空間推論

Gemini Robotics ER 模型可以指向物件、在影片中追蹤物件、以定界框偵測物件，以及生成移動軌跡。

如需完整的可執行程式碼，請參閱「機器人食譜」。

對準物件

以下範例會在圖片中尋找特定物件，並傳回標準化的 [y, x] 座標：

Python

from google import genai

PROMPT = """
          Point to no more than 10 items in the image. The label returned
          should be an identifying name for the object detected.
          The answer should follow the json format: [{"point": <point>,
          "label": <label1>}, ...]. The points are in [y, x] format
          normalized to 0-1000.
        """
client = genai.Client()

uploaded_file = client.files.upload(file="my-image.png")

image_response = client.interactions.create(
    model="gemini-robotics-er-2-preview",
    input=[
        {
            "type": "image",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        },
        {"type": "text", "text": PROMPT}
    ],
    generation_config={"thinking_level": "high"},
)

print(image_response.output_text)

REST

# First, ensure you have the image file locally.
# Encode the image to base64
IMAGE_BASE64=$(base64 -w 0 my-image.png)

curl -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-robotics-er-2-preview",
    "input": {
      "parts": [
        {
          "inlineData": {
            "mimeType": "image/png",
            "data": "'"${IMAGE_BASE64}"'"
          }
        },
        {
          "text": "Point to no more than 10 items in the image. The label returned should be an identifying name for the object detected. The answer should follow the json format: [{\"point\": [y, x], \"label\": <label1>}, ...]. The points are in [y, x] format normalized to 0-1000."
        }
      ]
    },
    "generation_config": {
      "thinking_config": {
        "thinking_level": "high"
      }
    }
  }'

輸出內容會是包含物件的 JSON 陣列，每個物件都有 point (標準化 [y, x] 座標) 和用於識別物件的 label。

JSON

[
  {"point": [376, 508], "label": "small banana"},
  {"point": [287, 609], "label": "larger banana"},
  {"point": [223, 303], "label": "pink starfruit"},
  {"point": [435, 172], "label": "paper bag"},
  {"point": [270, 786], "label": "green plastic bowl"},
  {"point": [488, 775], "label": "metal measuring cup"},
  {"point": [673, 580], "label": "dark blue bowl"},
  {"point": [471, 353], "label": "light blue bowl"},
  {"point": [492, 497], "label": "bread"},
  {"point": [525, 429], "label": "lime"}
]

下圖顯示這些點的範例：

顯示圖片中物體點的範例

追蹤影片中的物件

Gemini Robotics ER 2 也能分析影片影格，追蹤一段時間內的物體。如需支援的影片格式清單，請參閱「影片輸入」。

Python

from google import genai

client = genai.Client()

uploaded_file = client.files.upload(file="my-video.mp4")

prompt = """
          Point to the red ball in every frame where it appears.
          The answer should follow the json format: [{"point": [y, x],
          "label": <label>}, ...]. The points are in [y, x] format
          normalized to 0-1000. Return one entry per frame that contains
          the object.
        """

image_response = client.interactions.create(
  model="gemini-robotics-er-2-preview",
  input=[
    {
        "type": "video",
        "uri": uploaded_file.uri,
        "mime_type": uploaded_file.mime_type
    },
    {"type": "text", "text": prompt}
  ],
)

print(image_response.output_text)

物件偵測和定界框

除了點之外，您也可以提示模型傳回 2D 定界框，為偵測到的物件提供更多空間細節。

Python

from google import genai

client = genai.Client()

uploaded_file = client.files.upload(file="my-image.png")

prompt = """
          Detect all objects in this image and return bounding boxes.
          The answer should follow the JSON format:
          [{"label": <label>, "y": <y_min>, "x": <x_min>,
            "y2": <y_max>, "x2": <x_max>}, ...]
          where coordinates are normalized to 0-1000.
        """

image_response = client.interactions.create(
  model="gemini-robotics-er-2-preview",
  input=[
    {
        "type": "image",
        "uri": uploaded_file.uri,
        "mime_type": uploaded_file.mime_type
    },
    {"type": "text", "text": prompt}
  ],
)

print(image_response.output_text)

