How do humans learn about the reliability of automation?
Abstract In a range of settings, human operators make decisions with the assistance of automation, the reliability of which can vary depending upon context. Currently, the processes by which humans track the level of reliability of automation are unclear. In the current study, we test cognitive mode...
| Autores principales: | , , , , |
|---|---|
| Formato: | Artículo |
| Lenguaje: | English |
| Publicado: |
SpringerOpen
2024-02-01
|
| Colección: | Cognitive Research |
| Materias: | |
| Acceso en línea: | https://doi.org/10.1186/s41235-024-00533-1 |
| _version_ | 1827328794126450688 |
|---|---|
| author | Luke Strickland Simon Farrell Micah K. Wilson Jack Hutchinson Shayne Loft |
| author_facet | Luke Strickland Simon Farrell Micah K. Wilson Jack Hutchinson Shayne Loft |
| author_sort | Luke Strickland |
| collection | DOAJ |
| description | Abstract In a range of settings, human operators make decisions with the assistance of automation, the reliability of which can vary depending upon context. Currently, the processes by which humans track the level of reliability of automation are unclear. In the current study, we test cognitive models of learning that could potentially explain how humans track automation reliability. We fitted several alternative cognitive models to a series of participants’ judgements of automation reliability observed in a maritime classification task in which participants were provided with automated advice. We examined three experiments including eight between-subjects conditions and 240 participants in total. Our results favoured a two-kernel delta-rule model of learning, which specifies that humans learn by prediction error, and respond according to a learning rate that is sensitive to environmental volatility. However, we found substantial heterogeneity in learning processes across participants. These outcomes speak to the learning processes underlying how humans estimate automation reliability and thus have implications for practice. |
| first_indexed | 2024-03-07T15:23:28Z |
| format | Article |
| id | doaj.art-014a96e1e76a4a6697595d3bfda614e9 |
| institution | Directory Open Access Journal |
| issn | 2365-7464 |
| language | English |
| last_indexed | 2024-03-07T15:23:28Z |
| publishDate | 2024-02-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Cognitive Research |
| spelling | doaj.art-014a96e1e76a4a6697595d3bfda614e92024-03-05T17:24:59ZengSpringerOpenCognitive Research2365-74642024-02-019112010.1186/s41235-024-00533-1How do humans learn about the reliability of automation?Luke Strickland0Simon Farrell1Micah K. Wilson2Jack Hutchinson3Shayne Loft4The Future of Work Institute, Curtin UniversityThe School of Psychological Science, The University of Western AustraliaThe Future of Work Institute, Curtin UniversityThe School of Psychological Science, The University of Western AustraliaThe School of Psychological Science, The University of Western AustraliaAbstract In a range of settings, human operators make decisions with the assistance of automation, the reliability of which can vary depending upon context. Currently, the processes by which humans track the level of reliability of automation are unclear. In the current study, we test cognitive models of learning that could potentially explain how humans track automation reliability. We fitted several alternative cognitive models to a series of participants’ judgements of automation reliability observed in a maritime classification task in which participants were provided with automated advice. We examined three experiments including eight between-subjects conditions and 240 participants in total. Our results favoured a two-kernel delta-rule model of learning, which specifies that humans learn by prediction error, and respond according to a learning rate that is sensitive to environmental volatility. However, we found substantial heterogeneity in learning processes across participants. These outcomes speak to the learning processes underlying how humans estimate automation reliability and thus have implications for practice.https://doi.org/10.1186/s41235-024-00533-1Human-automation teamingAutomation reliabilityCognitive modelLearning |
| spellingShingle | Luke Strickland Simon Farrell Micah K. Wilson Jack Hutchinson Shayne Loft How do humans learn about the reliability of automation? Cognitive Research Human-automation teaming Automation reliability Cognitive model Learning |
| title | How do humans learn about the reliability of automation? |
| title_full | How do humans learn about the reliability of automation? |
| title_fullStr | How do humans learn about the reliability of automation? |
| title_full_unstemmed | How do humans learn about the reliability of automation? |
| title_short | How do humans learn about the reliability of automation? |
| title_sort | how do humans learn about the reliability of automation |
| topic | Human-automation teaming Automation reliability Cognitive model Learning |
| url | https://doi.org/10.1186/s41235-024-00533-1 |
| work_keys_str_mv | AT lukestrickland howdohumanslearnaboutthereliabilityofautomation AT simonfarrell howdohumanslearnaboutthereliabilityofautomation AT micahkwilson howdohumanslearnaboutthereliabilityofautomation AT jackhutchinson howdohumanslearnaboutthereliabilityofautomation AT shayneloft howdohumanslearnaboutthereliabilityofautomation |