Indoor localization and position tracking are essential to support applications and services for ambient-assisted living. While the problem of indoor localization is still open and already quite complex per se, in large public places, additional issues of cost, accuracy, and scalability arise. In this paper, the position estimation and tracking technique developed within the project devices for assisted living (DALi) is described, analyzed through simulations, and finally validated by means of a variety of experiments on the field. The goal of the DALi project is to design a robotic wheeled walker guiding people with psychomotor problems. Indeed, people with motor or cognitive impairments are often afraid of moving in large and crowded environments (e.g., because they could lose the sense of direction). In order to mitigate this problem, the position tracking approach described in this paper is based on multisensor data fusion and it is conceived to assure a good tradeoff between target accuracy, level of confidence, and deployment costs. Quite interestingly, the same approach could be used for indoor automated guided vehicles and robotics.