Review
Open access
Aug 2026
Vision‐Language‐Action Models for Embodied Artificial Intelligence: A Comprehensive Survey
A comprehensive review of VLA models for Embodied AI from an action‐generation perspective and proposes an action‐generation‐centered taxonomy that categorizes VLA models into three paradigms: direct policy learning, generative action modeling, and reasoning‐guided modeling.
Ning Xiong, Mingle Xu, Wei Chen et al.
· Journal of Field Robotics · 0 citations