Difference between revisions of "JetBot AI Kit"
Line 73: | Line 73: | ||
In this example we'll collect an image classification dataset that will be used to help keep JetBot safe! We'll teach JetBot to detect two scenarios free and blocked. We'll use this AI classifier to prevent JetBot from entering dangerous territory. | In this example we'll collect an image classification dataset that will be used to help keep JetBot safe! We'll teach JetBot to detect two scenarios free and blocked. We'll use this AI classifier to prevent JetBot from entering dangerous territory. | ||
;Step 1. Collect data on JetBot | ;Step 1. Collect data on JetBot | ||
− | *Access JetBot by going to <font style="background-color#EEEEEE" color=#B94A48><nowiki>https://<jetbot_ip_address>:8888</nowiki></font>, navigate to ~/Notebooks/collision_avoidance/ | + | *Access JetBot by going to <font style="background-color:#EEEEEE" color=#B94A48><nowiki>https://<jetbot_ip_address>:8888</nowiki></font>, navigate to ~/Notebooks/collision_avoidance/ |
*Open data_collection.ipynb file and following notebook | *Open data_collection.ipynb file and following notebook | ||
*This model was trained on a limited dataset using the IMX219-160 Camera with wide angle attachment. | *This model was trained on a limited dataset using the IMX219-160 Camera with wide angle attachment. | ||
Line 79: | Line 79: | ||
:[[File:JetBot_AI_Kit_Manual_13.jpg|600px]] | :[[File:JetBot_AI_Kit_Manual_13.jpg|600px]] | ||
;Step 2. Train neural network | ;Step 2. Train neural network | ||
− | *Access JetBot by going to <font style="background-color#EEEEEE" color=#B94A48><nowiki>https://<jetbot_ip_address>:8888</nowiki></font>, navigate to ~/Notebooks/collision_avoidance/ | + | *Access JetBot by going to <font style="background-color:#EEEEEE" color=#B94A48><nowiki>https://<jetbot_ip_address>:8888</nowiki></font>, navigate to ~/Notebooks/collision_avoidance/ |
*Open and follow the tain_model.ipynb notebook | *Open and follow the tain_model.ipynb notebook | ||
;Step 3. Run live demo on JetBot | ;Step 3. Run live demo on JetBot | ||
− | *Access JetBot by going to <font style="background-color#EEEEEE" color=#B94A48><nowiki>https://<jetbot_ip_address>:8888</nowiki></font>, navigate to ~/Notebooks/collision_avoidance/ | + | *Access JetBot by going to <font style="background-color:#EEEEEE" color=#B94A48><nowiki>https://<jetbot_ip_address>:8888</nowiki></font>, navigate to ~/Notebooks/collision_avoidance/ |
*Open and following the live_demo.ipynb notebook | *Open and following the live_demo.ipynb notebook | ||
+ | |||
===5. Object following=== | ===5. Object following=== | ||
Here we use [http://cocodataset.org/#home coco dataset] | Here we use [http://cocodataset.org/#home coco dataset] | ||
==Supports== | ==Supports== | ||
{{Service00}} | {{Service00}} |
Revision as of 07:53, 19 July 2019
| ||
Instruction
This is a AI Robot kit based on Jetson Nano Developer Kit. Supports facial recognition, object tracking, auto line following or collision advancing and so on.
User Guides
1. Install Image
【Note】 The software part of this guide mostly based on NVIDIA jetbot wiki , you can also directly refer to it
- Step 1. Write JetBot image to SD card
- You need to prepare a SD card which should be at least 64G
- Download JetBot image which is provided by NVIDIA and unzip it. Click here to download it
- Connect the SD card to PC via card reader
- User Etcher software to write image (unzip above) to SD card.Click here to download Etcher software
- After writting, eject the SD card
- Step 2. Start up Jetson Nano Developer Kit
- Insert SD card to SD card slot of Jetson nano (slot is under Jetson Nano board)
- Connect HDMI display (if you don't have HDMI or DP display and want to buy one, recommend our HDMI display), keyboard and Mouse to Jetson Nano Developer Kit
【Note】You had better test the Jetson Nano Developer Kit before you assemble JetBot
- Step 3. Connect Jetbot to WIFI
All the examples use WIFI, we need to connect JetBot to WIFI firstly.
- Start Jetson nano Developer Kit, default user name and password of Jetbot are both jetbot
- Click Network icon on top-right of Desktop and connect WIFI
- Power off. Then assemble Jetbot
- Start Jetson nano again. After booting, Ubuntu will auto-connect WIFI, IP address is also displayed on OLED
- Step 4. Access JetBot via Web
- After networking. You can remove peripherals and power adapter.
- Turn Power switch of Jetbot into On
- After booting, IP address of OLED can be displayed on OLED
- Navigate to http://<jetbot_ip_address>:8888 from your desktop's web browser
- Step 5. Install latest software (optional)
The JetBot GitHub repository may contain software that is newer than that pre-installed on the SD card image. To install the latest software:
- Access Jetbot by going to http://<jetbot_ip_address>:8888
- Launch a new terminal. Default user name and password are both jetbot
- Get and install the latest JetBot repository from GitHub.The repository provided here is modified by Waveshare, supports displaying current voltage of batteries. If you want to install original codes, please following NVIDIA jetbot GitHub.
git clone https://github.com/waveshare/jetbot cd jetbot sudo python3 setup.py install
- Step 6. Configure power mode
To ensure that the Jetson Nano doesn't draw more current than the battery pack can supply, place the Jetson Nano in 5W mode by calling the following command
- You need to launch a new Terminal and enter following commands to select 5W power mode
sudo nvpmodel -m1
- Check if mode is correct
sudo nvpmodel -q
【Note】m1: 5W power mode, m2: 10W power model
2. Basic motion
- Access jetbot by going to http://<jetbot_ip_address>:8888, navigate to ~/Notebooks/basic_motion/
- Open basic_motion.ipynb file and following the notebook
【Note】You can click icon ▶ to run codes, or select Run -> Run Select Cells. Make sure the JetBot has engough space to run.
3. Teleoperations
- Access JetBot by going to https://<jetbot_ip_address>:8888, navigate to ~/Notebooks/teleoperation/
- Open teleoperation.ipynb file and following notebook
- Connect USB adapter to PC
- Go to https://html5gamepad.com, check the INDEX of Gamepad
- Modify the index. Run and test Gamepad
- Modify axes values if require, here we use axes[0] and axes[1]
- For more details, please refer to notebook
4. Collision_avoidance
In this example we'll collect an image classification dataset that will be used to help keep JetBot safe! We'll teach JetBot to detect two scenarios free and blocked. We'll use this AI classifier to prevent JetBot from entering dangerous territory.
- Step 1. Collect data on JetBot
- Access JetBot by going to https://<jetbot_ip_address>:8888, navigate to ~/Notebooks/collision_avoidance/
- Open data_collection.ipynb file and following notebook
- This model was trained on a limited dataset using the IMX219-160 Camera with wide angle attachment.
- You need to put the JetBot to different spaces for collecting data as more as possible
- Access JetBot by going to https://<jetbot_ip_address>:8888, navigate to ~/Notebooks/collision_avoidance/
- Open and follow the tain_model.ipynb notebook
- Step 3. Run live demo on JetBot
- Access JetBot by going to https://<jetbot_ip_address>:8888, navigate to ~/Notebooks/collision_avoidance/
- Open and following the live_demo.ipynb notebook
5. Object following
Here we use coco dataset
Supports
Support
If you require technical support, please go to the Support page and open a ticket.