Effective Landmark Placement for Robot Indoor Localization With Position Uncertainty Constraints

A well-known, crucial problem for indoor positioning of mobile agents (e.g., robots) equipped with exteroceptive sensors is related to the need to deploy reference landmarks in a given environment. Normally, anytime a landmark is detected, an agent estimates its own location and attitude with respect to landmark position and/or orientation in the chosen reference frame. When instead no landmark is recognized, other sensors (e.g., odometers in the case of wheeled robots) can be used to track the agent position and orientation from the last detected landmark. At the moment, landmark placement is usually based just on common-sense criteria, which are not formalized properly. As a result, positioning uncertainty tends to grow unpredictably. On the contrary, the purpose of this paper is to minimize the number of landmarks, while ensuring that localization uncertainty is kept within wanted boundaries. The developed approach relies on the following key features: a dynamic model describing agents' motion, a model predicting the agents' paths within a given environment and, finally, a conjunctive normal form formalization of the optimization problem, which can be efficiently (although approximately) solved by a greedy algorithm. The effectiveness of the proposed landmark placement technique is first demonstrated through simulations in a variety of conditions and then it is validated through experiments on the field, by using non-Bayesian and Bayesian position tracking algorithms.