Using Humanoid Robot to Instruct and Evaluate Performance of a Physical Task

TL;DR

This paper introduces a humanoid robot-based system that instructs and evaluates users performing a block-moving task, using computer vision to monitor progress and adapt to task variations, demonstrated through a pilot study.

Contribution

The paper presents a novel robot-assisted assessment tool that dynamically evaluates user performance on a task with automated visual feedback and progress logging.

Findings

Users' performance was unaffected by task variations.

The system successfully detected block movements using computer vision.

Pilot results demonstrate feasibility of robot-guided performance assessment.

Abstract

In this paper, we present a tool to assess users ability to change tasks. To do this, we use a variation of the Box and Blocks Test. In this version, a humanoid robot instructs a user to perform a task involving the movement of certain colored blocks. The robot changes randomly change the color of blocks that the user is supposed to move. Canny Edge Detection and Hough Transformation are used to assess user perform the robot's built-in camera. This will allow the robot to inform the user and keep a log of their progress. We present this method for monitoring user progress by describing how the moved blocks are detected. We also present the results of a pilot study where users used this system to perform the task. Preliminary results show that users do not perform differently when the task is changed in this scenario.