id: 06084745
dt: a
an: 06084745
au: Strasdat, Hauke; Stachniss, Cyrill; Burgard, Wolfram
ti: Learning landmark selection policies for mapping unknown environments.
so: Pradalier, Cédric (ed.) et al., Robotics research. The 14th international
    symposium ISRR. Selected papers based on the presentations at the
    symposium, Lucerne, Switzerland, August 31st to September 3rd, 2009.
    Berlin: Springer (ISBN 978-3-642-19456-6/hbk; 978-3-642-19457-3/ebook).
    Springer Tracts in Advanced Robotics 70, 483-499 (2011).
py: 2011
pu: Berlin: Springer
la: EN
cc: 
ut: 
ci: 
li: doi:10.1007/978-3-642-19457-3_29
ab: Summary: In general, a mobile robot that operates in unknown environments
    has to maintain a map and has to determine its own location given
    themap. This introduces significant computational and memory
    constraints for most autonomous systems, especially for lightweight
    robots such as humanoids or flying vehicles. In this paper, we present
    a universal approach for learning a landmark selection policy that
    allows a robot to discard landmarks that are not valuable for its
    current navigation task. This enables the robot to reduce the
    computational burden and to carry out its task more efficiently by
    maintaining only the important landmarks. Our approach applies an
    unscented Kalman filter for addressing the simultaneous localization
    and mapping problem and uses Monte-Carlo reinforcement learning to
    obtain the selection policy. In addition to that, we present a
    technique to compress learned policies without introducing a
    performance loss. In this way, our approach becomes applicable on
    systems with constrained memory resources. Based on real world and
    simulation experiments, we show that the learned policies allow for
    efficient robot navigation and outperform handcrafted strategies.We
    furthermore demonstrate that the learned policies are not only usable
    in a specific scenario but can also be generalized towards environments
    with varying properties.
rv: