# rSkill manifest — RT-DETR COCO detector (kind: detector)
#
# Packages a PaddlePaddle RT-DETR-L model exported to ONNX for use as
# an OpenRAL perception producer. The skill runs on the camera tee and
# publishes ObjectsMetadata to /openral/perception/objects.
#
# This is a pure perception producer: it emits no Action chunks, drives
# no actuators, and has no proprioception contract. The runtime
# ObjectsDetector (openral_perception) reads the detector block at
# configure time to initialise the ONNX session and label map.
#
# LICENSE: weights are Apache-2.0 (PaddlePaddle RT-DETR public release).

schema_version: "0.1"
name: "OpenRAL/rskill-rtdetr_coco_r18-any-coco-fp32"
version: "0.1.0"
license: "apache-2.0"
role: "s1"
kind: "detector"  # Perception producer; emits ObjectsMetadata, no Action

# ── Compatibility contract ──────────────────────────────────────────────────
# embodiment-agnostic: a perception rSkill (detector/vlm) needs only an RGB
# camera, not a specific robot. The rSkill<->robot gate exempts these kinds
# (loader._EMBODIMENT_AGNOSTIC_KINDS), so the tag list is empty —
# it matches any robot/scene.
embodiment_tags: ["any"]  # explicit embodiment-agnostic wildcard

# The detector reads any RGB camera stream. vla_feature_key is omitted so
# the loader accepts any camera key, not just "camera1".
sensors_required:
  - modality: "rgb"
    min_width: 640
    min_height: 480

# Detectors command no actuators.
actuators_required: []

# ── Runtime / weights ───────────────────────────────────────────────────────
runtime: "onnx"
quantization:
  dtype: "fp32"
  backend: "onnx"

# RT-DETR-L exported to ONNX. References the in-tree rSkill package.
# The loader resolves local:// to the local rskills/<id>/ directory.
weights_uri: "local://rskills/rtdetr-coco-r18"

# ── Execution semantics ─────────────────────────────────────────────────────
# chunk_size is 1: the detector runs per-frame. The safety supervisor never
# sees detector output (no Action chunks), but chunk_size=1 keeps the
# execution tick consistent with the camera frame rate.
chunk_size: 1
latency_budget:
  # RT-DETR-L on an NVIDIA GPU is typically 15-30 ms; allow 50 ms budget
  # to cover CPU fallback on smaller hosts.
  per_chunk_ms: 50.0

# ── Detector contract ────────────────────────────────────────────────────
# 80 COCO labels (subset shown for readability — full list matches the
# 0-indexed COCO category order used by the exported model).
detector:
  # Always-on background producer (publishes ObjectsMetadata to
  # WorldState; not the on-demand locate_in_view locator).
  mode: "continuous"
  labels:
    - "person"
    - "bicycle"
    - "car"
    - "motorcycle"
    - "airplane"
    - "bus"
    - "train"
    - "truck"
    - "boat"
    - "traffic light"
    - "fire hydrant"
    - "stop sign"
    - "parking meter"
    - "bench"
    - "bird"
    - "cat"
    - "dog"
    - "horse"
    - "sheep"
    - "cow"
    - "elephant"
    - "bear"
    - "zebra"
    - "giraffe"
    - "backpack"
    - "umbrella"
    - "handbag"
    - "tie"
    - "suitcase"
    - "frisbee"
    - "skis"
    - "snowboard"
    - "sports ball"
    - "kite"
    - "baseball bat"
    - "baseball glove"
    - "skateboard"
    - "surfboard"
    - "tennis racket"
    - "bottle"
    - "wine glass"
    - "cup"
    - "fork"
    - "knife"
    - "spoon"
    - "bowl"
    - "banana"
    - "apple"
    - "sandwich"
    - "orange"
    - "broccoli"
    - "carrot"
    - "hot dog"
    - "pizza"
    - "donut"
    - "cake"
    - "chair"
    - "couch"
    - "potted plant"
    - "bed"
    - "dining table"
    - "toilet"
    - "tv"
    - "laptop"
    - "mouse"
    - "remote"
    - "keyboard"
    - "cell phone"
    - "microwave"
    - "oven"
    - "toaster"
    - "sink"
    - "refrigerator"
    - "book"
    - "clock"
    - "vase"
    - "scissors"
    - "teddy bear"
    - "hair drier"
    - "toothbrush"
  input_size: [640, 640]
  score_threshold: 0.7

# ── Provenance ──────────────────────────────────────────────────────────────
paper_url: "https://arxiv.org/abs/2304.08069"
source_repo: "hf://PekingU/rtdetr_r18vd_coco_o365"

description: >
  RT-DETR-L (Real-Time DEtection TRansformer, large variant) trained on
  COCO and exported to ONNX. Runs on the camera tee and publishes
  ObjectsMetadata to /openral/perception/objects. 80 COCO categories.
  Apache-2.0 weights. Reference latency ~20 ms on GPU, ~45 ms on CPU.
  This is the detector rSkill kind contract.

# Action vocabulary for the reasoner LLM tool palette.
# DETECT signals that this skill is a perception producer.
actions:
  - "detect"

objects:
  - "person"
  - "cup"
  - "bottle"
  - "bowl"
  - "chair"
  - "table"
scenes:
  - "tabletop"
  - "kitchen"
  - "indoor"