Belief Space Partitioning for Symbolic Motion Planning

Hou，Mengxue1; Lin，Tony X.1; Zhou，Haomin2; Zhang，Wei3; Edwards，Catherine R.4; Zhang，Fumin1

10.1109/ICRA48506.2021.9561121

2021

IEEE International Conference on Robotics and Automation (ICRA)

1050-4729

2577-087X

978-1-7281-9078-5

Proceedings - IEEE International Conference on Robotics and Automation

2021-May

8245-8251

MAY 30-JUN 05, 2021

null,Xian,PEOPLES R CHINA

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

We propose a memory-constrained partition-based method to extract symbolic representations of the belief state and its dynamics in order to solve planning problems in a partially observable Markov decision process (POMDP). Our K-means partitioning strategy uses a fixed number of symbols to represent the partitions of the belief space and ensures the parameterization of the belief dynamics does not grow exponentially as the system dimension increases. By casting our problem as a partitioning of the POMDP, we can then solve planning problems using traditional symbolic planning solvers (such as HTN or A* solvers). Our work is motivated by an autonomous underwater vehicle navigation problem where the vehicle is affected by uncertain flow conditions and receives severely limited position observations. Simulation experiments are provided to validate the performance of the proposed algorithms.

Casting Autonomous underwater vehicles Navigation Conferences Markov processes Planning Trajectory

其他

英语

CPCI-S ; EI

National Sleep Foundation[CNS-1828678];Air Force Office of Scientific Research[FA9550-19-1-0283];National Sleep Foundation[GCR-1934836];Office of Naval Research[N00014-19-1-2266];Office of Naval Research[N00014-19-1-2556];U.S. Naval Research Laboratory[N00173-17-1-G001];U.S. Naval Research Laboratory[N00173-19-P-1412];National Oceanic and Atmospheric Administration[NA16NOS0120028];National Sleep Foundation[S&AS-1849228];

Automation & Control Systems ; Robotics

Automation & Control Systems ; Robotics

WOS:000771405401106

20220911738316

Autonomous vehicles ; K-means clustering ; Markov processes ; Motion planning

Highway Transportation:432 ; Small Marine Craft:674.1 ; Robot Applications:731.6 ; Information Sources and Analysis:903.1 ; Probability Theory:922.1

2-s2.0-85125448036

Scopus

1.School of Electrical and Computer Engineering,Georgia Institute of Technology,Atlanta,30309,United States
2.School of Mathematics,Georgia Institute of Technology,Atlanta,30309,United States
3.Department of Mechanical and Energy Engineering,Southern University of Science and Technology,Shenzhen,Guangdong,518000,China
4.Skidaway Institute of Oceanography,University of Georgia,Savannah,31411,United States

Hou，Mengxue,Lin，Tony X.,Zhou，Haomin,et al. Belief Space Partitioning for Symbolic Motion Planning[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2021:8245-8251.