Electronic Glove Detects Sign Language

December 20, 2014 by Rick Osgood 11 Comments

A team of Cornell students recently built a prototype electronic glove that can detect sign language and speak the characters out loud. The glove is designed to work with a variety of hand sizes, but currently only fits on the right hand.

The glove uses several different sensors to detect hand motion and position. Perhaps the most obvious are the flex sensors that cover each finger. These sensors can detect how each finger is bent by changing the resistance according to the degree of the bend. The glove also contains an MPU-6050 3-axis accelerometer and gyroscope. This sensor can detect the hand’s orientation as well as rotational movement.

While the more high-tech sensors are used to detect most characters, there are a few letters that are similar enough to trick the system. Specifically, they had trouble with the letters R, U, and V. To get around this, the students strategically placed copper tape in several locations on the fingers. When two pieces of tape come together, it closes a circuit and acts as a momentary switch.

The sensor data is collected by an ATmega1284p microcontroller and is then compiled into a packet. This packet gets sent to a PC which then does the heavy processing. The system uses a machine learning algorithm. The user can train the it by gesturing for each letter of the alphabet multiple times. The system will collect all of this data and store it into a data set that can then be used for detection.

This is a great project to take on. If you need more inspiration there’s a lot to be found, including another Cornell project that speaks the letters you sign, as well as this one which straps all needed parts to your forearm.
Continue reading “Electronic Glove Detects Sign Language” →

Phone Gyroscope Signals Can Eavesdrop On Your Conversations

August 24, 2014 by Mathieu Stephan 9 Comments

A gyroscope is a device made for measuring orientation and can typically be found in modern smartphones or tablet PCs to enable rich user experience. A team from Stanford managed to recognize simple words from only analyzing gyroscope signals (PDF warning). The complex inner workings of MEMS based gyroscopes (which use the Coriolis effect) and Android software limitations only allowed the team to only sniff frequencies under 200Hz. This may therefore explain the average 12% word recognition rate that was achieved with custom recognition algorithms. It may however still be enough to make you reconsider installing an app that don’t necessarily need access to the on-board sensors to work. Interestingly, the paper also states that STMicroelectronics currently have a 80% market share for smartphone / Tablet PCs gyroscopes.

On the same topic, you may be interested to check out a gyroscope-based smartphone keylogging attack we featured a couple of years ago.

Prosthetic Spines Become Musical Instruments

July 16, 2013 by Brian Benchoff 4 Comments

spine

[Joseph] and [Ian] have been working on a project that turns physical objects into bendable, snake-like controllers

This build is the culmination of an earlier project that digitally modeled a flexible object with accelerometers, gyroscopes, and IMUs. When we first saw this build, we wondered what it could actually be used for, but it seems [Joseph] and [Ian] came up with a pretty cool use for it: turning prosthetic spines and ribs into musical instruments.

These flexible devices are loaded up with sensors along their joints and are connected to a microcontroller with a Zigbee radio transceiver. The positioning data from these devices is transmitted to a computer where it’s turned into audio, effectively turning a dancer into a musical instrument.

For an art piece, it’s pretty cool, but as a new means of interacting with a computer, we’re thinking this might be a game changer. Imagine a gauntlet loaded up with IMUs being turned into a waldo, or precisely controlling virtual objects naturally with your hand.

Autonomous RC Car Navigates By Waypoints

June 16, 2013 by Mike Szczys 8 Comments

autonomous-rc-car

Check out this autonomous RC car which [Jason] built for the chipKIT design challenge. It’s been able to successfully navigate a planned route taking just a few waypoints as inputs.

Obviously this uses a chipKIT as the controller, the max32 to be specific. [Jason’s] write-up shows off all of the components of the design, but you’ll have to head over to his recently posted update to hear about the custom board he had spun to host them all. It starts with a GPS module, but that’s only accurate enough to give the rover the big picture. To handle getting from one waypoint to the next successfully he also included a gyroscope which provides very accurate orientation data, as well as optical encoders on the wheels for on-board distance traveled information.

We hope he’ll keep refining the design and make a trip to next year’s Autonomous Vehicle Competition.

Continue reading “Autonomous RC Car Navigates By Waypoints” →

Valentine’s Puzzle Box Makes You Work For What’s Inside

February 18, 2013 by Mike Szczys 11 Comments

valentines-puzzle-box

Here’s a new take on a gift box which has been locked from the inside. I doesn’t rely on GPS coordinates or a real-time clock to unfasten the latch. Instead, the box itself acts as a puzzle. You follow the visual and audio clues, turning the box along three axes in order to input the unlock code.

There are three different difficulty settings. The easiest uses the LED heart to indicate which direction to turn the box next. This is accompanied by a beep for correct or a longer tone for incorrect movements. On the medium setting you can only go by the tones, but once you screw up the lights will aid you in getting back to where you where when making the mistake. The impossible setting doesn’t use the lights at all.

[Matt] took inspiration from some reverse geocache projects featured here on Hackaday. He already had an STM32F3 Discovery board on hand which he received as a sample. It’s driving all of the electronics inside, with the on-board gyroscope as the input device. Don’t miss the video after the break to see how well the thing works.

Continue reading “Valentine’s Puzzle Box Makes You Work For What’s Inside” →

Quadcopter Brain

February 15, 2013 by Mike Szczys 34 Comments

quadcopter-brain

This project is the warm center of [Alan Kharsansky’s] thesis in Electronic Engineering. It’s an all-in-one control board for a quadcopter. This is the second iteration of the board, the first version he actually etched himself. As you can see after the break the firmware is not quite ready for prime-time. But that doesn’t stop us from appreciating the design choices he’s made.

You can see the effort he made to keep the board symmetrical which will help when it comes time to balance the aircraft. At the center of the PCB is the jewel of the sensor array, a combination accelerometer and gyroscope. This location will help easy the trouble of designing PID algorithms to drive the four propellers. Also included in the sensor array is a magnetometer for navigation, and a barometric pressure sensor which can be used as an altimeter. There are four multipurpose connectors used to drive the motors and provide feedback to the boards. He also included two more sets of pads on the board (without their own connectors) in case he wants to add more motors in the future. The quadcopter can be controlled from a base station via the XBee module.

Continue reading “Quadcopter Brain” →

Tutorial Explains The Concepts Behind An IMU

September 25, 2012 by Mike Szczys 12 Comments

[Anilm3] wrote in to share the IMU tutorial series he is working on. An Inertial Measurement Unit is most often found in self-balancing robots and quadcopters, providing enough high-speed sensor data to keep up with the effects of gravity. He previously used some all-in-one IMU devices in school which did most of the work for him. But he wanted to grind down and look at what each sensor spits out and how those measurements are used. The first installment deals with the accelerometer, using its data to calculate pitch and roll. For these demonstrations [Anilm3] is using this ADXL345 sensor board, an Arduino, and some processing sketches for testing.

Whenever working with sensors you need to take noise into consideration. The post shows how to implement a low-pass filter in the code which will help smooth out the readings. The filtered data is then fed to a couple of mostly-painless formulas which calculate the movement of the accelerometer in degrees. The demonstration sketch is mapped to a 3D cube to give you an idea of how accurate the accelerometer is. There’s a little bit of lag which would let a self-balancing robot have a nasty fall. The solution to this issue will be discussed in upcoming parts of the series. The next installment tackles the gyroscope sensor.