Robots Can Finally Answer, Are You Talking To Me?

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?”

Near-Silent Bellows Uses Water Flow And Magnetic Coupling

Fan noise is a contentious issue among the computer community. Some don’t notice it, others rage against it as an annoyance and distraction. Some turn to liquid cooling, while others look to passive solutions to eliminate the scourge. [Matt] of [DIY Perks] may have found a far more oddball solution, however.

The build is essentially a giant bellows, but the manner in which it operates is unlike anything we’ve seen previously. To shift the large pusher plate inside back and forth, [Matt] initially experimented with building his own linear motor out of coils and magnets. After that failed, he began to tinker with a system of moving a magnet back and forth through a tube with water pressure from a pump, which would then drive the pusher plate through magnetic coupling. This looked promising, but reversing the flow proved difficult. After building his own set of water valves to change the flow direction, the bellows began to work slowly, but with limited performance. Realizing the valves weren’t up to scratch, [Matt] rebuilt the system with 10 pumps, set up in two banks of 5. With the pumps hooked up in series, they supplied plenty of pressure to force the bellows back and forth. Reed switches were used to reverse the flow at either end to make the bellows run continuously.

In testing, the bellows compared well with a bank of four large case fans, though at 20 times the size. Suffice to say this is not exactly a compact solution. We look forward to seeing [Matt] do more with the bellows, with his intention being to use it as the primary cooling system for a computer. Of course, if this looks too complex, you could always consider a mineral oil setup instead. Video after the break.

Continue reading “Near-Silent Bellows Uses Water Flow And Magnetic Coupling”

Door Mutes Microphone To Prevent Remote Learning Humiliation

In a kind of reverse twist on the doorbell, [TheStaticTurtle] whipped up a system to mute his computer’s microphone whenever someone opens the door to his room. He lives in France, where the government announced a strict lockdown last Friday. Like many university students around the world these days, he is now forced to take online classes. Even though he has his own room, occasionally someone will barge in and announce something, often to [TheStaticTurtle]’s embarrassment.  When his classmates suddenly heard “Do you want some pie?” the other day, it was the last straw.

His first decision was to sense the door opening with a magnet and sensor, which he stuck to the door and frame with hot glue. He then ran a long cable to his desk, where it connected to an ATTiny 85 with a DigiSpark boot-loader. He wrote firmware to simulate special key combinations, which were then registered with his audio routing software Voicemeeter Potato. We presume he isn’t using an external mic, in which case muting might have been easier to accomplish with a hardware switch. All in all, this is a pretty clever and timely hack. Should you be in a similar predicament and want to try this out, he’s published the source code on GitHub.

Continue reading “Door Mutes Microphone To Prevent Remote Learning Humiliation”

The BYTE Is The Grand Prize Winner Of The 2020 Hackaday Prize

The BYTE, an open-source mouth-actuated input device for people with physical challenges has just been named the Grand Prize winner of the 2020 Hackaday Prize. The award for claiming the top place and title of “Best All Around” in this global engineering initiative is $50,000. Five other top winners and four honorable mentions were also named during this evening’s Hackaday Prize Ceremony, held during the Hackaday Remoticon virtual conference.

This year’s Hackaday Prize focused on challenges put forth by four non-profit partners who have first hand knowledge of the problems that need solving as they work to accomplish their missions. These organizations are Conservation X Labs, United Cerebral Palsy Los Angeles, CalEarth, and Field Ready. Join us below for more on the grand prize winner and to see the Best in Category and Honorable Mention winners from each non-profit challenge, as well as the Best Wildcard project.

Over $200,000 in cash prizes have been distributed as part of this year’s initiative where hundreds of hardware hackers, makers, and artists competed to build a better future. Continue reading “The BYTE Is The Grand Prize Winner Of The 2020 Hackaday Prize”

An Old-School Control Panel For Your Computer

For as long as computers have been in the hands of programmers, they have offered frequent mildly tedious tasks that their operators have sought to automate. Who hasn’t written a shell script or a batch file that unites a string of commands into one just to save a bit of typing?

But even that effort can be reduced with a hardware add-on that ties the script to a physical control, and in this endeavor [Tomas] has created a beauty. His control panel project mimics the robust industrial panels of yesteryear with an array of metal buttons and toggle switches in a sturdy metal case sourced from an old KVM switch.

