Not Logged In

Subjective Localization With Action Respecting Embedding

Full Text: 05isrr.pdf PDF

Robot localization is the problem of how to estimate a robot's pose within an ob­ jective frame of reference. Traditional localization requires knowledge of two key conditional probabilities: the motion and sensor models. These models depend critically on the specific robot as well as its environment. Building these models can be time­consuming, manually intensive, and can require expert intuitions. However, the models are necessary for the robot to relate its own subjective view of sensors and motors to the robot's objective pose. In this paper we seek to remove the need for human provided models. We introduce a technique for subjective localization, relaxing the requirement that the robot localize within a global frame of reference. Using an algorithm for action­respecting non­linear dimensionality reduction, we learn a subjective representation of pose from a stream of actions and sensations. We then extract from the data natural motion and sensor models defined for this new representation. Monte Carlo localization is used to track this representation of the robot's pose while execut­ ing new actions and receiving new sensor readings. We evaluate the technique in a synthetic image manipulation domain and with a mobile robot using vision and laser sensors.

Citation

M. Bowling, D. Wilkinson, A. Ghodsi, A. Milstein. "Subjective Localization With Action Respecting Embedding". International Symposium of Robotics Research (ISRR), January 2005.

Keywords: subjective, localization, embedding, machine learning
Category: In Conference

BibTeX

@incollection{Bowling+al:ISRR05,
  author = {Michael Bowling and Dana Wilkinson and Ali Ghodsi and Adam
    Milstein},
  title = {Subjective Localization With Action Respecting Embedding},
  booktitle = {International Symposium of Robotics Research (ISRR)},
  year = 2005,
}

Last Updated: March 08, 2007
Submitted by AICML Admin Assistant

University of Alberta Logo AICML Logo