스트리밍을 사용한 로봇 공학

import asyncio
from google import genai
from google.genai import types

MODEL = "gemini-robotics-er-2-streaming-preview"

# ── Tool definitions ─────────────────────────────────────────────────────────
tools = [
   {
       "function_declarations": [
           {
               "name": "navigate",
               "description": "Navigate the robot to a named waypoint.",
               "behavior": "BLOCKING",
               "parameters": {
                   "type": "OBJECT",
                   "properties": {"name": {"type": "STRING"}},
                   "required": ["name"],
               },
           },
           # Add more function definitions here
       ]
   }
]

# ── Stub tool executor (replace with real robot SDK calls) ───────────────────
def execute_tool(name: str, args: dict) -> dict:
   print(f"  [Tool] {name}({args})")
   return {"status": "success"}

# ── Input helpers ────────────────────────────────────────────────────────────
def send_text(session, text: str):
   """Send a text turn."""
   return session.send_client_content(
       turns=types.Content(role="user", parts=[types.Part(text=text)]),
       turn_complete=True,
   )

def send_image(session, image_bytes: bytes, prompt: str = ""):
   """Send a JPEG image with an optional text prompt."""
   parts = [
       types.Part(
           inline_data=types.Blob(data=image_bytes, mime_type="image/jpeg")
       )
   ]
   if prompt:
       parts.append(types.Part(text=prompt))
   return session.send_client_content(
       turns=types.Content(role="user", parts=parts),
       turn_complete=True,
   )

def send_audio(session, audio_chunk: bytes):
   """Stream a chunk of raw PCM audio (16-bit, 16 kHz, mono)."""
   return session.send_realtime_input(
       media=types.Blob(data=audio_chunk, mime_type="audio/pcm;rate=16000")
   )

# ── Receive loop ─────────────────────────────────────────────────────────────
async def receive_loop(session):
   """Print model text and handle tool calls until the session ends."""
   async for message in session.receive():
       if message.server_content:
           sc = message.server_content
           if sc.model_turn and sc.model_turn.parts:
               for part in sc.model_turn.parts:
                   if part.text:
                       print(f"Model: {part.text}", end="", flush=True)
           if sc.turn_complete:
               print("\n[Turn Complete]")
       elif message.tool_call:
           responses = []
           for call in message.tool_call.function_calls:
               print(f"\n[Tool Call] {call.name}({call.args})")
               result = execute_tool(call.name, call.args)
               responses.append(
                   types.FunctionResponse(
                       name=call.name,
                       response=result,
                       id=call.id,
                   )
               )
           await session.send_tool_response(function_responses=responses)

# ── Main ─────────────────────────────────────────────────────────────────────
async def main():
   client = genai.Client(api_key=os.environ["GEMINI_API_KEY"])
   config = types.LiveConnectConfig(
       response_modalities=["TEXT"],
       tools=tools,
       system_instruction=types.Content(
           parts=[types.Part(text="You are a robot controller. Use tools to execute commands.")]
       ),
   )
   async with client.aio.live.connect(model=MODEL, config=config) as session:
       recv_task = asyncio.create_task(receive_loop(session))
       # Connect robot perception callbacks and user inputs to the helpers above.
       recv_task.cancel()

asyncio.run(main())

async def heartbeat(session, camera, er_turn_done: asyncio.Event):
    TARGET_INTERVAL_SEC = 1.0

    while True:
        start_time = asyncio.get_running_loop().time()

        frame = await camera.latest_jpeg()
        await session.send_realtime_input(
            video=types.Blob(data=frame, mime_type="image/jpeg")
        )
        await session.send_realtime_input(
            text=(
                "[HEARTBEAT] If no task is active, call 'ack' and wait for user"
                " input. If a task is active: observe the scene. If the current"
                " step is progressing correctly, call 'ack'. If the current step"
                " is complete, call 'run_instruction' with the next step. If the"
                " overall goal is achieved, call 'reset' and inform the user."
            )
        )

        # Wait for the model to finish responding before sending the next heartbeat
        await er_turn_done.wait()
        er_turn_done.clear()

        # Sleep only the remaining time to maintain ~1 Hz cadence
        elapsed = asyncio.get_running_loop().time() - start_time
        remaining = TARGET_INTERVAL_SEC - elapsed
        if remaining > 0:
            await asyncio.sleep(remaining)

# In receive_loop: signal when the model finishes its turn
if sc.turn_complete:
    er_turn_done.set()

TOOLS = [
    {
        "name": "send_message",
        "description": (
            "Speak a message aloud via TTS, then deliver it to the"
            " specified target. Use target='user' to speak directly"
            " to the user, or a peer agent name (e.g., 'duo') to"
            " communicate with another robot."
        ),
        "parameters": {
            "type": "object",
            "properties": {
                "target": {
                    "type": "string",
                    "description": "Recipient: 'user' or a peer agent name.",
                },
                "message": {
                    "type": "string",
                    "description": "The message to speak and deliver.",
                },
            },
            "required": ["target", "message"],
        },
    },
]