The mechanism
A learned robot policy maps observations into an action representation trained for a particular embodiment and task distribution. An action token is not self-describing: a codec must map it to units, coordinate conventions, action dimensions and an update interval. A policy may produce an in-range token whose decoded action is unsuitable for the current geometry or dynamics. RT-2 gives primary context for learning action-token outputs from robot trajectories and vision-language data. The five-bin codec below is an authored example, not RT-2’s actual encoding or a running VLA model. Its purpose is to connect a symbolic output to a bounded numeric command and to keep that command distinct from a successfully completed physical task.
- The observation contract specifies sensor inputs, timestamps, frames and any task-language context.
- A learned or recorded policy produces an action representation associated with a specific model and embodiment.
- The action codec maps symbols to declared command units, bounds and timing.
- Runtime constraints and feedback evaluate feasibility and observed completion; token validity alone is insufficient.
Science and assumptions
Learned action policies need embodiment evidence · explicit relationship
This authored uniform codec maps an integer bin to velocity, then integrates that ideal velocity over one interval.
Symbols and units
- k
- Integer action bin from 0 through B−1
index
- B
- Number of bins, at least two
count
- vmax
- Positive maximum encoded speed
m/s
- v(k)
- Decoded velocity command
m/s
- Δt
- Command interval
s
- Δx
- Ideal requested displacement
m
An authored one-axis codec maps integer bins 0 through 4 uniformly onto velocities −0.2, −0.1, 0, 0.1 and 0.2 m/s. Bin 4 therefore commands +0.2 m/s; under an ideal constant-velocity interval of 0.2 s it requests 0.04 m displacement. Bin 5 is outside the schema and must be rejected. A valid bin 4 may still point into an obstacle, so range validation cannot replace geometry or feedback. These numbers illustrate action semantics without claiming that a language model produced or successfully executed them.
Assumptions Teaching codec only; not a published model’s tokenization. Actual motion requires compatible control, geometry and dynamics; a requested displacement is not observed completion.
Engineering example
An authored one-axis codec maps integer bins 0 through 4 uniformly onto velocities −0.2, −0.1, 0, 0.1 and 0.2 m/s. Bin 4 therefore commands +0.2 m/s; under an ideal constant-velocity interval of 0.2 s it requests 0.04 m displacement. Bin 5 is outside the schema and must be rejected. A valid bin 4 may still point into an obstacle, so range validation cannot replace geometry or feedback. These numbers illustrate action semantics without claiming that a language model produced or successfully executed them.
Distinctions and tradeoffs
A legal action token is not proof that the robot can safely or successfully execute it.
Discretized actions simplify an output vocabulary but trade resolution against representation size and still depend on the trained embodiment.
Vision-language-action systems connect learned representations to actuation through codecs, constraints and feedback.
Specifications and interfaces
- Mechanism boundary
- What makes an action token meaningful to a robot?
Teaching codec only; not a published model’s tokenization. Actual motion requires compatible control, geometry and dynamics; a requested displacement is not observed completion.
- Evidence type
- Authored worked example
Worked explanation with a bounded numeric or state example. This lesson does not claim an executing implementation of an external model or platform.
Interfaces
- Declared input and state Input
- The observation contract specifies sensor inputs, timestamps, frames and any task-language context.
- Checked outcome Output
- Decode a bounded action representation into physical units and distinguish valid output from feasible motion.
Check your understanding
Under the stated codec, what displacement does bin 4 request over 0.2 s?
- 0.04 m
- 0.4 m
- Four meters because the token is 4
Answer and reasoning
0.04 m
Bin 4 maps to 0.2 m/s; multiplying by 0.2 s gives 0.04 m under the ideal velocity assumption.
Evidence and scope
This is a worked explanation, not an executing external platform, model or robot. The quantities and fixtures are authored. Source scope is recorded in the automation learning review manifest; no source benchmark or private system behavior is claimed. Teaching codec only; not a published model’s tokenization. Actual motion requires compatible control, geometry and dynamics; a requested displacement is not observed completion.
The worked example explains this mechanism. General numerical labs are a reference; they do not execute this lesson’s full mechanism.