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

Algorithms based on deep network models are being used for many patternrecognition and decision-making tasks in robotics and AI. Training these modelsrequires a large labeled dataset and considerable computational resources,which are not readily available in many domains. Also, it is difficult toexplore the internal representations and reasoning mechanisms of these models.As a step towards addressing the underlying knowledge representation,reasoning, and learning challenges, the architecture described in this paperdraws inspiration from research in cognitive systems. As a motivating example,we consider an assistive robot trying to reduce clutter in any given scene byreasoning about the occlusion of objects and stability of object configurationsin an image of the scene. In this context, our architecture incrementallylearns and revises a grounding of the spatial relations between objects anduses this grounding to extract spatial information from input images.Non-monotonic logical reasoning with this information and incompletecommonsense domain knowledge is used to make decisions about stability andocclusion. For images that cannot be processed by such reasoning, regionsrelevant to the tasks at hand are automatically identified and used to traindeep network models to make the desired decisions. Image regions used to trainthe deep networks are also used to incrementally acquire previously unknownstate constraints that are merged with the existing knowledge for subsequentreasoning. Experimental evaluation performed using simulated and real-worldimages indicates that in comparison with baselines based just on deep networks,our architecture improves reliability of decision making and reduces the effortinvolved in training data-driven deep network models.

Combining Commonsense Reasoning and Knowledge Acquisition to Guide Deep Learning in Robotics