Bangle.js: The Hackable Smartwatch Powered By Google’s TensorFlow

NearForm Research and Espruino have jointly developed the first open-source JavaScript (JS) hackable smartwatch, which was recently showcased to the attendees of the NodeConf 2019.

The new concept smartwatch called as “Bangle.js” runs the software developed by Espruino and is powered by Machine Learning (ML) via Google’s TensorFlow Lite. Bangle.js device can be easily customized and it allows developers to create their own AI (artificial intelligence) applications for the device.

It comes pre-loaded with features and apps including: heart rate monitor, 3 Axis Accelerometer, JavaScript interpreter, Pedometer, games, GPS, compass, maps, gesture-control of PC applications over Bluetooth and more.

“Bangle.js is not just about a single device, codebase or company. I believe it has the potential to bootstrap a community-driven open health platform where anyone can build or use any compatible device and everyone owns their own data. Machine Learning is a critical aspect of health technology and we’re so pleased to be further involved in the TensorFlow open source project,” said Conor O’Neill, chief product officer for NearForm.

The addition of Google’s TensorFlow Lite ML framework allowed the developers to run ML gesture detection algorithm, which enables the user to control applications, including PowerPoint, with hand gestures.

Further, even ‘lapsed’ and non-programmers can make changes to Bangle.js using Blockly or low-code Node-RED.

Check out the demonstration video below to know more about the Bangle.js smartwatch.

“You can easily install new apps from the web or develop your own using JavaScript or a graphical programming language (Blockly). All you need is a Web Browser (Chrome, Edge or Opera) and you can upload apps or write code to run on your watch wirelessly! Bangle.js is waterproof and AI enabled and comes with bluetooth low energy, GPS, a heart rate monitor, accelerometer and more.”

Specifications of the smartwatch include:

– IP68 Waterproof: up to 10m underwater
– 64MHz nRF52832 ARM Cortex-M4 processor with Bluetooth LE
– 64kB RAM 512kB on-chip flash, 4MB external flash
– Nordic 1.3 inch 240×240 16 bit LCD display with 2 zone touch
– GPS/Glonass receiver (UBlox)
– Heart rate monitor
– 3 Axis Accelerometer (with Pedometer and Tap detect)
– 3 Axis Magnetometer
– Piezo speaker and Vibration motor
– 350mAh battery, 1 week standby time
– 5 x 5 x 1.7 cm case, plastic with stainless steel ring
– Can be disassembled with just 4 screws

Software specifications for the smartwatch:

– Easy to code and debug wirelessly using JavaScript or our graphical editor (based on Blockly)
– Pre-programmed with the Espruino Open Source JavaScript interpreter
– Vast majority of JavaScript ES5 features and many ES6 features including: Regular Expressions, Promises, Arrow Functions, Template Literals
– 40kB RAM for program memory/variables
– Bluetooth 4.2 Advertising, Central and Peripheral mode support with built-in Nordic UART service
– Graphics library with Vector fonts, bimap rotate & scale
– Tensorflow Lite for Microcontrollers AI
– Wear-levelled flash filesystem
– Heatshrink compression
– Upload functions written in C or ARM Assembler
– Built-in wireless debugging
– VT100 Terminal support on LCD
– Program with Web-based Web Bluetooth IDE or Node.js-based command line tools

The Bangle.js project is currently fully funded on Kickstarter. The watches are expected to start shipping around the world in March 2020