Model Gemini Robotics ER dapat menunjuk objek, melacaknya dalam video, mendeteksinya dengan kotak pembatas, dan membuat lintasan gerakan.
Untuk kode yang dapat dijalankan sepenuhnya, lihat Robotics cookbook.
Arahkan ke objek
Contoh berikut menemukan objek tertentu dalam gambar dan menampilkan koordinat [y, x] yang dinormalisasi:
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"
}
}
}'
Outputnya akan berupa array JSON yang berisi objek, yang masing-masing memiliki point
(koordinat [y, x] yang dinormalisasi) dan label yang mengidentifikasi objek.
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"}
]
Gambar berikut adalah contoh cara titik-titik ini dapat ditampilkan:
Melacak objek dalam video
Gemini Robotics ER 2 juga dapat menganalisis frame video untuk melacak objek dari waktu ke waktu. Lihat Input video untuk mengetahui daftar format video yang didukung.
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)
Deteksi objek dan kotak pembatas
Selain titik, Anda dapat meminta model untuk menampilkan kotak pembatas 2D, yang memberikan detail spasial lebih banyak untuk objek yang terdeteksi.
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)
Lintasan
Gemini Robotics ER 2 dapat membuat urutan titik yang menentukan lintasan, yang berguna untuk memandu pergerakan robot.
Contoh ini meminta lintasan untuk memindahkan pena merah ke pengatur, termasuk perkiraan titik jalan perantara. Kode telah dikurangi untuk menampilkan hanya perintah.
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.
"""
Menyediakan ruang untuk laptop
Contoh ini menunjukkan cara Gemini Robotics ER dapat memahami ruang. Perintah meminta model untuk mengidentifikasi objek mana yang perlu dipindahkan untuk membuat ruang bagi item lain.
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)
Respons berisi koordinat 2D objek yang menjawab pertanyaan pengguna, dalam hal ini, objek yang harus dipindahkan untuk memberi ruang bagi laptop.
[
{"point": [672, 301], "label": "The object that I need to remove to make room for my laptop"}
]
Mengepak bekal makan siang
Model ini juga dapat memberikan petunjuk untuk tugas multi-langkah dan menunjukkan objek yang relevan untuk setiap langkah. Contoh ini menunjukkan cara model merencanakan serangkaian langkah untuk mengemas tas bekal.
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)
Respons terhadap perintah ini adalah serangkaian petunjuk langkah demi langkah tentang cara mengemas tas makan siang dari input gambar.
Gambar input

Output model
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"}]
Langkah berikutnya
- Kemampuan seperti agen — eksekusi kode, pembacaan instrumen, anotasi gambar.
- Orkestrasi tugas — tugas dengan cakupan panjang menggunakan API robot kustom.
- Robotika dengan streaming — streaming dua arah real-time (khusus Gemini Robotics ER 2).
- Pemahaman video — penemuan momen dan klasifikasi progres (khusus Gemini Robotics ER 2).