
Gravity: HUSKYLENS with Devastator Tank Mobile Robot Platform and Romeo V2
- Delivery nationwide via The Courier Guy — R150 flat, free over R2,000
- Free collection from our Milnerton (Cape Town) warehouse
- Secure checkout — PayFast card payment or EFT
- Questions? WhatsApp us on +27 65 900 8570
Description
This complete robotics kit combines the AI-powered HuskyLens vision sensor, the rugged Devastator Tank mobile platform, and the Romeo V2 Arduino Leonardo controller with built-in motor drivers. It is an ideal development platform for students, makers, and educators building autonomous, vision-guided tracked robots without coding complex machine learning algorithms from scratch.
Six built-in vision algorithms
HuskyLens comes pre-programmed with face recognition, object tracking, object recognition, line tracking, colour recognition, and tag detection. Users can switch between vision modes instantly using onboard hardware controls.

Multi-platform controller communication
The sensor communicates over UART or I2C to interface seamlessly with controllers such as Arduino, micro:bit, Raspberry Pi, and LattePanda. The included Romeo V2 board easily receives sensor telemetry to control the tank platform's dual motors.

Onboard display and calibration
A built-in 2.0-inch IPS screen with a 320x240 resolution provides real-time visual feedback and simplifies parameter tuning without requiring a computer. Dedicated hardware buttons allow you to trigger new object training cycles directly on the device.

Continuous multi-angle learning
HuskyLens uses integrated machine learning algorithms to record and remember target objects. By holding the learning button, the sensor continuously captures training data across various angles and distances to improve recognition accuracy.

Kendryte K210 neural processor
Powered by the specialised Kendryte K210 AI chip, HuskyLens runs neural network algorithms 1,000 times faster than an STM32H743 MCU. Paired with a 2.0-megapixel OV2640 camera, it quickly detects and tracks fast-moving objects in dynamic environments.

Interactive gesture tracking
The sensor's object-tracking capabilities can learn specific hand movements and output their real-time positional data. This enables the Devastator platform to respond directly to interactive hand gesture commands and spatial triggers.

Push-button line tracking
Line following requires no manual algorithm configuration or tedious parameter adjustments. Pressing the learning button trains HuskyLens on the target line, allowing the Devastator tank to track paths autonomously.

Video
Downloads & documentation
Specifications
| Processor | Kendryte K210 |
| Image Sensor | OV2640 (2.0Megapixel Camera) |
| Supply Voltage | 3.3~5.0V |
| Current Consumption (TYP) | [email protected] , [email protected] (face recognition mode; 80% backlight brightness; fill light off) |
| Connection Interface | UART, I2C |
| Display | 2.0-inch IPS screen with 320*240 resolution |
| Built-in Algorithms | Face Recognition, Object Tracking, Object Recognition, Line Tracking, Color Recognition, Tag Recognition |
| Dimension | 52mm * 44.5mm / 2.05 x 1.75inch |
In the box
| HuskyLens Mainboard | 1 |
| Devastator Tank Mobile Robot Platform | 1 |
| Romeo V2- an Arduino Robot Board (Arduino Leonardo) with Motor Driver | 1 |
| M3 Screws | 6 |
| M3 Nuts | 6 |
| Small Mounting Bracket | 1 |
| Heightening Bracket | 1 |
| Gravity 4-Pin Sensor Cable | 1 |
Reviews
No reviews yet — be the first to review this product.
From the same brand

Gravity: 4Pin I2C/UART Sensor Cable (10PCS)

Gravity: Analog CH4 Gas Sensor (MQ4) For Arduino

Gravity: Analog Gas Sensor (MQ2)

3xAAA Battery Holder
You might like

Replacement Motor Kit for Maqueen V5 STEM Robot

micro: Maqueen Lite - micro:bit Educational Programming Robot Platform

Pro'sKit AI Probbie Robot 2 micro:bit Kit (GE-894)
