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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Deep neural networks (DNNs) can be useful within the marine robotics field,but their utility value is restricted by their black-box nature. Explainableartificial intelligence methods attempt to understand how such black-boxes maketheir decisions. In this work, linear model trees (LMTs) are used toapproximate the DNN controlling an autonomous surface vessel (ASV) in asimulated environment and then run in parallel with the DNN to giveexplanations in the form of feature attributions in real-time. How well a modelcan be understood depends not only on the explanation itself, but also on howwell it is presented and adapted to the receiver of said explanation. Differentend-users may need both different types of explanations, as well as differentrepresentations of these. The main contributions of this work are (1)significantly improving both the accuracy and the build time of a greedyapproach for building LMTs by introducing ordering of features in the splittingof the tree, (2) giving an overview of the characteristics of theseafarer/operator and the developer as two different end-users of the agent andreceiver of the explanations, and (3) suggesting a visualization of the dockingagent, the environment, and the feature attributions given by the LMT for whenthe developer is the end-user of the system, and another visualization for whenthe seafarer or operator is the end-user, based on their differentcharacteristics.

Explaining a Deep Reinforcement Learning Docking Agent Using Linear Model Trees with User Adapted Visualization