Principle:ARISE Initiative Robosuite Action Vector Construction
Metadata:
- robosuite
- Teleoperation
- Control_Systems
- last_updated: 2026-02-15 12:00 GMT
Overview
Mechanism for assembling a flat action vector from a structured action dictionary by concatenating per-part actions in the correct order for environment stepping.
Description
Robosuite robots may have multiple controllable parts (arm, gripper, mobile base, torso). Each part controller expects its own action sub-vector. The action dictionary from input2action() maps part names to their individual action arrays. create_action_vector() concatenates these in the order expected by the composite controller to form a single flat numpy array compatible with env.step().
Usage
Use in teleoperation loops between device.input2action() and env.step() to convert structured actions to flat vectors.
Theoretical Basis
Action space composition. Multi-part robots have composite action spaces. Each part contributes a sub-vector. The composite controller defines the ordering. Pseudocode only.