軌跡

Gemini Robotics ER 2 可生成定義軌跡的點序列，引導機器人移動。

這個範例要求將紅筆移動到收納盒的軌跡，包括中間路徑點的估計值。程式碼已縮減，只顯示提示。

Python

prompt = """
          Generate a trajectory for the robotic arm to pick up the red pen
          and place it in the organizer. Return a list of waypoints as JSON:
          [{"step": <int>, "point": [y, x], "action": <description>}, ...]
          where coordinates are normalized to 0-1000.
        """

為筆電預留空間

這個範例顯示 Gemini Robotics ER 如何推論空間。提示會要求模型找出需要移動的物件，以便為其他項目騰出空間。

Python

from google import genai

client = genai.Client()

uploaded_file = client.files.upload(file="path/to/image-with-objects.jpg")

prompt = """
          Point to the object that I need to remove to make room for my laptop
          The answer should follow the JSON format: [{"point": <point>,
          "label": <label1>}, ...]. The points are in [y, x] format normalized to 0-1000.
        """

image_response = client.interactions.create(
  model="gemini-robotics-er-2-preview",
  input=[
    {
        "type": "image",
        "uri": uploaded_file.uri,
        "mime_type": uploaded_file.mime_type
    },
    {"type": "text", "text": prompt}
  ],
)

print(image_response.output_text)

回覆內容包含可回答使用者問題的物體 2D 座標，在本例中，該物體應移動，為筆電騰出空間。

[
  {"point": [672, 301], "label": "The object that I need to remove to make room for my laptop"}
]

範例：顯示另一個物件需要移動的物件

準備午餐

模型也能提供多步驟工作的操作說明，並指出每個步驟的相關物件。這個範例顯示模型如何規劃一系列步驟，將午餐裝進袋子。

Python

from google import genai

client = genai.Client()

uploaded_file = client.files.upload(file="path/to/image-of-lunch.jpg")

prompt = """
          Explain how to pack the lunch box and lunch bag. Point to each
          object that you refer to. Each point should be in the format:
          [{"point": [y, x], "label": }], where the coordinates are
          normalized between 0-1000.
        """

image_response = client.interactions.create(
  model="gemini-robotics-er-2-preview",
  input=[
    {
        "type": "image",
        "uri": uploaded_file.uri,
        "mime_type": uploaded_file.mime_type
    },
    {"type": "text", "text": prompt}
  ],
)

print(image_response.output_text)

這個提示詞的回覆內容是一組逐步說明，教導如何包裝圖片輸入內容中的午餐袋。

輸入圖片

午餐盒和要放入其中的物品圖片

模型輸出內容

Based on the image, here is a plan to pack the lunch box and lunch bag:

1.  **Pack the fruit into the lunch box.** Place the [apple](apple), [banana](banana), [red grapes](red grapes), and [green grapes](green grapes) into the [blue lunch box](blue lunch box).
2.  **Add the spoon to the lunch box.** Put the [blue spoon](blue spoon) inside the lunch box as well.
3.  **Close the lunch box.** Secure the lid on the [blue lunch box](blue lunch box).
4.  **Place the lunch box inside the lunch bag.** Put the closed [blue lunch box](blue lunch box) into the [brown lunch bag](brown lunch bag).
5.  **Pack the remaining items into the lunch bag.** Place the [blue snack bar](blue snack bar) and the [brown snack bar](brown snack bar) into the [brown lunch bag](brown lunch bag).

Here is the list of objects and their locations:
*   [{"point": [899, 440], "label": "apple"}]
*   [{"point": [814, 363], "label": "banana"}]
*   [{"point": [727, 470], "label": "red grapes"}]
*   [{"point": [675, 608], "label": "green grapes"}]
*   [{"point": [706, 529], "label": "blue lunch box"}]
*   [{"point": [864, 517], "label": "blue spoon"}]
*   [{"point": [499, 401], "label": "blue snack bar"}]
*   [{"point": [614, 705], "label": "brown snack bar"}]
*   [{"point": [448, 501], "label": "brown lunch bag"}]

後續步驟

代理能力：執行程式碼、讀取儀器、標註圖片。
工作調度：使用自訂機器人 API 執行長期工作。
串流機器人：即時雙向串流 (僅限 Gemini Robotics ER 2)。
影片理解：尋找特定時刻和進度分類 (僅限 Gemini Robotics ER 2)。