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

Affordance information about a scene provides important clues as to whatactions may be executed in pursuit of meeting a specified goal state. Thus,integrating affordance-based reasoning into symbolic action plannning pipelineswould enhance the flexibility of robot manipulation. Unfortunately, the topperforming affordance recognition methods use object category priors to boostthe accuracy of affordance detection and segmentation. Object priors limitgeneralization to unknown object categories. This paper describes an affordancerecognition pipeline based on a category-agnostic region proposal network forproposing instance regions of an image across categories. To guide affordancelearning in the absence of category priors, the training process includes theauxiliary task of explicitly inferencing existing affordances within aproposal. Secondly, a self-attention mechanism trained to interpret eachproposal learns to capture rich contextual dependencies through the region.Visual benchmarking shows that the trained network, called AffContext, reducesthe performance gap between object-agnostic and object-informed affordancerecognition. AffContext is linked to the Planning Domain Definition Language(PDDL) with an augmented state keeper for action planning across temporallyspaced goal-oriented tasks. Manipulation experiments show that AffContext cansuccessfully parse scene content to seed a symbolic planner problemspecification, whose execution completes the target task. Additionally,task-oriented grasping for cutting and pounding actions demonstrate theexploitation of multiple affordances for a given object to complete specifiedtasks.

Recognizing Object Affordances to Support Scene Reasoning for Manipulation Tasks