DIGIT
Status: hardware-verified
Hardware-verified Collection with the left and right DIGIT is checked on Rakuda2.
DigitSensor uses digit-interface to capture tactile images. It requires the digit extra (Installation). Set different serial numbers for the left and right sensors.
type: digit
serial: SET_DIGIT_LEFT_SERIAL
name: left
resolution: QVGA
height: 320
width: 240
fps: 30
resolution |
height |
width |
|---|---|---|
QVGA |
320 | 240 |
VGA |
640 | 480 |
Because digit-interface.get_frame() returns a transposed image, the configured height and width are in this order. Do not swap them back to the usual QVGA/VGA width/height notation. Choose fps from the values the SDK supports for that resolution; unsupported values are rejected on connection.
Captured images are converted from BGR to RGB. When the node names are digit_left / digit_right, they are recorded in observation.images.digit_left / observation.images.digit_right.
Each DIGIT node also needs a max_age_ms entry in nodes/recorder.yaml; see "Recorder entry" in Sensors.
The supported Rakuda2 configurations and how to combine DIGIT with gravity compensation are on the robot page.
Image storage
Set storage: video | image in each image sensor's node YAML (RealSense, DIGIT, V4L2 including Pika wrist cameras). The default is video: the existing lossy MP4 encoding. image embeds lossless PNG frames in Parquet; use it for DIGIT/background pixel differences. Formats can be mixed in one dataset. Invalid values are refused at configuration load, including validate.
PNG generally needs more disk space and PNG compression/write work; actual size and throughput depend on image content and hardware. As an uncompressed RGB reference, 320×240×3 at 30 dataset fps is 6.9 MB/s per sensor (640×480: 27.6 MB/s); these are not measured PNG rates. LeRobot 0.7.0 uses PNG compression level 6 for image. Changing storage changes the feature dtype: choose a separate dataset output; resume into the previous schema is refused.
Live observations remain HWC uint8 RGB, and LeRobot dataset reads return CHW float32 in [0, 1] for either format by default. Checkpoint inputs remain VISUAL. Storage was tested with mock/synthetic frames only, without hardware.
The codec of video MP4s (H.264 by default, or AV1) is chosen with the recorder's video_codec.