Robotics
← Roadmap/Learning

Vision-Language-Action (VLA)

End-to-end physical-AI policies: images + language → actions.

Progress0/5 questions

Prerequisites

Why it matters in robotics

Vision-Language-Action models are the headline of 'physical AI' and the fastest-moving area of robot learning. Unlike classic modular perception-planning-control stacks, a VLA fine-tunes an internet-pretrained vision-language model into a single policy that turns camera images and a language instruction directly into robot actions. The lineage of systems behind this idea comes with real constraints: data scale, transferring across different robot bodies, control frequency and latency from large backbones, evaluation, and safety in a real-time loop.

What to study

  • Action representation: discrete action-token binning (RT-2/OpenVLA) vs. frequency-space tokenization (FAST/DCT) vs. continuous diffusion/flow-matching action heads (Octo, pi-0), and the precision/frequency tradeoffs of each.
  • Why internet pretraining helps: how a finetuned VLM backbone transfers semantic and visual knowledge so the policy generalizes to unseen objects, attributes, and language not present in the robot demos.
  • Key systems and their lineage: RT-1 (transformer policy), RT-2 (VLM-as-policy), Open X-Embodiment/RT-X (cross-embodiment data), Octo (open generalist diffusion policy), OpenVLA (7B open VLA), pi-0 and pi0-FAST (flow-matching vs. autoregressive).
  • Deployment realities and open problems: control frequency/latency vs. large-backbone inference (action chunking, async inference), data scale and cross-embodiment normalization, evaluation/reproducibility, and safety of language-conditioned action.

Where to study

Cheatsheet

Symbols used below

oto_tobservation (image + language) at time tt
ata_trobot action at time tt
HHaction-chunk length

What a VLA is

A vision-language-action model fine-tunes an internet-pretrained vision-language backbone so it maps (ot,instruction)at(o_t, \text{instruction}) \to a_t directly, replacing a hand-built perception-planning-control stack with one end-to-end policy.

Action representations

Discrete binning (RT-2, OpenVLA): each action dimension is quantized into bins and predicted as tokens, reusing the VLM's language-modeling head — simple, but coarse and slow (one token per dimension per step).

Frequency-space tokenization (FAST): actions are transformed (DCT-like) before tokenization so a short token sequence encodes a longer, smoother action chunk.

Diffusion / flow-matching heads (Octo, pi-0): a small action-expert network iteratively denoises a continuous action chunk conditioned on the VLM's features — higher precision and naturally multimodal, at the cost of extra inference steps.

Why pretraining transfers

The backbone's web-scale visual and semantic knowledge lets the policy recognize objects, attributes, and instructions it never saw in robot demonstrations — generalization comes from the frozen or lightly fine-tuned VLM, not from the (comparatively tiny) robot-action data.

System lineage

RT-1: transformer policy trained from scratch on robot data only. RT-2: co-trains a VLM on web + robot data, action-as-language-tokens. Open X-Embodiment / RT-X: pools demonstrations across many robot bodies into one cross-embodiment dataset. Octo: open generalist policy with a diffusion action head. OpenVLA: 7B openly-released VLA. pi-0 / pi0-FAST: flow-matching vs. autoregressive-token action generation from the same backbone family.

Control frequency vs. latency

A large VLM backbone can take well over 1/fcontrol1/f_{\text{control}} seconds to run, so systems predict an action chunk of length HH per forward pass and execute it open-loop for those HH steps, or run the slow backbone asynchronously alongside a fast low-level controller — trading reactivity for backbone size.

 Discrete bins (RT-2/OpenVLA)Frequency tokens (FAST)Diffusion / flow (Octo, pi-0)
OutputPer-dim discrete tokenCompressed token sequenceContinuous denoised chunk
PrecisionCoarse (bin width)Better temporal coverageHigh
Multimodal actionsNoNoYes
Inference costOne decode step per dimFewer tokens per chunkMultiple denoising steps

Application focus

Select an application above.

Practice questions (5)