5G Is For Robots

October 30, 2019 by Gerrit Coetzee 45 Comments

Ecclesiastes 1:9 reads “What has been will be again, what has done will be done again; there is nothing new under the sun.” Or in other words, 5G is mostly marketing nonsense; like 4G, 3G, and 2G was before it. Let’s not forget LTE, 4G LTE, Advance 4G, and Edge.

Just a normal everyday antenna array in a Seattle parking garage.

Technically, 5G means that providers could, if they wanted to, install some EHF antennas; the same kind we’ve been using forever to do point to point microwave internet in cities. These frequencies are too lazy to pass through a wall, so we’d have to install these antennas in a grid at ground level. The promised result is that we’ll all get slightly lower latency tiered internet connections that won’t live up to the hype at all. From a customer perspective, about the only thing it will do is let us hit the 8Gb ceiling twice as faster on our “unlimited” plans before they throttle us. It might be nice on a laptop, but it would be a historically ridiculous assumption that Verizon is going to let us tether devices to their shiny new network without charging us a million Yen for the privilege.

So, what’s the deal? From a practical standpoint we’ve already maxed out what a phone needs. For example, here’s a dirty secret of the phone world: you can’t tell the difference between 1080p and 720p video on a tiny screen. I know of more than one company where the 1080p on their app really means 640 or 720 displayed on the device and 1080p is recorded on the cloud somewhere for download. Not a single user has noticed or complained. Oh, maybe if you’re looking hard you can feel that one picture is sharper than the other, but past that what are you doing? Likewise, what’s the point of 60fps 8k video on a phone? Or even a laptop for that matter?

Are we really going to max out a mobile webpage? Since our device’s ability to present information exceeds our ability to process it, is there a theoretical maximum to the size of an app? Even if we had Gbit internet to every phone in the world, from a user standpoint it would be a marginal improvement at best. Unless you’re a professional mobile game player (is that a thing yet?) latency is meaningless to you. The buffer buffs the experience until it shines.

So why should we care about billion dollar corporations racing to have the best network for sending low resolution advertising gifs to our disctracto cubes? Because 5G is for robots.

Continue reading “5G Is For Robots” →

Wiping Your Windscreen To The Beat

October 24, 2019 by Danie Conradie 32 Comments

Nothing spoils your mood quite like your windscreen wipers not feeling it when the beat drops. Every major car manufacturer is focused on trying to build the electric self driving vehicle for the masses, yet ignoring this very real problem. Well [Ian Charnas] is taking charge, and has successfully slaved his car’s wipers to beat of its stereo.

Starting with the basics, [Ian] first needed to control the speed of the wiper motor. This was done using a custom power supply adapted from another project. The brain of the system is a Raspberry Pi 3B+ which runs a phase locked loop algorithm to sync the music and the motor. Detecting the beat turned out to be the most difficult part of the project, and from the research [Ian] did, there is no standard solution. He ended up settling on “madmom“, a Python audio and music signal processing library, which runs a neural net to detect the beat in real time. The Raspi sends the required PWM and Enable signals to an Arduino over serial, which in turn controls the power supply. The entire system was neatly integrated in the car, with a switch in the dash that connects the motor to the new power supply on demand, to allow the wipers to still be used normally (and safely).

[Ian] filed a provisional patent application for the idea, and will be putting it on auction on eBay soon, with the hope that some major car manufacturer would be interested. For older cars, you can shove an Arduino into the stereo, or do a super cheap bluetooth upgrade. Check out the video after the break. Continue reading “Wiping Your Windscreen To The Beat” →

Robot Allows Remote Colleagues To Enjoy Office Shenanigans

October 17, 2019 by Anool Mahidharia 3 Comments

[Esther Rietmann] and colleagues built a Telepresence Robot to allow work at home teammates to have a virtual, but physical presence in the office. A telepresence robot is like a tablet mounted on a Roomba, providing motion capability in addition to an audio/video connection. Built during a 48 hour hackathon, it is a bit crude under the hood and misses out on some features, such as a bidirectional video feed. But overall, it pretty much does what is expected from such a device.

The main structure is build from cheap aluminium profiles and sheets. A Raspberry Pi is at the heart of the electronics hardware, with a servo mounted Pi-camera and speaker-microphone pair taking care of video and audio. The two DC motors are driven by H-bridges controlled from the Pi and an idle swivel caster is attached as the third wheel. The whole thing is powered by a power bank. The one important thing missing is an HDMI display which can show a video feed from the remote laptop camera. That may have been due to time constraints, but this feature should not be too difficult to add as a future upgrade. It’s important for both sides to be able to see each other.

The software is built around WebRTC protocol, with the WebRTC Extension from UV4L doing most of the heavy lifting. The UV4L Streaming Server not only provides its own built-in set of web applications and services, but also embeds a general-purpose web server on another port, allowing the user to run and deploy their own custom web apps. This allowed [Esther Rietmann]’s team to build a basic but functional front-end to transmit data from the remote interface for controlling the robot. The remote computer runs a Python control script, running as a system service, to control the drive motors and camera servo.

The team also played with adding basic object, gesture and action recognition features. This was done using PoseNet – a machine learning model, which allows for real-time human pose estimation in the browser using TensorFlowJS – allowing them to demonstrate some pose detection capability. This could be useful as a “follow me” feature for the robot.

Another missing feature, which most other commercial telepresence robots have, is a sensor suite for collusion avoidance, object detection and awareness such as micro switches, IR / ultrasonic detectors, time of flight cameras or LiDAR’s. It would be relatively easy to add one or several sensors to the robot.

