indoor location systems utilizing the fingerprinting technique require frequent signal map generation due to the dynamic properties of indoor environments. This time‐consuming task can be freed from human involvement by using various techniques. Thus, a robot‐aided signal map creator is implemented and its positioning performance as well as its mapping time is compared with a widely used human facilitated approach. For testing purposes, a low‐cost, low‐power, not off‐the‐shelf signal data collection robot is implemented. Its signal collection speed and location estimation precision is then compared with the manual method both in a small and large environment. The findings indicate that in the small environment, robot‐aided approach performs with 268‐cm error‐rate 70% of the time. On the other hand, the improved robot‐aided approach in large environment saves 52 min of labor‐intense legwork and achieves 303.5‐cm mean error‐rate.