17-03-2014, 10:52 AM
Abstract
Localization is the problem of determining the position
of a mobile robot from sensor data. Most existing localization
approaches are passive, i.e., they do not exploit the
opportunity to control the robot’s effectors during localization.
This paper proposes an active localization approach.
The approach provides rational criteria for (1) setting the
robot’s motion direction (exploration), and (2) determining
the pointing direction of the sensors so as to most eflciently
localize the robot. Furthermore, it is able to deal with noisy
sensors and approximative world models. The appropriateness
of our approach is demonstrated empirically using a
mobile robot in a structured oflce environment.
1. Introduction
To navigate reliably in indoor environments, a mobile
robot must know where it is. Over the last few years, there
has been a tremendous scientific interest in algorithms for
estimating a robot’s location from sensor data. A recent
book on this issue [2] illustrates the importance of the localization
problem and provides a unique description of the
state-of-the-art.
The majority of existing approaches to localization are
passive. Passive localization exclusively addresses the estimation
of the location based on an incoming stream of
sensor data. It rests on the assumption that neither robot
motion, nor the pointing direction of the robot’s sensors can
be controlled. Active localization assumes that during localization,
the localization routine has partial or full control
over the robot, providing the opportunity to increase the efficiency
and the robustness of localization. Key open issues
in active localization are “where to move” and “where to
look” so as to best localize the robot.
This paper demonstrates that active localization is a
promising research direction for developing more efficient
and more robust localization methods. In other sub-fields
of artificial intelligence (such as heuristic search and machine
learning), the value of active control during learning
and problem solving has long been recognized. It has been
shown, both through theoretical analysis and practical experimentation,
that the complexity of achieving a task can
be greatly reduced by actively interacting with the environment.
For example, choosing the right action during exploration
can reduce exponential complexity to low-degree
polynomial complexity, as for example shown in Koenig’s
and Thrun’s work on exploration in heuristic search and
learning control [lo, 171. Similarly, active vision (see e.g.,
[l]) has also led to results superior to passive approaches
to computer vision. In the context of mobile robot localization,
actively controlling a robot is particularly beneficial
when the environment possesses relatively few features
that enable a robot to unambiguously determine its location.
This is the case in many office environments. For example,
corridors and offices often look alike foi- a mobile robot.
hence random motion or perpetual wall following is often
incapable for determining a robot’s position, or very inefficient.
In this paper we demonstrate that actively controlling
the robot’s actuators can significantly improve the efficiency
of localization. Our -Framework is based on Mavkov
localization, a passive probabilistic approach to localization
which was recently developed in different variants by
[5, 7, 14, 151. At any point in time, Markov localization
maintains a probability density (belief) over the entire configuration
space of the robot; however, it does not provide
an answer as to how to control the robot’s actuators. The
guiding principle of our approach is to control the actuators
so as to minimize future expected uncertainty. Uncertainty
is measured by the entropy of future belief distributions.
By choosing actions to minimize the expected future uncertainty,
the approach is capable of actively localizing the
robot.
Localization is the problem of determining the position
of a mobile robot from sensor data. Most existing localization
approaches are passive, i.e., they do not exploit the
opportunity to control the robot’s effectors during localization.
This paper proposes an active localization approach.
The approach provides rational criteria for (1) setting the
robot’s motion direction (exploration), and (2) determining
the pointing direction of the sensors so as to most eflciently
localize the robot. Furthermore, it is able to deal with noisy
sensors and approximative world models. The appropriateness
of our approach is demonstrated empirically using a
mobile robot in a structured oflce environment.
1. Introduction
To navigate reliably in indoor environments, a mobile
robot must know where it is. Over the last few years, there
has been a tremendous scientific interest in algorithms for
estimating a robot’s location from sensor data. A recent
book on this issue [2] illustrates the importance of the localization
problem and provides a unique description of the
state-of-the-art.
The majority of existing approaches to localization are
passive. Passive localization exclusively addresses the estimation
of the location based on an incoming stream of
sensor data. It rests on the assumption that neither robot
motion, nor the pointing direction of the robot’s sensors can
be controlled. Active localization assumes that during localization,
the localization routine has partial or full control
over the robot, providing the opportunity to increase the efficiency
and the robustness of localization. Key open issues
in active localization are “where to move” and “where to
look” so as to best localize the robot.
This paper demonstrates that active localization is a
promising research direction for developing more efficient
and more robust localization methods. In other sub-fields
of artificial intelligence (such as heuristic search and machine
learning), the value of active control during learning
and problem solving has long been recognized. It has been
shown, both through theoretical analysis and practical experimentation,
that the complexity of achieving a task can
be greatly reduced by actively interacting with the environment.
For example, choosing the right action during exploration
can reduce exponential complexity to low-degree
polynomial complexity, as for example shown in Koenig’s
and Thrun’s work on exploration in heuristic search and
learning control [lo, 171. Similarly, active vision (see e.g.,
[l]) has also led to results superior to passive approaches
to computer vision. In the context of mobile robot localization,
actively controlling a robot is particularly beneficial
when the environment possesses relatively few features
that enable a robot to unambiguously determine its location.
This is the case in many office environments. For example,
corridors and offices often look alike foi- a mobile robot.
hence random motion or perpetual wall following is often
incapable for determining a robot’s position, or very inefficient.
In this paper we demonstrate that actively controlling
the robot’s actuators can significantly improve the efficiency
of localization. Our -Framework is based on Mavkov
localization, a passive probabilistic approach to localization
which was recently developed in different variants by
[5, 7, 14, 151. At any point in time, Markov localization
maintains a probability density (belief) over the entire configuration
space of the robot; however, it does not provide
an answer as to how to control the robot’s actuators. The
guiding principle of our approach is to control the actuators
so as to minimize future expected uncertainty. Uncertainty
is measured by the entropy of future belief distributions.
By choosing actions to minimize the expected future uncertainty,
the approach is capable of actively localizing the
robot.