Hidden Markov Models derived from Behavior Trees
This work addresses a gap in robotics and human motion tracking by providing a method to handle noisy data in BT systems, though it appears incremental as it leverages existing HMM techniques.
The authors tackled the problem of tracking or identifying parameters of Behavior Trees (BTs) under noisy observations by establishing a new relationship between augmented BTs and Hidden Markov Models (HMMs), enabling the application of existing HMM algorithms to BT-based systems.
Behavior trees are rapidly attracting interest in robotics and human task-related motion tracking. However no algorithms currently exist to track or identify parameters of BTs under noisy observations. We report a new relationship between BTs, augmented with statistical information, and Hidden Markov Models. Exploiting this relationship will allow application of many algorithms for HMMs (and dynamic Bayesian networks) to data acquired from BT-based systems.