Watch-Bot: Unsupervised Learning for Reminding Humans of Forgotten Actions

TL;DR

This paper introduces an unsupervised learning-based robotic system that observes human activities, detects forgotten actions, and reminds humans using a laser pointer, all without requiring human annotations.

Contribution

It presents a scalable, annotation-free approach for activity understanding and forgetting detection in assistive robots using RGB-D data.

Findings

Improves unsupervised action segmentation and clustering.

Effectively detects forgotten actions in challenging datasets.

Successfully reminds humans of forgotten actions in robotic experiments.

Abstract

We present a robotic system that watches a human using a Kinect v2 RGB-D sensor, detects what he forgot to do while performing an activity, and if necessary reminds the person using a laser pointer to point out the related object. Our simple setup can be easily deployed on any assistive robot. Our approach is based on a learning algorithm trained in a purely unsupervised setting, which does not require any human annotations. This makes our approach scalable and applicable to variant scenarios. Our model learns the action/object co-occurrence and action temporal relations in the activity, and uses the learned rich relationships to infer the forgotten action and the related object. We show that our approach not only improves the unsupervised action segmentation and action cluster assignment performance, but also effectively detects the forgotten actions on a challenging human activity RGB-D video dataset. In robotic experiments, we show that our robot is able to remind people of forgotten actions successfully.