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

The current paper presents how a predictive coding type deep recurrent neuralnetworks can generate vision-based goal-directed plans based on prior learningexperience by examining experiment results using a real arm robot. The proposeddeep recurrent neural network learns to predict visuo-proprioceptive sequencesby extracting an adequate predictive model from various visuomotor experiencesrelated to object-directed behaviors. The predictive model was developed interms of mapping from intention state space to expected visuo-proprioceptivesequences space through iterative learning. Our arm robot experiments adoptedwith three different tasks with different levels of difficulty showed that theerror minimization principle in the predictive coding framework applied toinference of the optimal intention states for given goal states can generategoal-directed plans even for unlearned goal states with generalization. It was,however, shown that sufficient generalization requires relatively large numberof learning trajectories. The paper discusses possible countermeasure toovercome this problem.

Generating Goal-Directed Visuomotor Plans Based on Learning Using a Predictive Coding-type Deep Visuomotor Recurrent Neural Network Model