CompliantRobotMotion.PDF

Learning Motion Patterns of People for Compliant Robot Motion Maren Bennewitz? Wolfram Burgard? Grzegorz Cielniak? Sebastian Thrun§ ?Department of Computer Science, University of Freiburg, 79110 Freiburg, Germany ?Department of Technology, Orebro¨ University, 70182 Orebro,¨ Sweden §School of Computer Science, Carnegie Mellon University, Pittsburgh PA, USA Abstract Whenever people move through their environments they do not move ran- domly. Instead, they usually follow speci?c trajectories or motion patterns cor- responding to their intentions. Knowledge about such patterns enables a mobile robot to robustly keep track of persons in its environment and to improve its be- havior. This paper proposes a technique for learning collections of trajectories that characterize typical motion patterns of persons. Data recorded with laser-range ?nders is clustered using the expectation maximization algorithm. Based on the result of the clustering process we derive a Hidden Markov Model (HMM) that is applied to estimate the current and future positions of persons based on sensory input. We also describe how to incorporate the probabilistic belief about the po- tential trajectories of persons into the path planning process. We present several experiments carried out in different environments with a mobile robot equipped with a laser range scanner and a camera system. The results demonstrate that our approach can reliably learn motion patterns of persons, can robustly estimate and predict positions of persons, and can be used to improve the navigation behavior of a mobile robot. 1 Introduction Recently, there has been a substantial progress in the ?eld of service robots (see for example the book by Schraft and Schmierer [57] fo