Maren Bennewitz , Wolfram Burgard , Grzegorz Cielniak and Sebastian Thrun Learning Motion Patterns of People for Compliant Robot Motion
نویسندگان
چکیده
Whenever people move through their environments they do not move randomly. Instead, they usually follow specific trajectories or motion patterns corresponding to their intentions. Knowledge about such patterns enables a mobile robot to robustly keep track of persons in its environment and to improve its behavior. In this paper we propose a technique for learning collections of trajectories that characterize typical motion patterns of persons. Data recorded with laser-range finders are clustered using the expectation maximization algorithm. Based on the result of the clustering process, we derive a hidden Markov model 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 potential trajectories of persons into the path planning process of a mobile robot. 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. KEY WORDS—learning activity models, trajectory clustering, machine learning, mobile robot navigation, human robot interaction The International Journal of Robotics Research Vol. 24, No. 1, January 2005, pp. 31-48, DOI: 10.1177/0278364904048962 ©2005 Sage Publications
منابع مشابه
Learning Motion Patterns of People for Compliant Robot Motion
Whenever people move through their environments they do not move randomly. Instead, they usually follow specific trajectories or motion patterns corresponding to their intentions. Knowledge about such patterns enables a mobile robot to robustly keep track of persons in its environment and to improve its behavior. In this paper we propose a technique for learning collections of trajectories that...
متن کاملRobust Localization of Persons Based on Learned Motion Patterns
Whenever people move through their environments they do not move randomly. Instead, they usually follow specific trajectories or motion patterns corresponding to their intentions. Knowledge about such patterns may enable a mobile robot to robustly keep track of persons in its environment. This paper proposes a technique to derive a Hidden Markov Model (HMM) from learned motion patterns of peopl...
متن کاملLearning Motion Patterns
We propose a method for learning models of people’s motion behaviors in an indoor environment. As people move through their environments, they do not move randomly. Instead, they often engage in typical motion patterns, related to specific locations that they might be interested in approaching and specific trajectories that they might follow in doing so. Knowledge about such patterns may enable...
متن کاملUtilizing Learned Motion Patterns to Robustly Track Persons
Whenever people move through their environments they do not move randomly. Instead, they usually follow specific trajectories or motion patterns corresponding to their intentions. Knowledge about such patterns may enable a mobile robot to robustly keep track of the position of the persons in its environment or to improve its behavior. This paper proposes a technique for learning collections of ...
متن کامل