Robots Can Finally Answer, Are You Talking To Me?

November 8, 2020 by Matthew Carlson 25 Comments

Voice Assistants, love them, or hate them, are becoming more and more commonplace. One problem for voice assistants is the situation of multiple devices listening in the same place. When a command is given, which device should answer? Researchers at CMU’s Future Interfaces Group [Karan Ahuja], [Andy Kong], [Mayank Goel], and [Chris Harrison] have an answer; smart assistants should try to infer if the user is facing the device they want to talk to. They call it direction-of-voice or DoV.

Currently, smart assistants use a simple race to see who heard it first. The reasoning is that the device you are closest to will likely hear it first. However, in situations with echos or when you’re equidistant from multiple devices, the outcome can seem arbitrary to a user.

The implementation of DoV uses an Extra-Trees Classifier from the python sklearn toolkit. Several other machine learning algorithms were considered, but ultimately efficiency won out and Extra-Trees was selected. Another interesting facet of the research was determining what facing really means. The team had humans ‘listeners’ stand in for smart assistants. A ‘talker’ would speak the key phrase while the ‘listener’ determined if the talker was facing them or not. Based on their definition of facing, the system can determine if someone is facing the device with 90% accuracy that rises to 93% with per-room calibration.

Their algorithm as well as the data they collected has been open-sourced on GitHub. Perhaps when you’re building your own voice assistant, you can incorporate DoV to improve wake-word accuracy.

Continue reading “Robots Can Finally Answer, Are You Talking To Me?” →

A Smart Speaker That Reminds You It’s Listening

October 15, 2020 by Matthew Carlson 20 Comments

[markw2k9] has an Alexa device that sits in his kitchen and decided it was time to spruce it up with some rather uncanny eyes. With some inspiration from the Adafruit Uncanny Eyes project, which displays similar animated eyes, [markw2k9] designed a 3d printed shell that goes on top of a 2nd generation Amazon Echo. A teensy 3.2 powers two OLED displays and monitors the light ring to know when to turn the lights on and show that your smart speaker is listening. The eyes look around in a shifty sort of manner. Light from the echo’s LED ring is diffused through a piece of plexiglass that was lightly sanded on the outside ring and the eye lenses are 30mm cabochons (a glass lens often used for jewelry).

One hiccup is that the ring on the Echo will glow in a steady pattern when there’s a notification. As this would cause the OLEDs to be on almost continuously and concerned for the lifetime of the OLED panels, the decision was made to detect this condition in the state machine and go into a timeout state. With that issue solved, the whole thing came together nicely. Where this project really shines is the design and execution. The case is sleek PLA and the whole thing looks professional.

We’ve seen a few other projects inspired by the animated eyes project such as this Halloween themed robot that is honestly quite terrifying. The software and STL files for the smart speaker’s eyes are on Github and Thingiverse.

Continue reading “A Smart Speaker That Reminds You It’s Listening” →

Voice Controlled RGB LEDs Go Big

October 2, 2020 by Tom Nardi 1 Comment

When we see RGB LEDs used in a project, they’re often used more for aesthetic purposes than as a practical source of light. It’s an easy way to throw some color around, but certainly not the sort of thing you’d try to light up anything larger than a desk with. Apparently nobody explained the rules to [Brian Harms] before he built Light[s]well.

Believe it or not, this supersized light installation doesn’t use any exotic hardware you aren’t already familiar with. Fundamentally, what we’re looking at is a WiFi enabled Arduino MKR1000 driving strips of NeoPixel LEDs. It’s just on a far larger scale than we’re used to, with a massive 4 x 8 aluminum extrusion frame suspended over the living room.

Onto that frame, [Brian] has mounted an undulating diffuser made of 74 pieces of laser-cut cardstock. Invoking ideas of waves or clouds, the light looks like its of natural or even biological origin while at the same time having a distinctively otherworldly quality to it.

The effect is even more pronounced when the RGB LEDs kick in, thanks to the smooth transitions between colors. In the video after the break, you can see Light[s]well work its way from bright white to an animated rainbow. As an added touch, he added Alexa voice control through Arduino’s IoT Cloud service.

While LED home lighting is increasingly becoming the norm, projects like Light[s]well remind us that we aren’t really embracing the possibilities offered by the technology. The industry has tried so hard to make LEDs fit into the traditional role of incandescent bulbs, but perhaps its time to rethink things.

Continue reading “Voice Controlled RGB LEDs Go Big” →

Robotic Biped Walks On Inverse Kinematics

July 3, 2020 by Orlando Hoilett 6 Comments

Robotics projects are always a favorite for hackers. Being able to almost literally bring your project to life evokes a special kind of joy that really drives our wildest imaginations. We imagine this is one of the inspirations for the boom in interactive technologies that are flooding the market these days. Well, [Technovation] had the same thought and decided to build a fully articulated robotic biped.

