Next robot →

Yahboom Roboduino V2 AI Vision Car

Yahboom (China) · 2024

$99.99Amazon US $99.99 and Yahboom store $110.00 (October 2026). Yahboom UNO R3 board, expansion board and ESP32-S3 Wi-Fi camera module included. The Amazon listing says one lithium battery is included, and the Yahboom tutorial covers the supplied lithium pack and charger (charger inclusion unconfirmed). Year taken from the GitHub repo creation and store listing dates (June 2024).
AvailableVia SSH / web / bridgeArduinoESP32CameraWi-FiMecanum wheelsKit build
Weeks+Shipping: About 2–3 weeks (Amazon, shipped by Yahboom). Sold and shipped by Yahboom on Amazon US, in stock with free delivery quoted for October 14–23 in October 2026. Also sold on the Yahboom web store. Amazon ↗
Remote control: Sketches upload to the UNO over USB (the camera must be unplugged since it shares the serial port). The camera joins a home network or makes its own hotspot (192.168.4.1), and per Yahboom's camera docs it can publish images to a laptop running a ROS2 micro-ROS agent. A documented HTTP/MJPEG stream for a plain laptop script is unconfirmed.

Overview

A metal mecanum-wheel car built on an Arduino UNO with an ESP32-S3 Wi-Fi camera that streams video to a phone app and runs small vision models on board. It suits beginners who want Arduino C++ plus a camera car without buying a Raspberry Pi, and it is one of the few kits under $150 whose camera can flag a cat by itself. Yahboom's cat(dog) detection lesson only beeps and lights the RGB LED, and the model cannot tell cats from dogs, so turning detections into following would need extra work (color and face following lessons exist as starting points). Programming is Arduino IDE only, with no block coding or MicroPython on the car.

Specifications

CategoryWheeled rovers · Classroom coding cars
Released2024
CountryChina
AvailabilityAvailable
ProgrammabilityFull SDK
Built-in autonomyReactive · Responds to its surroundings without a map, such as avoiding obstacles or following a person
LLM supportPossible via SDK · Open Arduino code and a simple serial command format ($...# strings forwarded from the Wi-Fi camera to the UNO) give an LLM something to drive, but Yahboom supplies no LLM lessons for this kit.
MuJoCo simulationNone found · Nothing found.
NVIDIA Isaac simulationNone found · Nothing found.
Gazebo simulationNone found · Nothing found.
Best forAges 10+ (maker rating)
Vision sensorsCamera, Sonar / ultrasonic
ActuatorsDC / gear motors
AudioSpeaker
Compute typeArduino / ESP32 / microcontroller
Remote controlVia SSH / web / bridge
SizeNot published
Drive4WD mecanum (omnidirectional) with 4 independently driven DC gear motors and 60 mm mecanum wheels (motor gearing not stated)
ComputeYahboom UNO R3 (Arduino UNO compatible, ATmega328P) on the Roboduino expansion board, whose STC8G co-processor drives the motors over I2C, plus an ESP32-S3 in the camera module that runs the vision models
VisionYahboom ESP32-S3 WiFi camera module with a 2 MP (200W) camera on an app-adjustable PTZ mount (sensor model not stated). On-board modes include cat/dog detection, person detection, face detection and recognition, color recognition and QR codes.
LidarNone
SensorsUltrasonic module, 3-channel line tracking module, IR receiver with remote, key, RGB LED, buzzer
RuntimeLithium battery pack included per Amazon (stored at 7.0 to 7.8 V per Yahboom, so likely 2S, capacity unconfirmed), runtime not published
SpeedNot published
SDKArduino IDE (C/C++) sketches, YahboomCAM app for iOS and Android, IR remote. The camera module also has ROS2 (micro-ROS over UDP) and OpenCV/MediaPipe PC lessons in Yahboom's WiFi camera docs.

Ratings & reviews

Compared side by side

Similar robots

Image credits