Disentangled Sequence Clustering for Human Intention Inference

TL;DR

This paper introduces DiSCVAE, an unsupervised clustering framework that disentangles sequence data to infer human intent, enabling robots to understand high-level intentions without prior labels, demonstrated on real-world human-robot interaction data.

Contribution

The paper presents DiSCVAE, a novel unsupervised variational autoencoder that disentangles sequence features and infers discrete intent variables for human intention inference.

Findings

Discrete variable aligns with human intent

Effective clustering of high-level intentions

Potential for improved human-robot collaboration

Abstract

Equipping robots with the ability to infer human intent is a vital precondition for effective collaboration. Most computational approaches towards this objective derive a probability distribution of "intent" conditioned on the robot's perceived state. However, these approaches typically assume task-specific labels of human intent are known a priori. To overcome this constraint, we propose the Disentangled Sequence Clustering Variational Autoencoder (DiSCVAE), a clustering framework capable of learning such a distribution of intent in an unsupervised manner. The proposed framework leverages recent advances in unsupervised learning to disentangle latent representations of sequence data, separating time-varying local features from time-invariant global attributes. As a novel extension, the DiSCVAE also infers a discrete variable to form a latent mixture model and thus enable clustering over these global sequence concepts, e.g. high-level intentions. We evaluate the DiSCVAE on a real-world human-robot interaction dataset collected using a robotic wheelchair. Our findings reveal that the inferred discrete variable coincides with human intent, holding promise for collaborative settings, such as shared control.