Refactor voice control core and robot behavior

dataflow_voice_control_ulite6_zed.yml

@@ -43,22 +43,19 @@ nodes:
     path: dora_iobridge/dora_iobridge/main.py
     env:
       VIRTUAL_ENV: ./.venv
-      VOICE_HOST: "0.0.0.0"
-      VOICE_PORT: "8765"
-      VOICE_IN_OUTPUT: "voice_in"
-      VOICE_OUT_INPUT: "voice_out"
-      SCENE_INPUT: "scene_update"
+      WS_HOST: "0.0.0.0"
+      WS_PORT: "9001"
     inputs:
-      voice_out: voice/voice_out
-      scene_update: voice/scene_update
+      text_in: voice/voice_out
+      data_in: voice/scene_update
       tick: dora/timer/millis/100
     outputs:
-      - voice_in
+      - text_out
   - id: detector
     build: |
       uv venv -p 3.12 --seed --allow-existing
-      uv pip install -e dora_detector
-    path: dora_detector/dora_detector/main.py
+      uv pip install -e dora_yolo_object_detector
+    path: dora_yolo_object_detector/dora_yolo_object_detector/main.py
     env:
       VIRTUAL_ENV: ./.venv
       IMAGE_INPUT: "image_bgr"
@@ -90,6 +87,7 @@ nodes:
     path: dora_voice_control/dora_voice_control/main.py
     env:
       VIRTUAL_ENV: ./.venv
+      ROBOT_TYPE: "vacuum"  # "vacuum" or "gripper"
       OBJECTS_INPUT: "objects"
       POSE_INPUT: "tcp_pose"
       STATUS_INPUT: "status"
@@ -119,12 +117,12 @@ nodes:
       IMAGE_WIDTH: "1280"
       IMAGE_HEIGHT: "720"
       API_ENABLED: "true"
-      API_PORT: "8080"
+      API_PORT: "9002"
     inputs:
       objects: detector/objects
       tcp_pose: ulite6/tcp_pose
       status: ulite6/status
-      voice_in: iobridge/voice_in
+      voice_in: iobridge/text_out
       image_annotated: detector/image_annotated
       tick: dora/timer/millis/100
     outputs: