Robotic arms can be expensive especially if you want one with AI Vision support, but Yahboom DOFBOT robotic arm designed for NVIDIA Jetson Nano offers a lower cost alternative as the 6 DoF robot arm sells for about $289 with a VGA camera, or $481 with the Jetson Nano SBC included.
We previously published a review of the myCobot 280 Pi robotic arm from Elephant Robotics, and while it’s working well, supports computer vision through the Raspberry Pi, and is nicely packaged, it sells for around $800 and up depending on the accessories, and one reader complained the “price tag is still way too high for exploration“. The DOFBOT robotic arm is looking more like a DIY build, but its price may make it more suitable for education and hobbyists.
DOFBOT robotic arm main components and specifications:
- SBC – NVIDIA Jetson Nano B01 developer kit recommended, but Raspberry Pi, Arduino, BBC Micro:bit boards are also listed as compatible.
- Storage – MicroSD card preload with firmware image (for Jetson Nano)
- Structural design
- Aluminum alloy brackets with 2mm thickness.
- Suction cups to secure the robotic arm on the desk
- 6-DOF vision robotic arm: 5 DoF plus gripper
- 5x 15kg servos and 1x 6Kg servo.
- Payload – Up to 200 grams when the arm is straight, up to 500 grams for “clamping handling weight” (note sure how to write that in proper English, I guess it’s when the arm is retracted)
- Arm span – 350 mm
- Diameter of grabbed object – 1 to 6 cm
- “Effective crawl range” – Radius less than 30cm (not sure what that means…)
- Repeatability – +/- 0.5mm (obviously not an industrial-gade robot arm)
- Camera – Wide-angle 0.3MP camera @ 30 fps with manual focus adjustment
- Connectivity and expansion
- PS2 game controller receiver
- WiFi/Bluetooth module
- 2x I2C interfaces
- Buttons – Emergency stop, Network, Reset
- 5V fan header
- RGB LED
- OLED display
- Power Supply – 12V/5A
- Dimensions – 303 x 135 x 473 mm (when assembled)
- Weight – 1,256 grams
The robotic arm comes with an expansion board that supports the NVIDIA Jetson Nano, but also Arduino UNO, STM32, and STC microcontroller boards, and the Raspberry Pi SBC. The accessories included in the kit are the fully assembled DOFBOT robot arm, an optional Jetson Nano B01 board, a map, a cooling fan, a user manual, a USB game controller, a power adapter, the robot arm expansion board shown above, a USB camera, an OLED display, a wireless module, some suction cups, a USB drive with the system image, and some fixtures and cables to connect everything together.
With cheaper hardware, companies will typically provide workable hardware with some basic demos and source code, basically leaving the users on their own to figure out more complex scenarios. But Yahboom provides a system image with Ubuntu 18.04 with ROS Melodic for the Jetson Nano, a mobile app available for Android and iOS to control the robot, and various tutorials which you can find on their website. They also shared the tutorials and a soft copy of the user manual (20 JPEG files! Why?) on GitHub.
The company provides AI features through the OpenCV library, and offers Jupyter Lab as a web-based interactive development environment, and more advanced users can also use Python 3 for programming. The DOFBOT robotic arm supports gesture recognition, color interaction, visual positioning, garbage sorting, catch game, face tracking, and other computer vision algorithms as shown in the video below.
Besides getting from the Aliexpress store linked in the introduction, it’s also possible to purchase the DOFBOT on Amazon or directly from the Yahboom store, but the price is higher starting at around $380.
Jean-Luc started CNX Software in 2010 as a part-time endeavor, before quitting his job as a software engineering manager, and starting to write daily news, and reviews full time later in 2011.