Using our SaraKIT electronics, we can build a device with ChatGPT support in a housing printed on a 3D printer with the function of tracking and recognition the user's face:
the operation of the device is shown in this video:
Of course, for simple integration with ChatGPT, the PCB itself is enough, without cameras, motors or a special housing, but this deprives our assistant of the sense of sight.
With three sensitive microphones, it is possible to recognize speech from a distance of up to 5 meters, which makes it easy to integrate the device with Amazon Alexa, ChatGPT, Google Home, and other voice control systems.
In the version with the pan-tilt camera, facial detection and tracking allow for activation with just a glance (without the need to speak wake words like "Alexa" or "OK Google"). An example of this can be seen in the demonstration video:
SaraKIT is an easy-to-use face analysis solution for Raspberry Pi 4 CM4, powered by state-of-the-art algorithms based on MediaPipe from Google. It provides robust functionality for face detection, face landmark detection, and face mesh processing, specifically optimized for the Raspberry Pi 64-bit platform.
"Discover the Power of SaraKIT's Pan-Tilt Camera with Advanced Face Detection and Tracking!"
Our pan tilt camera system, based on the SaraKIT platform, offers excellent face detection capabilities and the ability to track facial movements. By utilizing quiet, precise, and fast BLDC Gimbal motors, the camera can smoothly move in response to facial motions, ensuring precise and accurate tracking. This innovative solution represents another way to leverage SaraKIT in projects related to artificial intelligence and home automation. It enables integration with AI systems and home automation, opening up new possibilities for monitoring, facial recognition, and real-time interaction.
Object detection is another component of our project thanks to which we can build our ChatGPT with many new features. Be amazed by our ChatGPT-powered voice assistant that not only hears but also sees and asks questions based on what it sees.
Watch in awe as we showcase our latest creation - a remote-controlled car controlled by a smartphone! Using the versatile SaraKIT platform combined with LEGO bricks, we've brought this innovative project to life. With just a few taps on your smartphone, you can maneuver the car with precision and explore the world of remote control like never before.
But that's not all! With the power of Raspberry Pi, you can unlock endless possibilities. Connect a camera and explore the surroundings, follow lines with precision, detect objects, or even control the car with your voice. The only limit is your imagination!
To get started with your own remote-controlled car project, head over to our GitHub repository. There, you'll find the source code for our programs in C++, Python, and Delphi. Feel free to explore, experiment, and customize the code to suit your preferences and take your project to the next level.
Join us on this exciting journey as we demonstrate the seamless integration between SaraKIT, LEGO, and Raspberry Pi. Witness the incredible capabilities and unleash your creativity to take this project to new heights.
Control of a silent precision pan-tilt camera or two cameras with two BLDC gimbal motors
This example shows how to control motor speed, torque and angle of BLDC gimbal motors using the Field Oriented Control (FOC) algorithm (or not) in C++/Python.
BLDC motors have become increasingly popular due to their smooth operation, high torque, and precise control. In this guide, we will explore the use of BLDC motors using SaraKIT, and compare them to other commonly used motors such as stepper motors and servos.
In this video, I demonstrate how easy it is to control BLDC gimbal motors, and also discuss the advantages and disadvantages of solutions based on servos or stepper motors. I also show the difference in controlling gimbal motors that have a decoder and those that do not.
We try to simplify the program code as much as possible, we show many examples of use. For example, what you see in the video above is implemented literally in a few lines of the program:
or knowing the diameter of the wheel, we can move the vehicle by a certain number of centimeters or meters (c++,python):
BLDCMotor_DriveMeters(uchar motorId, float centimeters, float speed, uchar torque, float WhellDiameter);
Example of use, demonstration of the speed and power of BLDC motors
This movie showcases one of the applications of SaraKIT, an extension kit for Raspberry Pi 4 in CM4 version.
The SaraKIT kit includes most of the necessary elements:
- Two FOC gimbal motor drivers for BLDC motors
- An accelerometer with a gyroscope
- Support for motor encoders
- 3 sensitive microphones for voice control
- Two camera outputs for live streaming from a moving vehicle
- The ability to connect power from easily available Power Banks (PD2.0 PD3.0 Fast Charging and QC4 with USB-C output) with a special PD 12v cable or by connecting a USB cable via USB-C Pd Trigger Module Pd 12v.
Additionally, you will need two BLDC gimbal motors, two encoders, two motor-to-brick adapters, and some building blocks. The design of the vehicle is up to you. The brick adapters can be easily 3D-printed (the relevant stl and obj files are included on our website) or purchased for a few dollars from our site.
This robot demonstrates the power of BLDC gimbal motors; it is very difficult to overturn, quiet, and fast, and does not require heavy loads to be placed high up.
SaraKIT with thre microphones and ZL38063 enables to analyse sound direction location. ZL38063 beamformer reports the angle of the most significant sound source for linear/triangular microphone configuration. The axis between Mics 1 and 2 defines the main axis, with 0 degrees to the right and +180 degrees to the left, with +90 degrees defined as being at the top of the array (opposite side of main axis from Mic 3)