📄 Abstract
Abstract: Autonomous agents are increasingly expected to operate in complex, dynamic,
and uncertain environments, performing tasks such as manipulation, navigation,
and decision-making. Achieving these capabilities requires agents to understand
the underlying mechanisms and dynamics of the world, moving beyond purely
reactive control or simple replication of observed states. This motivates the
development of world models as internal representations that encode
environmental states, capture dynamics, and enable prediction, planning, and
reasoning. Despite growing interest, the definition, scope, architectures, and
essential capabilities of world models remain ambiguous. In this survey, rather
than directly imposing a fixed definition and limiting our scope to methods
explicitly labeled as world models, we examine approaches that exhibit the core
capabilities of world models through a review of methods in robotic
manipulation. We analyze their roles across perception, prediction, and
control, identify key challenges and solutions, and distill the core
components, capabilities, and functions that a real world model should possess.
Building on this analysis, we aim to outline a roadmap for developing
generalizable and practical world models for robotics.
Key Contributions
This survey examines methods in robotic manipulation that exhibit core capabilities of world models, such as perception, prediction, and planning, even if not explicitly labeled as such. It aims to clarify the scope and architectures of world models by analyzing their manifestation in manipulation tasks.
Business Value
Provides a foundational understanding for developing more intelligent and adaptable robots capable of complex tasks in unstructured environments, leading to advancements in automation across industries.