Recent advances in the field of radio frequency identification techniques have reached a state that will allow us within the next years to equip virtually every object in an environment with small, cheap Radio Frequency Identification (RFID) tags [1]. Such tags contain circuitry that gain power from radio waves emitted by readers in their vicinity. They use this power to reply their unique identifier to the reader. Figure 1 depicts three different RFID tags that were used to carry out the experiments described in this paper. The detection range of these tags is approximately 6 m.
RFID tags open up a wide variety of applications. For example, an important problem in the health-care sector is the recognition of daily activities a home patient is engaged in. The Guide project [2] uses small RFID readers worn by a person to identify the objects the person touches. The sequence of touched objects is used by a Bayesian reasoning system toestimate the activity of the person and to provide support if needed. Location context can provide important information for the interpretation of RFID readings. For example, touching the toothpaste has very different meanings depending on whether it happens in the storage room or in the bathroom. In this paper, we investigate how RFID technology can be enhanced by location information. We use a mobile robot equipped with RFID antennas to determine the locations of RFID tags attached to objects in an indoor environment. Figure 2 (left) depicts the robot built to carry out this research. The robot consists of an off-the-shelf Pioneer 2 robot equipped with a laser range scanner and two RFID antennas.
The antennas are mounted on top of the robot and point approximately 45 degrees to the left and to the right with respect to the robot. To use these antennas for estimating the locations of objects, we first learn a sensor model that describes the likelihood of detecting an RFID tag given its location relative to one of the antennas. Since the noise of these sensors is highly non-Gaussian, we represent the measurement likelihood model by a piecewise constant approximation. Then we describe a technique to estimate the locations of RFID tags using a mobile robot equipped with RFID antennas to detect tags. This process uses a map previously learned from laser range data. We then apply Monte Carlo localization [3], [4] to estimate the pose of the robot and even of persons in this environment. Experimental results suggest that it is possible to accurately localize moving objects based on this technology. Further experiments demonstrate that RFID tags greatly reduce the time required for global localization of a mobile robot in its environment. Additionally, this technology can be used to drastically reduce the number of samples required for global localization.
This paper is organized as follows. After discussing related work we will present the sensor model for RFID receivers in Section III. Then we describe how this model can be used in combination with a laser-based FastSLAM [5] approach to effectively determine the locations of RFID tags. In Section V we describe how the resulting beliefs about the locations of the tags can be utilized to determine the position of the robot and of persons in the environment. Finally, we present experimental results illustrating the advantages of RFID tags for robot localization and person tracking.
RFID tags open up a wide variety of applications. For example, an important problem in the health-care sector is the recognition of daily activities a home patient is engaged in. The Guide project [2] uses small RFID readers worn by a person to identify the objects the person touches. The sequence of touched objects is used by a Bayesian reasoning system toestimate the activity of the person and to provide support if needed. Location context can provide important information for the interpretation of RFID readings. For example, touching the toothpaste has very different meanings depending on whether it happens in the storage room or in the bathroom. In this paper, we investigate how RFID technology can be enhanced by location information. We use a mobile robot equipped with RFID antennas to determine the locations of RFID tags attached to objects in an indoor environment. Figure 2 (left) depicts the robot built to carry out this research. The robot consists of an off-the-shelf Pioneer 2 robot equipped with a laser range scanner and two RFID antennas.
The antennas are mounted on top of the robot and point approximately 45 degrees to the left and to the right with respect to the robot. To use these antennas for estimating the locations of objects, we first learn a sensor model that describes the likelihood of detecting an RFID tag given its location relative to one of the antennas. Since the noise of these sensors is highly non-Gaussian, we represent the measurement likelihood model by a piecewise constant approximation. Then we describe a technique to estimate the locations of RFID tags using a mobile robot equipped with RFID antennas to detect tags. This process uses a map previously learned from laser range data. We then apply Monte Carlo localization [3], [4] to estimate the pose of the robot and even of persons in this environment. Experimental results suggest that it is possible to accurately localize moving objects based on this technology. Further experiments demonstrate that RFID tags greatly reduce the time required for global localization of a mobile robot in its environment. Additionally, this technology can be used to drastically reduce the number of samples required for global localization.
This paper is organized as follows. After discussing related work we will present the sensor model for RFID receivers in Section III. Then we describe how this model can be used in combination with a laser-based FastSLAM [5] approach to effectively determine the locations of RFID tags. In Section V we describe how the resulting beliefs about the locations of the tags can be utilized to determine the position of the robot and of persons in the environment. Finally, we present experimental results illustrating the advantages of RFID tags for robot localization and person tracking.
By
Dirk H¨ahnel Wolfram Burgard
University of Freiburg
Department of Computer Science
Freiburg, Germany
Dieter Fox
University of Washington
Computer Science and Engineering
Seattle, WA, USA
Ken Fishkin Matthai Philipose
Intel Research Seattle
Seattle, WA, USA
[1] Klaus Finkenzeller. RFID Handboook: Radio-Frequency Identification Fundamentals and Applications. Wiley, New York, 2000.
[2] M. Philipose, K. Fishkin, D. Fox, H. Kautz, D. Patterson, and M. Perkowitz. Guide: Towards understanding daily life via autoidentification and statistical analysis. In Proc. of the Int. Workshop on Ubiquitous Computing for Pervasive Healthcare Applications (Ubihealth), 2003.
[3] F. Dellaert, D. Fox, W. Burgard, and S. Thrun. Monte Carlo localization for mobile robots. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 1999.
[4] D. Fox, W. Burgard, F. Dellaert, and S. Thrun. Monte Carlo localization: Efficient position estimation for mobile robots. In Proc. of the National Conference on Artificial Intelligence (AAA I), 1999.
[5] D. H¨ahnel, W. Burgard, D. Fox, and S. Thrun. An efficient fastslam algorithm for generating maps of large-scale cyclic environments from raw laser range measurements. In Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2003.