Behind the scenes are a pair of I/O extenders and a NodeMCU board, whose ESP8266 does the talking to the host computer on which a daemon awaits its call. Individual addressable LEDs next to each switch convey the state of operation, and the switches trigger useful operations such as connecting to a VPN. All the code is available in a handy GitHub repository, and you can see it in action in the video we’ve placed below the break.

We rather like the idea of a desktop control panel here at Hackaday, indeed this isn’t the first one we’ve brought you.

Continue reading “An Old-School Control Panel For Your Computer”

One Wheel Is All We Need To Roll Into Better Multirotor Efficiency

Multirotor aircraft enjoy many intrinsic advantages, but as machines that fight gravity with brute force, energy efficiency is not considered among them. In the interest of stretching range, several air-ground hybrid designs have been explored. Flying cars, basically, to run on the ground when it isn’t strictly necessary to be airborne. But they all share the same challenge: components that make a car work well on the ground are range-sapping dead weight while in the air. [Youming Qin et al.] explored cutting that dead weight as much as possible and came up with Hybrid Aerial-Ground Locomotion with a Single Passive Wheel.

As the paper’s title made clear, they went full minimalist with this design. Gone are the driveshaft, brakes, steering, even other wheels. All that remained is a single unpowered wheel bolted to the bottom of their dual-rotor flying machine. Minimizing the impact on flight characteristics is great, but how would that work on the ground? As a tradeoff, these rotors have to keep spinning even while in “ground mode”. They are responsible for keeping the machine upright, and they also have to handle tasks like steering. These and other control algorithm problems had to be sorted out before evaluating whether such a compromised ground vehicle is worth the trouble.

Happily, the result is a resounding “yes”. Even though the rotors have to continue running to do different jobs while on the ground, that was still far less effort than hovering in the air. Power consumption measurements indicate savings of up to 77%, and there are a lot of potential venues for tuning still awaiting future exploration. Among them is to better understand interaction with ground effect, which is something we’ve seen enable novel designs. This isn’t exactly the flying car we were promised, but its development will still be interesting to watch among all the other neat ideas under development to keep multirotors in the air longer.

[IROS 2020 Presentation video (duration 10:49) requires no-cost registration, available until at least Nov. 25th 2020. Forty-two second summary embedded below]

Continue reading “One Wheel Is All We Need To Roll Into Better Multirotor Efficiency”

How To Improve A Smart Motor? Make It Bigger!

Brushless motors can offer impressive torque-to-size ratios, and when combined with complex drive control and sensor feedback, exciting things become possible that expand the usual ideas of what motors can accomplish. For example, to use a DC motor in a robot leg, one might expect to need a gearbox, a motor driver, plus an encoder for position sensing. If smooth, organic motion is desired, some sort of compliant mechanical design would be involved as well. But motors like the IQ Vertiq 6806 offered by [IQ Motion Control] challenge those assumptions. By combining a high-torque brushless DC motor, advanced controller, and position sensing into an integrated device, things like improved drone performance and direct-drive robotic legs like those of the Mini Cheetah become possible.

IQ Vertiq 6806 brushless DC motor with integrated controller, driver, and position sensing.

First, the bad news: these are not cheap motors. The IQ Vertiq 6806 costs $399 USD each through the Crowd Supply pre-order ($1499 for four), but they aren’t overpriced for what they are. The cost compares favorably with other motors and controllers of the same class. A little further than halfway down the Crowd Supply page, [IQ Motion Control] makes a pretty good case for itself by comparing features with other solutions. Still, these are not likely to be anyone’s weekend impulse purchase.

So how do these smart motors work? They have two basic operating modes: Speed and Position, each of which requires different firmware, and which one to use depends on the intended application.

The “Speed” firmware is designed with driving propeller loads in mind, and works a lot like any other brushless DC motor with an ESC (electronic speed control) on something like a drone or other UAV. But while the unit can be given throttle or speed control signals like any other motor, it can also do things like accept commands in terms of thrust. In other words, an aircraft’s flight controller can communicate to motors directly in thrust units, instead of a speed control signal whose actual effect is subject to variances like motor voltage level.

The “Position” mode has the motor function like a servo with adjustable torque, which is perfect for direct drive applications like robotic legs. The position sensing also allows for a few neat tricks, like the ability to use the motors as inputs. Embedded below are two short videos showcasing both of these features, so check them out.

Continue reading “How To Improve A Smart Motor? Make It Bigger!”