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

When faced with an execution failure, an intelligent robot should be able toidentify the likely reasons for the failure and adapt its execution policyaccordingly. This paper addresses the question of how to utilise knowledgeabout the execution process, expressed in terms of learned constraints, inorder to direct the diagnosis and experience acquisition process. Inparticular, we present two methods for creating a synergy between failurediagnosis and execution model learning. We first propose a method fordiagnosing execution failures of parameterised action execution models, whichsearches for action parameters that violate a learned precondition model. Wethen develop a strategy that uses the results of the diagnosis process forgenerating synthetic data that are more likely to lead to successful execution,thereby increasing the set of available experiences to learn from. Thediagnosis and experience correction methods are evaluated for the problem ofhandle grasping, such that we experimentally demonstrate the effectiveness ofthe diagnosis algorithm and show that corrected failed experiences cancontribute towards improving the execution success of a robot.

Robot Action Diagnosis and Experience Correction by Falsifying Parameterised Execution Models