English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Emergent behavior arising in a joint human-robot system cannot be fullypredicted based on an understanding of the individual agents. Typically, robotbehavior is governed by algorithms that optimize a reward function that shouldquantitatively capture the joint system's goal. Although reward functions canbe updated to better match human needs, this is no guarantee that nomisalignment with the complex and variable human needs will occur. Algorithmsmay learn undesirable behavior when interacting with the human and theintrinsically unpredictable human-inhabited world, thereby producing furthermisalignment with human users or bystanders. As a result, humans might behavedifferently than anticipated, causing robots to learn differently andundesirable behavior to emerge. With this short paper, we state that to designfor Human-Robot Interaction that mitigates such undesirable emergent behavior,we need to complement advancements in human-robot interaction algorithms withhuman factors knowledge and expertise. More specifically, we advocate athree-pronged approach that we illustrate using a particularly challengingexample of safety-critical human-robot interaction: a driver interacting with asemi-automated vehicle. Undesirable emergent behavior should be mitigated by acombination of 1) including driver behavioral mechanisms in the vehicle'salgorithms and reward functions, 2) model-based approaches that account forinteraction-induced driver behavioral adaptations and 3) driver-centeredinteraction design that promotes driver engagement with the semi-automatedvehicle, and the transparent communication of each agent's actions that allowsmutual support and adaptation. We provide examples from recent empirical workin our group, in the hope this proves to be fruitful for discussing emergenthuman-robot interaction.

Mitigating undesirable emergent behavior arising between driver and semi-automated vehicle