Robot arms

ArmPi Ultra

A Raspberry Pi 5 robot arm for ROS2 teaching, with 3D depth vision and ChatGPT voice control as kit options.

Raspberry Pi
Suggested for secondary
Suggested for university

ArmPi Ultra is a desktop robot arm that Hiwonder built for ROS teaching. Six high-torque smart bus servos move the arm, and a Raspberry Pi 5 works with an STM32 controller: the Pi handles vision and decisions, the STM32 drives the servos. The Standard and Advanced kits carry a 3D depth camera that lets the arm recognise, track and pick up objects in three dimensions; the Starter Kit uses a monocular camera. The Advanced Kit adds the WonderEcho Pro AI voice box, which connects the arm to ChatGPT and vision language models. It runs ROS2, and Hiwonder supplies tutorials, source code and system images.

Zeta42 is an authorised Hiwonder partner in the Middle East.

Configurations

Choose how it ships.

Model: ArmPi Ultra Starter Kit · ArmPi Ultra Standard Kit · ArmPi Ultra Advanced Kit
Controller: Without Raspberry Pi 5 · With Raspberry Pi 5 2GB · With Raspberry Pi 5 4GB · With Raspberry Pi 5 8GB · With Raspberry Pi 5 16GB

What it does

Built for.

3D vision and grasping
With the depth camera, ArmPi Ultra fuses colour and depth (RGB+D) to recognise and track objects and pick them up in a 3D scene.
Two controllers
The Raspberry Pi 5 takes care of vision and decision-making while the STM32 controller handles precise servo control, which keeps the arm responsive.
Voice and large AI models
In the Advanced Kit, the WonderEcho Pro voice box and ChatGPT let the arm act on spoken commands: sorting by colour or shape, sorting waste, describing a scene, tracking an object or moving it to a named place.
Object detection you can retrain
YOLO26 runs real-time detection of several objects at once, and students can train models on their own objects. The kit includes waste-pattern blocks for sorting practice.
Metal arm on a bearing base
The arm is anodised aluminium throughout, and its base uses industrial-grade bearings for demanding grabbing work.
Simulate first
ArmPi Ultra is developed on ROS and supports Gazebo, so control and algorithms can be checked in a virtual environment before they run on the arm.

Where it is used

Applications.

Secondary and university robotics courses built on ROS2
Machine vision and object detection projects
Embodied AI exercises driven by voice commands (Advanced Kit)
Sorting tasks by colour, shape or waste category

Videos

See it run.

Specifications

The full sheet.

Size: 288 × 177 × 450 mm
Weight: 1.47kg (Standard kit)
Controllers: Raspberry Pi 5 + STM32F103RBT6
Material: Full metal aluminum alloy bracket, sandblasted and anodized finish
Control methods: ROS topic/node control, Python program control, app control, PC software control
Power supply: 7.4V 6A DC
Storage: 64GB SD card
Software: PC software + iOS / Android app
Communication: USB 2.0 ×2; USB 3.0 ×2; serial port
Camera: USB monocular camera (Starter Kit) / Aurora depth camera (Standard and Advanced Kit)
Depth camera: Aurora930 Pro (Standard and Advanced Kit)
Depth camera working distance: 15-300 cm
Depth accuracy: ±8mm @1m
Depth resolution / frame rate: 640×400 @12fps (FOV: 74°×51°)
OS: RaspberryOS + Ubuntu 22.04 LTS (Docker)
Programming tools: Python / C / C++ / JavaScript
Servo models: HTS-16L, HTS-25L, HX-06L, LX-15D, LX-225 intelligent bus servos
Tutorials: User manual, comprehensive tutorial, ROS source code, STM32 source code, system images, software
Package weight and size: 3.2kg, 50 × 30 × 16 cm