Each leg has pivot points at the foot, knee, and hip, mimicking the articulation of the human leg. To control the robot’s movements, [Technovation] uses inverse kinematics, a method of calculating join movements rather than explicitly programming them. The user inputs the end coordinates of each foot, as opposed to each individual joint angle, and a special function outputs the joint angles necessary to reach each end coordinate. This part of the software is well commented and worth your time to dig into.

In case you want to change the height of the robot or its stride length, [Technovation] provides a few global constants in the firmware that will automatically adjust the calculations to fit the new robot’s dimensions. Of all the various aspects of this project, the detailed write-up impressed us the most. The robot was designed in Fusion 360 and the parts were 3D printed allowing for maximum design flexibility for the next hacker.

Maybe [Technovation’s] biped will help resurrect the social robot craze. Until then, happy hacking.

Continue reading “Robotic Biped Walks On Inverse Kinematics” →

Alexa, Shoot Me Some Chocolate

May 11, 2020 by Kristina Panos 10 Comments

[Harrison] has been busy finding the sweeter side of quarantine by building a voice-controlled, face-tracking M&M launcher. Not only does this carefully-designed candy launcher have control over the angle, direction, and velocity of its ammunition, it also locates and locks on to targets by itself.

Here comes the science: [Harrison] tricked Alexa into thinking the Raspberry Pi inside the machine is a smart TV named [Chocolate]. He just tells an Echo to increase the volume by however many candy-colored projectiles he wants launched at his face. Simply knowing the secret language isn’t enough, though. Thanks to a little face-based security, you pretty much have to be [Harrison] or his doppelgänger to get any candy.

The Pi takes a picture, looks for faces, and rotates the turret base in that direction using three servos driven by Arduino Nanos. Then the Pi does facial landmark detection to find the target’s mouth hole before calculating the perfect parabola and firing. As [Harrison] notes in the excellent build video below, this machine uses a flywheel driven by a DC motor instead of being spring-loaded. M&Ms travel a short distance from the chute and hit a flexible, spinning disc that flings them like a pitching machine.

We would understand if you didn’t want your face involved in a build with Alexa. It’s okay — you can still have a voice-controlled candy cannon.

Continue reading “Alexa, Shoot Me Some Chocolate” →

Stay Smarter Than Your Smart Speaker

April 1, 2020 by Kristina Panos 56 Comments

Smart speakers have always posed a risk to privacy and security — that’s just the price we pay for getting instant answers to life’s urgent and not-so-urgent questions the moment they arise. But it seems that many owners of the 76 million or so smart speakers on the active install list have yet to wake up to the reality that this particular trick of technology requires a microphone that’s always listening. Always. Listening.

With so much of the world’s workforce now working from home due to the global SARS-CoV-2 pandemic, smart speakers have suddenly become a big risk for business, too — especially those where confidential conversations are as common and crucial as coffee.

Imagine the legions of lawyers out there, suddenly thrust from behind their solid-wood doors and forced to set up ramshackle sub rosa sanctuaries in their homes to discuss private matters with their equally out-of-sorts clients. How many of them don’t realize that their smart speaker bristles with invisible thorns, and is even vulnerable to threats outside the house? Given the recent study showing that smart speakers can and do activate accidentally up to 19 times per day, the prevalence of the consumer-constructed surveillance state looms like a huge crisis of confidentiality.

So what are the best practices of confidential work in earshot of these audio-triggered gadgets?

Continue reading “Stay Smarter Than Your Smart Speaker” →

Smart Speakers “Accidentally” Listen Up To 19 Times A Day

March 11, 2020 by Kristina Panos 66 Comments

In the spring of 2018, a couple in Portland, OR reported to a local news station that their Amazon Echo had recorded a conversation without their knowledge, and then sent that recording to someone in their contacts list. As it turned out, the commands Alexa followed came were issued by television dialogue. The whole thing took a sitcom-sized string of coincidences to happen, but it happened. Good thing the conversation was only about hardwood floors.

But of course these smart speakers are listening all the time, at least locally. How else are they going to know that someone uttered one of their wake words, or something close enough? It would sure help a lot if we could change the wake word to something like ‘rutabaga’ or ‘supercalifragilistic’, but they probably have ASICs that are made to listen for a few specific words. On the Echo for example, your only choices are “Alexa”, “Amazon”, “Echo”, or “Computer”.

So how often are smart speakers listening when they shouldn’t? A team of researchers at Boston’s Northeastern University are conducting an ongoing study to determine just how bad the problem really is. They’ve set up an experiment to generate unexpected activation triggers and study them inside and out.

Continue reading “Smart Speakers “Accidentally” Listen Up To 19 Times A Day” →