If you’d like to build one for yourself, check out their code repository on Github and the videos below.

Continue reading “Robot Allows Remote Colleagues To Enjoy Office Shenanigans” →

BeagleBone Deep Learning Video Demo

September 22, 2019 by Al Williams 10 Comments

BeagleBoard often gets eclipsed by Raspberry Pi. Where the Pi focuses on ease-of-use, the BeagleBone generally has more power for hardcore applications. With machine learning AI all the rage now, BeagleBoard now has the BeagleBone AI, a board with specific features aimed at machine learning. A recent video (see below) shows a demo of using TIDL (Texas Instruments Deep Learning Library). The video includes an example of streaming video to a browser and using predefined learning models to identify things picked up by a web camera.

The CPU onboard is the TI Sitara AM5729. That’s a dual Arm Cortex A15 running at 1.5 GHz. There are also two C66x floating-point DSP processors and two dual ARM Cortex M4 coprocessors. Still need more? You get four embedded vision engines, two dual-core real-time units, a 2D graphics accelerator, a 3D graphics accelerator, and a subsystem for encoding and decoding video and cryptography.

Continue reading “BeagleBone Deep Learning Video Demo” →

Name Stone Helps You Greet Coworkers

September 16, 2019 by Lewin Day 17 Comments

When starting a new job, learning coworkers names can be a daunting task. Getting this right is key to forming strong professional relationships. [Ahad] noted that [Marcos] was struggling with this, so built the Name Stone to help.

The Name Stone consists of some powerful hardware, wrapped up in a 3D printed case reminiscent of the Eye of Agamotto from Doctor Strange. Inside, there’s a Jetson Nano – an excellent platform for any project built around machine learning tasks. This is combined with a microphone and camera to collect data from the environment.

[Ahad] then went about training neural networks to help with basic identification tasks. Video was taken of the coworkers, then the frames used to train a convolutional neural network using PyTorch. Similarly, a series of audio clips were used to again train a network to identify individuals through the sound of their voice, using MFCC techniques. Upon activating the stone, the device will capture an image or a short sound clip, and process the data to identify the target coworker and remind [Marcos] of their name.

It’s a project that could be quite useful, given to new employees to help them transition into the new workplace. Of course, pervasive facial recognition technology does have some drawbacks. Video after the break.

Continue reading “Name Stone Helps You Greet Coworkers” →

Machine Learning With Microcontrollers Hack Chat

September 9, 2019 by Dan Maloney 4 Comments

Join us on Wednesday, September 11 at noon Pacific for the Machine Learning with Microcontrollers Hack Chat with Limor “Ladyada” Fried and Phillip Torrone from Adafruit!

We’ve gotten to the point where a $35 Raspberry Pi can be a reasonable alternative to a traditional desktop or laptop, and microcontrollers in the Arduino ecosystem are getting powerful enough to handle some remarkably demanding computational jobs. But there’s still one area where microcontrollers seem to be lagging a bit: machine learning. Sure, there are purpose-built edge-computing SBCs, but wouldn’t it be great to be able to run AI models on versatile and ubiquitous MCUs that you can pick up for a couple of bucks?

We’re moving in that direction, and our friends at Adafruit Industries want to stop by the Hack Chat and tell us all about what they’re working on. In addition to Ladyada and PT, we’ll be joined by Meghna Natraj, Daniel Situnayake, and Pete Warden, all from the Google TensorFlow team. If you’ve got any interest in edge computing on small form-factor computers, you won’t want to miss this chat. Join us, ask your questions about TensorFlow Lite and TensorFlow Lite for Microcontrollers, and see what’s possible in machine learning way out on the edge.

Our Hack Chats are live community events in the Hackaday.io Hack Chat group messaging. This week we’ll be sitting down on Wednesday, September 11 at 12:00 PM Pacific time. If time zones have got you down, we have a handy time zone converter.

Click that speech bubble to the right, and you’ll be taken directly to the Hack Chat group on Hackaday.io. You don’t have to wait until Wednesday; join whenever you want and you can see what the community is talking about.

This Machine Learning Algorithm Is Meta

September 3, 2019 by Bryan Cockfield 20 Comments

Suppose you ran a website releasing many articles per day about various topics, all following a general theme. And suppose that your website allowed for a comments section for discussion on those topics. Unless you are brand new to the Internet, you’ll also imagine that the comments section needs at least a little bit of moderation to filter out spam, off topic, or even toxic comments. If you don’t want to employ any people for this task, you could try this machine learning algorithm instead.

[Ladvien] goes through a general overview of how to set up a convolutional neural network (CNN) which can be programmed to do many things, but this one crawls a web page, gathers data, and also makes decisions regarding that data. In this case, the task is to identify toxic comments but the goal is not to achieve the sharpest sword in the comment moderator’s armory, but to learn more about how CNNs work.

Written in Python, the process outlines the code itself and how it behaves, setting up a small server to host the neural network, and finally creating the webservice. As with any machine learning, you need a reliable dataset to use for training and this one came from Wikipedia comments previously flagged by humans. Trolling nuance is thrown aside, as the example homes in on blatant insults and vulgarity.

While [Ladvien] notes that his guide isn’t meant to be comprehensive, but rather to fill in some gaps that he noticed within other guides like this, we find this to be an interesting read. He also mentioned that, in theory, this tool could be used to predict the number of comments following an article like this very one based on the language in the article. We’ll leave that one as an academic exercise for now, probably.