Mtjspaan at 18:36, 4 December 2008

2008-12-04T18:36:08Z

← Older revision		Revision as of 18:36, 4 December 2008
Line 28:		Line 28:
	In general, we consider decision-theoretic approaches		In general, we consider decision-theoretic approaches
	to cooperative active perception. We propose		to cooperative active perception. We propose
	to use Partially ~~ObservableMarkov~~ Decision Processes		to use Partially Observable Markov Decision Processes
	(POMDPs) as a		(POMDPs) as a
	framework for active cooperative perception. POMDPs provide		framework for active cooperative perception. POMDPs provide

Mtjspaan: New page: One of the recent research topics at the Intelligent Systems Lab is cooperative active perception. In our context, cooperative perception refers to the fusion of sensory information betwee...

2008-12-04T18:34:44Z

New page: One of the recent research topics at the Intelligent Systems Lab is cooperative active perception. In our context, cooperative perception refers to the fusion of sensory information betwee...

New page

One of the recent research topics at the Intelligent Systems Lab is cooperative active perception.
In our context, cooperative perception refers to the fusion
of sensory information between fixed surveillance cameras
and robots, with as goal maximizing the amount and quality of perceptual information available to the system.
This information can be used by a robot to choose its
actions, as well as providing a global picture for monitoring
the system. In general, incorporating information from
spatially distributed sensors will raise the level of situational
awareness.

Active perception means that an agent considers the effects
of its actions on its sensors, and in particular it tries
to improve their performance. This can mean selecting sensory
actions, for instance pointing a pan-and-tilt camera or
choosing to execute an expensive vision algorithm; or to influence
a robot’s path planning, e.g., given two routes to get
to a desired location, take the more informative one. Performance
can be measured by trading off the costs of executing
actions with how much we improve the quality of the information
available to the system, and should be derived from
the system’s task. Combining the two concepts, cooperative
active perception is the problem of active perception involving
multiple sensors and multiple cooperating decision
makers.

[[Image:robotPersonPOMDP.jpg|thumb|400px|right|Robot and person, observed by surveillance cameras, using POMDP decision making.]]

In general, we consider decision-theoretic approaches
to cooperative active perception. We propose
to use Partially ObservableMarkov Decision Processes
(POMDPs) as a
framework for active cooperative perception. POMDPs provide
an elegant way to model the interaction of an active
sensor with its environment. Based on prior knowledge of
the sensor’s model and the environment dynamics, we can
compute policies that tell the active sensor how to act, based
on the observations it receives. As we are essentially dealing
with multiple decision makers, it could also be beneficial to
consider modeling (a subset of) sensors as a decentralized
POMDP (Dec-POMDP).
In a cooperative perception framework, an important task
encoded by the (Dec-)POMDP could be to reduce the uncertainty
in its view of the environment as much as possible.
Entropy can be used as a suitable measure for uncertainty.
However, using a POMDP solution, we can tackle
more elaborate scenarios, for instance in which we prioritize
the tracking of certain objects. In particular, POMDPs
inherently trade off task completion and information gathering.

Cooperative Active Perception - Revision history

Mtjspaan at 18:36, 4 December 2008

Mtjspaan: New page: One of the recent research topics at the Intelligent Systems Lab is cooperative active perception. In our context, cooperative perception refers to the fusion of sensory information betwee...