
Robot arms
ArmPi mini
A compact Raspberry Pi robot arm for beginners, with a wide-angle camera, OpenCV vision and Python.
- Raspberry Pi
- Suggested for secondary
- Suggested for university
ArmPi mini is a compact robot arm for learning AI vision and machine learning on a Raspberry Pi 5 or 4B. A 170° wide-angle HD camera and OpenCV image processing let it recognise colours, sort them, track targets and stack blocks, and inverse kinematics turns a target's position into precise grasping. The arm has four degrees of freedom plus a duralumin gripper, driven by a full-metal high-torque servo at the base and an anti-blocking micro servo at the end. It runs on two 18650 batteries for about 60 minutes and is programmed in Python. Kits come with or without a Raspberry Pi; kits without one do not include a microSD card.
Zeta42 is an authorised Hiwonder partner in the Middle East.
Configurations
Choose how it ships.
- Model
- Without Raspberry Pi 4B · With Raspberry Pi 4B (4GB) · Without Raspberry Pi 5 · With Raspberry Pi 5 (2GB) · With Raspberry Pi 5 (4GB) · With Raspberry Pi 5 (8GB)
What it does
Built for.
Vision with OpenCV
The 170° wide-angle camera and OpenCV handle colour recognition, colour sorting, target tracking and intelligent palletising.
Inverse kinematics
ArmPi mini recognises a target's colour, works out its coordinates, then uses inverse kinematics to track, grip and sort it accurately.
Metal arm, mixed servos
The bracket is lightweight, high-strength aluminium alloy. A full-metal high-torque servo with a metal horn drives the base, and an anti-blocking micro servo works the duralumin gripper.
Raspberry Pi 5 or 4B
The arm runs on a Raspberry Pi 5 or 4B with an expansion board, for motion control, machine vision and OpenCV projects in Python. Kits come with a Pi 4B (4GB), with a Pi 5 (2GB, 4GB or 8GB), or without a board.
App and PC control
Control it from the iOS and Android app or from PC software on a computer. It connects over Wi-Fi or Ethernet.
Room to play
Hiwonder's examples go beyond sorting, to stacking blocks and picking up dolls.
Where it is used
Applications.
- A first robot arm course in Python and OpenCV
- Colour recognition, sorting and palletising exercises
- Teaching inverse kinematics on a small desktop arm
- Prototyping and STEAM projects
Videos
See it run.
Specifications
The full sheet.
- Size
- 208 × 134 × 309 mm
- Weight
- 0.7kg
- Material
- Metal bracket
- Camera
- HD 170° wide-angle, 480P
- DOF of robotic arm
- 4DOF + gripper
- Power
- 2 × 18650 LiPo battery (1800mAh)
- Continuous working time
- About 60 min
- Hardware
- Raspberry Pi 4B/5 and Raspberry Pi expansion board
- Software
- iOS / Android app
- Communication method
- WiFi, Ethernet
- Servo
- LDX-218 / LD-1501MG digital servo and LFD-01M micro servo
- Control method
- Computer / phone control
- Package size
- 33 × 20 × 10 cm
- Package weight
- About 1.1kg
Specifications as published by Hiwonder.
Request a quote
Quote for ArmPi mini.
Quantity, configuration, delivery and setup: we quote each order on its own terms.
Levels are our recommendation, not Hiwonder's. Ask us if you are unsure which fits.
More from Hiwonder
Robot arms.

AiArm
An ESP32 vision robot arm coded in Scratch or Python, with an optional sorting-scene kit.
- ESP32

ArmPi FPV
An open-source 6DOF robot arm on Raspberry Pi, with a camera on the arm, ROS and Python.
- Raspberry Pi

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

JetArm
A desktop robot arm on NVIDIA Jetson for teaching ROS, 3D vision and embodied AI.
- NVIDIA Jetson

JetArm Pro
The JetArm 3D vision arm with an add-on: a mecanum or tank chassis, a sliding rail or a conveyor belt.
- NVIDIA Jetson

JetMax
A Jetson Nano robot arm with an end camera, ROS and deep learning; Standard and Advanced kits add end tools.
- NVIDIA Jetson