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

Computer vision approaches are widely used by autonomous robotic systems tosense the world around them and to guide their decision making as they performdiverse tasks such as collision avoidance, search and rescue, and objectmanipulation. High accuracy is critical, particularly for Human-on-the-loop(HoTL) systems where decisions are made autonomously by the system, and humansplay only a supervisory role. Failures of the vision model can lead toerroneous decisions with potentially life or death consequences. In this paper,we propose a solution based upon adaptive autonomy levels, whereby the systemdetects loss of reliability of these models and responds by temporarilylowering its own autonomy levels and increasing engagement of the human in thedecision-making process. Our solution is applicable for vision-based tasks inwhich humans have time to react and provide guidance. When implemented, ourapproach would estimate the reliability of the vision task by consideringuncertainty in its model, and by performing covariate analysis to determinewhen the current operating environment is ill-matched to the model's trainingdata. We provide examples from DroneResponse, in which small Unmanned AerialSystems are deployed for Emergency Response missions, and show how the visionmodel's reliability would be used in addition to confidence scores to drive andspecify the behavior and adaptation of the system's autonomy. This workshoppaper outlines our proposed approach and describes open challenges at theintersection of Computer Vision and Software Engineering for the safe andreliable deployment of vision models in the decision making of autonomoussystems.

Adaptive Autonomy in Human-on-the-Loop Vision-Based Robotics Systems