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

Creating autonomous robots that can actively explore the environment, acquireknowledge and learn skills continuously is the ultimate achievement envisionedin cognitive and developmental robotics. Their learning processes should bebased on interactions with their physical and social world in the manner ofhuman learning and cognitive development. Based on this context, in this paper,we focus on the two concepts of world models and predictive coding. Recently,world models have attracted renewed attention as a topic of considerableinterest in artificial intelligence. Cognitive systems learn world models tobetter predict future sensory observations and optimize their policies, i.e.,controllers. Alternatively, in neuroscience, predictive coding proposes thatthe brain continuously predicts its inputs and adapts to model its own dynamicsand control behavior in its environment. Both ideas may be considered asunderpinning the cognitive development of robots and humans capable ofcontinual or lifelong learning. Although many studies have been conducted onpredictive coding in cognitive robotics and neurorobotics, the relationshipbetween world model-based approaches in AI and predictive coding in roboticshas rarely been discussed. Therefore, in this paper, we clarify thedefinitions, relationships, and status of current research on these topics, aswell as missing pieces of world models and predictive coding in conjunctionwith crucially related concepts such as the free-energy principle and activeinference in the context of cognitive and developmental robotics. Furthermore,we outline the frontiers and challenges involved in world models and predictivecoding toward the further integration of AI and robotics, as well as thecreation of robots with real cognitive and developmental capabilities in thefuture.

World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges