Bangle.js is an Hackable, Open Source JavaScript and TensorFlow-driven Smartwatch (Crowdfunding)
Espruino brought JavasScript to the Microcontroller, now Bangle.js is bringing Javascript plus TensorFlow Lite to your smartwatch. There has been some movement by some developers that says that JavaScript should be used for everything, even though I find that idea ridiculous, I still find JavaScript a fascinating language.
Bangle.js is the first hackable open source JS and TensorFlow-driven smartwatch.
The NeaForm Research team and Gordon Williams (the brain behind Espruino) have all teamed up in launching Bangle.js Smartwatch. Bangle.js isn’t your ordinary smartwatch, at the heart of it is the open-source ecosystem. JavaScript plus TensorFlow Lite and of course, a cool looking Smartwatch is what Bangle.js is offering.
Bangle.js was launched at the recently concluded NodeConf EU conference, and the goal is to bootstrap an Open Health Platform hopefully. NodeWatch is the specific implementation of Bangle.js for NodeConf EU 2019, co-developed by Espruino and NearForm Research.
This project 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.
The Evolution of Bangle.js – Espruino conference badges of 2017, 2018 and 2019 at NodeConf EU 2019.
At the core of Bangle.js is the Nordic Semi Nordic Semiconductor NRF52832 SoC using the Bluetooth LE 4.2 Technology and a 32mbit flash. The device also comes with a KX023 accelerometer, a single 3 axis compass, BD 1668 heart rate monitor, a Holtek touch controller (bs83a02a with 2 zones on/off). The display is made up of 240×240 Colour LCD, GPS is included using the U-box UBX-M8130 (supports GPS, Galileo, GLONASS, BeiDou), three buttons, and a buzzer for notification possibilities.
Specs:
IP68 Waterproof: up to 10m underwater
Nordic 64MHz nRF52832 ARM Cortex-M4 processor with Bluetooth LE
64kB RAM 512kB on-chip flash, 4MB external flash
1.3 inch 240×240 16 bit LCD 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
The team has demonstrated the machine learning capability of the device with the gesture control demonstration at the NodeConf EU. The gesture recognition is based on TensorFlow and HID to control presentation slides.
The buttons on the app can re-programmed for other applications like controlling your RC Car, flying your drone, controlling electrical applications, and maybe starting your car. Bangle.js is fully hackable, and the applications are limited to your own imagination, and with TensorFlow, AI is just next door. Bangle.js uses the Open Source (MPLv2) Espruino JavaScript interpreter. All source code, tools, and documentation are provided under an Open Source license.
Bangle.js comes with an App Loader to upload JavaScript apps to the device and uses Web Bluetooth to transfer the apps.
Bangle.js is now running a Kickstarter campaign, which, as at this point in writing, has exceeded its target goal. With a pledge of £47 plus £10 for shipping (~$61 + $13), you can get one Bangle.js watch. Delivery is expected around March 2020.
More information about Bangle.js is available on the announcement post.
I enjoy writing about the latest news in the areas of embedded systems with a special focus on AI on edge, fog computing, and IoT. When not writing, I am working on some cool embedded projects or data science projects. Got a tip, freebies, launch, idea, gig, bear, hackathon (I love those), or leak? Contact me.
I’m not sure if javascript is a bad choice here.
Note that javascript != node.js or so.
Basically it is an interpreted language,
I don’t know exactly how they implemented it in the phone, but if you e.g. translate upfront to some byte code it may be pretty efficient wrt storage usage. (the older ones among you may still remember things like P-code and Forth).
They seem to have some apps already (https://banglejs.com/apps/) Not sure how good they are and how many will fit on a phone though.
About three times the price of the PineTime for rather similar specs, so I guess I’ll end up choosing the latter… which additionally will have way more storage (8 or 16MB), and hopefully the better SoC (nRF52840). On the other side, in all fairness, there’s things the Bangle.js has and the PineTime hasn’t, like the GPS, magnetometer and speaker and the better waterproof rating (IP68 vs IP67). All of which are more or less “nice to have” features, but not something that would tip the balance the other way or make up for the price diff imho.
Well yeah in the sense that on the manufacturer side the price of the additional GPS does explain a good part of the higher price. Doesn’t change the fact that it’s at best “nice to have” and not something that would make me (on the consumer side) want to pay that much more for it. When I’m outside in a situation where I want GPS, I have a GPS-capable smartphone with me anyways. The added value of a smartwatch (at least for my use cases) is totally independent of a having a second (redundant) GPS receiver.
It greatly depends on your use case.
A GPS watch is convenient if you want to track you cycling or running trip.
Of course a smartphone can also do this job, but when I go cycling (ATB), I’d rather travel light and leave my phone at home. Less weight and no risk for damage.
It is probably also easier to correlate heartbeat data with location (although like most watches, heartbeat measurement is probably not that reliable).
yeah well i suppose it depends on personal preferences indeed. It would not come into my mind to go biking without a phone. Especially not ATB. If there’s any accident, problem, whatever, I wouldn’t want to be out there without a phone to call for help. Not gonna risk my security just to protect a phone. And there are lots of ultra-cheap, lightweight, well-protected phone bags/pouch options (for arm, belt, bike, etc). But yeah, to each their own priorities, use cases and preferences i guess.
Javascript on a smart watch? Hell no! ^^ And Tensorflow? What is wrong with these people?
Well… JavaScript for Everything.
I’m not sure if javascript is a bad choice here.
Note that javascript != node.js or so.
Basically it is an interpreted language,
I don’t know exactly how they implemented it in the phone, but if you e.g. translate upfront to some byte code it may be pretty efficient wrt storage usage. (the older ones among you may still remember things like P-code and Forth).
They seem to have some apps already (https://banglejs.com/apps/) Not sure how good they are and how many will fit on a phone though.
About three times the price of the PineTime for rather similar specs, so I guess I’ll end up choosing the latter… which additionally will have way more storage (8 or 16MB), and hopefully the better SoC (nRF52840). On the other side, in all fairness, there’s things the Bangle.js has and the PineTime hasn’t, like the GPS, magnetometer and speaker and the better waterproof rating (IP68 vs IP67). All of which are more or less “nice to have” features, but not something that would tip the balance the other way or make up for the price diff imho.
I think the GPS on its own carries a punch in price already.
Well yeah in the sense that on the manufacturer side the price of the additional GPS does explain a good part of the higher price. Doesn’t change the fact that it’s at best “nice to have” and not something that would make me (on the consumer side) want to pay that much more for it. When I’m outside in a situation where I want GPS, I have a GPS-capable smartphone with me anyways. The added value of a smartwatch (at least for my use cases) is totally independent of a having a second (redundant) GPS receiver.
It greatly depends on your use case.
A GPS watch is convenient if you want to track you cycling or running trip.
Of course a smartphone can also do this job, but when I go cycling (ATB), I’d rather travel light and leave my phone at home. Less weight and no risk for damage.
It is probably also easier to correlate heartbeat data with location (although like most watches, heartbeat measurement is probably not that reliable).
yeah well i suppose it depends on personal preferences indeed. It would not come into my mind to go biking without a phone. Especially not ATB. If there’s any accident, problem, whatever, I wouldn’t want to be out there without a phone to call for help. Not gonna risk my security just to protect a phone. And there are lots of ultra-cheap, lightweight, well-protected phone bags/pouch options (for arm, belt, bike, etc). But yeah, to each their own priorities, use cases and preferences i guess.