Mengxue Hou

Ph.D. candidate, Georgia Institute of Technology

Belief abstraction for symbolic motion planning

We propose a memory-constrained partition-based method to extract symbolic representations of the belief state andits 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 partitioningof the POMDP, we can then solve planning problems using traditional symbolic planning solvers (such as HTN or A* solvers).