Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Wearable Interfaces for Robotic Caregiving

Akhil Padmanabha, Carmel Majidi, Zackory Erickson

TL;DR

The paper tackles the challenge of enabling physically impaired individuals to operate home caregiving robots without overwhelming user workload or sacrificing perceived control. It advances three control paradigms: active control through the Head-Worn Assistive Teleoperation (HAT) interface, shared control via Driver Assistance (DA) that leverages open-vocabulary perception to align robot actions with user intent, and passive control that uses wearable sensors to detect implicit cues and guide robotic actions. In-the-wild and in-home evaluations demonstrate that DA can significantly reduce task time (e.g., up to 70% for certain grasp tasks) and lower mental workload while preserving user agency, with HAT providing accessible direct control and setting a baseline for workload. Passive control is proposed to further reduce input demands by sensing subconscious user signals, with initial non-impaired studies and plans to extend to feeding and other caregiving tasks, potentially broadening the practical impact of wearable interfaces in robotic caregiving.

Abstract

Physically assistive robots in home environments can enhance the autonomy of individuals with impairments, allowing them to regain the ability to conduct self-care and household tasks. Individuals with physical limitations may find existing interfaces challenging to use, highlighting the need for novel interfaces that can effectively support them. In this work, we present insights on the design and evaluation of an active control wearable interface named HAT, Head-Worn Assistive Teleoperation. To tackle challenges in user workload while using such interfaces, we propose and evaluate a shared control algorithm named Driver Assistance. Finally, we introduce the concept of passive control, in which wearable interfaces detect implicit human signals to inform and guide robotic actions during caregiving tasks, with the aim of reducing user workload while potentially preserving the feeling of control.

Towards Wearable Interfaces for Robotic Caregiving

TL;DR

The paper tackles the challenge of enabling physically impaired individuals to operate home caregiving robots without overwhelming user workload or sacrificing perceived control. It advances three control paradigms: active control through the Head-Worn Assistive Teleoperation (HAT) interface, shared control via Driver Assistance (DA) that leverages open-vocabulary perception to align robot actions with user intent, and passive control that uses wearable sensors to detect implicit cues and guide robotic actions. In-the-wild and in-home evaluations demonstrate that DA can significantly reduce task time (e.g., up to 70% for certain grasp tasks) and lower mental workload while preserving user agency, with HAT providing accessible direct control and setting a baseline for workload. Passive control is proposed to further reduce input demands by sensing subconscious user signals, with initial non-impaired studies and plans to extend to feeding and other caregiving tasks, potentially broadening the practical impact of wearable interfaces in robotic caregiving.

Abstract

Physically assistive robots in home environments can enhance the autonomy of individuals with impairments, allowing them to regain the ability to conduct self-care and household tasks. Individuals with physical limitations may find existing interfaces challenging to use, highlighting the need for novel interfaces that can effectively support them. In this work, we present insights on the design and evaluation of an active control wearable interface named HAT, Head-Worn Assistive Teleoperation. To tackle challenges in user workload while using such interfaces, we propose and evaluate a shared control algorithm named Driver Assistance. Finally, we introduce the concept of passive control, in which wearable interfaces detect implicit human signals to inform and guide robotic actions during caregiving tasks, with the aim of reducing user workload while potentially preserving the feeling of control.

Paper Structure

This paper contains 4 sections, 1 figure.

Table of Contents

  1. Introduction
  2. RQ1: Active Control
  3. RQ2: Shared Control
  4. RQ3: Passive Control

Figures (1)

  • Figure 1: Left: The wireless head-worn interface (HAT) with integrated inertial measurement unit (IMU) sensing. Middle: Henry Evans, a non-speaking individual with quadriplegia, uses HAT to teleoperate a mobile manipulator. The interface records and wirelessly sends head orientation angles to a companion laptop, which computes and transmits actuator velocities to the robot. A clicker is used to switch between modes, distinct operational states of the HAT system. Right: Our system for passive control using wearable sensing for robot assisted feeding is shown. The wearable sensors include glasses and ear IMUs and a throat contact microphone.