Sources — Foundations of Vision Language Action Models

The references below are organized as a developmental chain describing how perception, embodiment, action, control, autonomous systems, and Vision Language Action Models (VLAs) became progressively formalized across disciplines.

Perceptual Foundations

The foundational question concerns how perception emerges from environmental observation.

Maurice Merleau-Ponty
Phenomenology of Perception (1945)
https://archive.org/details/phenomenologyofp0000merl_e6m9
James J. Gibson
The Ecological Approach to Visual Perception (1979)
https://archive.org/details/pdfy-u5hmFOvOM2Civ4Gz/mode/2up

Embodiment and Action

Perception becomes operational through embodied interaction and action.

André Leroi-Gourhan
Gesture and Speech (1964-1965)
https://archive.org/details/leroi-gourhan-andre-gesture-and-speech

Environment and Meaning

Perception and action occur within environmental and relational systems.

Gregory Bateson
Steps to an Ecology of Mind (1972)
https://archive.org/details/stepstoecologyof0000bate

Decision and Control

Observed conditions become actionable through decision and control processes.

Herbert A. Simon
Administrative Behavior (1947)
https://archive.org/details/administrativebe0000simo_f3b1
W. Ross Ashby
An Introduction to Cybernetics (1956)
https://archive.org/details/AnIntroductionToCybernetics

Autonomous Systems

Perception, interpretation, and control become integrated within autonomous system architectures.

Stuart Russell & Peter Norvig
Artificial Intelligence: A Modern Approach (1995)
https://archive.org/details/isbn_9788177583670
Robin Murphy
Introduction to AI Robotics (2000)
https://archive.org/details/introductiontoai0000murp
Peter Corke
Robotics, Vision and Control (2011)
https://archive.org/details/bwb_P8-AQW-220

Vision-Language-Action Models

Google DeepMind
RT-1: Robotics Transformer for Real-World Control at Scale (2022)
https://arxiv.org/abs/2212.06817
Google DeepMind
RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control (2023)
https://arxiv.org/abs/2307.15818
OpenVLA
Open Vision-Language-Action Models (2024)
https://arxiv.org/abs/2406.09246

Structural Interpretation

Taken together, these references describe a progression from perception and embodied action toward autonomous systems capable of transforming environmental observations into realized state transitions.

Perception

Embodiment

Environment

Decision

Control

Autonomous Systems

Vision Language Action Models (VLAs)

Within this progression, Vision Language Action Models (VLAs) represent contemporary autonomous system architectures that integrate perception, interpretation, action selection, and transition realization within a unified operational framework.