Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Exploring of Discrete and Continuous Input Control for AI-enhanced Assistive Robotic Arms

Max Pascher, Kevin Zinta, Jens Gerken

TL;DR

This study evaluates discrete and continuous input modalities for AI-enhanced shared control of assistive robotic arms, integrating three devices (Joy-Con, head-based IMU, and assistive buttons) within the AdaptiX XR framework and Adaptive DoF Mapping (ADMC). Using a within-subject MR study with 14 participants controlling a Kinova Jaco 2 in a pick-and-place task, the authors compare workload, usability, and user preference across modalities. Results favor the Joy-Con and button-based controls over head-based input, with head control suffering from higher workload and usability concerns, partly due to bulky hardware and mapping ambiguity. The findings inform design choices for input technologies in assistive robotics and underscore the potential for customization and better-harnessed multimodal interfaces in real-world HRI applications.

Abstract

Robotic arms, integral in domestic care for individuals with motor impairments, enable them to perform Activities of Daily Living (ADLs) independently, reducing dependence on human caregivers. These collaborative robots require users to manage multiple Degrees-of-Freedom (DoFs) for tasks like grasping and manipulating objects. Conventional input devices, typically limited to two DoFs, necessitate frequent and complex mode switches to control individual DoFs. Modern adaptive controls with feed-forward multi-modal feedback reduce the overall task completion time, number of mode switches, and cognitive load. Despite the variety of input devices available, their effectiveness in adaptive settings with assistive robotics has yet to be thoroughly assessed. This study explores three different input devices by integrating them into an established XR framework for assistive robotics, evaluating them and providing empirical insights through a preliminary study for future developments.

Exploring of Discrete and Continuous Input Control for AI-enhanced Assistive Robotic Arms

TL;DR

This study evaluates discrete and continuous input modalities for AI-enhanced shared control of assistive robotic arms, integrating three devices (Joy-Con, head-based IMU, and assistive buttons) within the AdaptiX XR framework and Adaptive DoF Mapping (ADMC). Using a within-subject MR study with 14 participants controlling a Kinova Jaco 2 in a pick-and-place task, the authors compare workload, usability, and user preference across modalities. Results favor the Joy-Con and button-based controls over head-based input, with head control suffering from higher workload and usability concerns, partly due to bulky hardware and mapping ambiguity. The findings inform design choices for input technologies in assistive robotics and underscore the potential for customization and better-harnessed multimodal interfaces in real-world HRI applications.

Abstract

Robotic arms, integral in domestic care for individuals with motor impairments, enable them to perform Activities of Daily Living (ADLs) independently, reducing dependence on human caregivers. These collaborative robots require users to manage multiple Degrees-of-Freedom (DoFs) for tasks like grasping and manipulating objects. Conventional input devices, typically limited to two DoFs, necessitate frequent and complex mode switches to control individual DoFs. Modern adaptive controls with feed-forward multi-modal feedback reduce the overall task completion time, number of mode switches, and cognitive load. Despite the variety of input devices available, their effectiveness in adaptive settings with assistive robotics has yet to be thoroughly assessed. This study explores three different input devices by integrating them into an established XR framework for assistive robotics, evaluating them and providing empirical insights through a preliminary study for future developments.
Paper Structure (18 sections, 2 figures, 1 table)

This paper contains 18 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Discrete and Continuous Control Methods
  4. Motion Controller
  5. Head-based Control
  6. Assistive Buttons
  7. Study
  8. Study Design
  9. Apparatus
  10. Procedure
  11. Experimental Task
  12. Results
  13. Perceived workload
  14. Evaluation of Physical Assistive Devices
  15. Individual Ranking
  16. ...and 3 more sections

Figures (2)

  • Figure 1: Overview of the study setup. The participant is wearing a Varjo XR-3HMD and controls the Kinova Jaco 2 via head movements. The goal is to grasp the light-colored rounded block and place it on the large orange square in the middle of the table. The small orange markings are potential starting points for the rounded block.
  • Figure 2: Comparison of the task load dimensions for the three different control methods: Joy-Con, Head, and Button