In order to meet the increasing demands of mobile service robot applications, a dedicated perception module is an essential requirement for the interaction with users in real-world scenarios. In particular, multi sensor fusion and human re-identification are recognized as active research fronts. Through this paper we contribute to the topic and present a modular detection and tracking system that models position and additional properties of persons in the surroundings of a mobile robot. The proposed system introduces a probability-based data association method that besides the position can incorporate face and color-based appearance features in order to realize a re-identification of persons when tracking gets interrupted. The system combines the results of various state-of-the-art image-based detection systems for person recognition, person identification and attribute estimation. This allows a stable estimate of a mobile robot’s user, even in complex, cluttered environments with long-lasting occlusions. In our benchmark, we introduce a new measure for tracking consistency and show the improvements when face and appearance-based re-identification are combined. The tracking system was applied in a real world application with a mobile rehabilitation assistant robot in a public hospital. The estimated states of persons are used for the user-centered navigation behaviors, e.g., guiding or approaching a person, but also for realizing a socially acceptable navigation in public environments.

For a mobile assistive robot operating in a human-populated environment, a polite navigation is an important requirement for the social acceptance. When operating in a confined environment, narrow passages can lead to deadlock situations with persons. In our approach we distinguish two types of deadlock situations at narrow passages, in which the robot lets the conflicting person pass, and either waits in a non-disturbing waiting position, or forms a queue with that person. Forthcoming deadlock situations are captured by a set of qualitative features. As part of these features, we detect narrow passages with a raycasting approach and predict the movement of persons. In contrast to numerical features, the qualitative description forms a more compact human-understandable space allowing to employ a rule-based decision tree to classify the considered situation types. To determine a non-disturbing waiting position, a multi-criteria optimization approach is used together with the Particle Swarm Optimization as solver. In field tests, we evaluated our approach for deadlock recognition in a hospital environment with narrow corridors.