Evaluating levels of automation in human–robot collaboration at different workload levels

Dana Gutman, Samuel Olatunji, Yael Edan

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

This study explored how levels of automation (LOA) influence human robot collaboration when operating at different levels of workload. Two LOA modes were designed, implemented, and evaluated in an experimental collaborative assembly task setup for four levels of workload composed of a secondary task and task complexity. A user study conducted involving 80 participants was assessed through two constructs especially designed for the evaluation (quality of task execution and usability) and user preferences regarding the LOA modes. Results revealed that the quality of task execution and usability was better at high LOA for low workload. Most of participants also preferred high LOA when the workload increases. However, when complexity existed within the workload, most of the participants preferred the low LOA. The results reveal the benefits of high and low LOA in different workload situations. This study provides insights related to shared control designs and reveals the importance of considering different levels of workload as influenced by secondary tasks and task complexity when designing LOA in human–robot collaborations.

Original languageEnglish
Article number7340
JournalApplied Sciences (Switzerland)
Volume11
Issue number16
DOIs
StatePublished - 2 Aug 2021

Keywords

  • Assembly task
  • Human–robot collaboration
  • Quality of task execution
  • Usability
  • User preferences
  • User studies

ASJC Scopus subject areas

  • Materials Science (all)
  • Instrumentation
  • Engineering (all)
  • Process Chemistry and Technology
  • Computer Science Applications
  • Fluid Flow and Transfer Processes

Fingerprint

Dive into the research topics of 'Evaluating levels of automation in human–robot collaboration at different workload levels'. Together they form a unique fingerprint.

Cite this