Dynamical System Segmentation for Information Measures in Motion
This work provides a new method for assessing performance and the effectiveness of assistance for human subjects performing dynamic tasks, which could benefit fields like robotics and human-computer interaction.
This paper introduces a novel algorithm called dynamical system segmentation to extract an alphabet of behaviors from motion data without prior knowledge. By comparing the relative frequencies of these behaviors against an optimal agent using Kullback-Leibler divergence, they found that individuals receiving assistance better embodied the task and that task embodiment is a better predictor of assistance than integrated mean-squared-error.
Motions carry information about the underlying task being executed. Previous work in human motion analysis suggests that complex motions may result from the composition of fundamental submovements called movemes. The existence of finite structure in motion motivates information-theoretic approaches to motion analysis and robotic assistance. We define task embodiment as the amount of task information encoded in an agent's motions. By decoding task-specific information embedded in motion, we can use task embodiment to create detailed performance assessments. We extract an alphabet of behaviors comprising a motion without \textit{a priori} knowledge using a novel algorithm, which we call dynamical system segmentation. For a given task, we specify an optimal agent, and compute an alphabet of behaviors representative of the task. We identify these behaviors in data from agent executions, and compare their relative frequencies against that of the optimal agent using the Kullback-Leibler divergence. We validate this approach using a dataset of human subjects (n=53) performing a dynamic task, and under this measure find that individuals receiving assistance better embody the task. Moreover, we find that task embodiment is a better predictor of assistance than integrated mean-squared-error.