Track manipulation, locomotion and embodied systems.
Search papers, labs, and topics across Lattice.
This survey provides a system-level review of Physical AI, analyzing the closed-loop process of physical interaction from perception to action and learning. It synthesizes recent advances in foundation models and robot learning, highlighting how these components interact to enable intelligent agents to operate in the physical world under uncertainty and real-time constraints. The paper identifies key challenges in generalization, resource efficiency, state tracking, safety, and adaptation, arguing for a shift towards integrated systems for robust physical autonomy.
Achieving reliable physical autonomy demands a system-level perspective, integrating diverse components beyond isolated model performance to navigate real-world complexities.
Physical AI aims to enable intelligent systems to perceive, reason, act, and learn through interaction with the physical world. Unlike purely digital intelligence, physical agents must operate under partial observability, uncertain dynamics, embodiment constraints, and real-time requirements, while their actions continuously reshape the environment and subsequent observations. Recent advances in foundation models and robot learning have expanded the capabilities of physical agents, yet achieving reliable autonomy requires more than improvements in individual models. This survey presents a comprehensive, system-level review of Physical AI, organized around the closed-loop process of physical interaction. We examine the foundations and recent developments in task representations and memory, predictive and action-generating models, data and learning methods, embodiment and control, computing systems, evaluation, and safety. Beyond reviewing individual advances, we investigate how these components interact and collectively shape the capabilities and limitations of Physical AI systems. Building on this integrated perspective, we identify fundamental challenges in generalization, resource-efficient learning and execution, reliable state tracking, safety, recovery, and continual adaptation. We argue that advancing Physical AI requires moving beyond isolated model performance toward integrated systems capable of robust, efficient, safe, and autonomous physical interaction under changing real-world conditions.