Frame Transformer

A FrameTransformer measures target poses relative to a source frame across all environments. Use it to track a hand, foot, or object without calculating each transform yourself.

Define frames

The sensor’s prim_path selects the source rigid body. Each FrameCfg selects one or more target rigid bodies and can add a fixed pose offset. Target paths accept regular expressions; the data order is recorded in target_frame_names.

from isaaclab.sensors import FrameTransformerCfg
feet_in_base = FrameTransformerCfg(
    prim_path="{ENV_REGEX_NS}/Robot/base",
    target_frames=[
        FrameTransformerCfg.FrameCfg(
            prim_path="{ENV_REGEX_NS}/Robot/.*_FOOT",
            name="foot",
        ),
    ],
    debug_vis=True,
)

A target expression is inclusive. If it also matches the source body, the output includes the identity transform from the source to itself. Use a narrower expression when that entry is not wanted.

Read transforms

For E environments and T resolved target frames, positions have shape (E, T, 3), quaternions have shape (E, T, 4), and combined poses have shape (E, T, 7). Quaternions use (x, y, z, w) order.

transforms = scene["feet_in_base"].data
foot_names = transforms.target_frame_names
foot_pos_b = transforms.target_pos_source.torch
foot_quat_b = transforms.target_quat_source.torch
foot_pose_w = transforms.target_pose_w.torch

target_*_source fields express targets in the configured source frame. target_*_w fields express the offset target frames in the world frame. The corresponding source_*_w fields expose the offset source frame in world coordinates. Positions are in meters; quaternions are unitless.

A complete runnable example is available as frame-transformer:

uv run --extra isaacsim isaaclab example frame-transformer