Please use this identifier to cite or link to this item:
|Title:||A point-based POMDP planner for target tracking|
|Authors:||Hsu, D. |
|Citation:||Hsu, D., Lee, W.S., Rong, N. (2008). A point-based POMDP planner for target tracking. Proceedings - IEEE International Conference on Robotics and Automation : 2644-2650. ScholarBank@NUS Repository. https://doi.org/10.1109/ROBOT.2008.4543611|
|Abstract:||Target tracking has two variants that are often studied independently with different approaches: target searching requires a robot to find a target initially not visible, and target following requires a robot to maintain visibility on a target initially visible. In this work, we use a partially observable Markov decision process (POMDP) to build a single model that unifies target searching and target following. The POMDP solution exhibits interesting tracking behaviors, such as anticipatory moves that exploit target dynamics, information-gathering moves that reduce target position uncertainty, and energy-conserving actions that allow the target to get out of sight, but do not compromise long-term tracking performance. To overcome the high computational complexity of solving POMDPs, we have developed SARSOP, a new point-based POMDP algorithm based on successively approximating the space reachable under optimal policies. Experimental results show that SARSOP is competitive with the fastest existing point-based algorithm on many standard test problems and faster by many times on some. ©2008 IEEE.|
|Source Title:||Proceedings - IEEE International Conference on Robotics and Automation|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Jun 16, 2018
WEB OF SCIENCETM
checked on May 29, 2018
checked on Apr 21, 2018
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.