ESP32-S3 TensorFlow Lite Model Issues - tensorflow

I worked with the new ESP32-S3 Development Board and an I2S microphone in order to create a simple voice recognition system. The software and firmware behind this are based on this project: Voice Controlled Robot - Atomic14 https://github.com/atomic14/voice-controlled-robot
This project worked flawlessly on the developer kit so I moved forward and created my own board. This schematic is inspired by the design made by Espressif: ESP32-s3 Dev Kit Schematics https://dl.espressif.com/dl/SCH_ESP32-S3-DEVKITC-1_V1_20210312C.pdf
The flashing works perfectly. I am able to use different code that uses the microphone and record sounds. No issues with programming whatsoever. But when I upload the same code that uses TFLITE (the first provided link), the code uploads, runs, and prints outputs, but the neural network does not process or output anything.
Please note that there are no differences between the code uploaded to my board and the one uploaded to the dev kit (on which everything works as it should).
There are only small differences between the two boards, but everything else (code-wise) works on my board so I am not sure what hardware issue would affect only the neural network.
The ESP32-s3 used in my design is the same one as the one on the dev kit, the only difference is the 16MB Flash in my design and 8MB Flash in the ESP32-s3 dev kit design (smaller flash memory on the board that works with the nn, compared to larger flash on the board that doesn't work with the nn).
-> Could it be a memory problem caused by an incorrectly used capacitor that could create small differences in the voltage that powers the memory?
My schematics design is attached below
ESP32-s3 my PCB design for the voice recognition module

Related

Program uploading to LPC 2148 by the time of component assembling

I am developing an elevator GLCD display (128*64) with LPC2148 Micro controller, I have done program and PCB designing also. Now I want to upload the program to micro controller, how to do it? Before fixing micro controller or after fixing micro controller want to upload program?
If I understand correctly you want to program the device without using a bootloader or a JTAG. There is some standalone programmers available for the LPC2148 device. Example here. This will allow the MCU to be programmed before placing it on the board.
The maintainability of your design however raises red flags. You should at least have a JTAG header on the board even if it is not populated. JTAG is very flexible and cheap and add lots of development and testing options.
If I am right, than the LPC2100 series does have an ROM bootloader. You only have to pull a pin (I think P0.14) to ground while reset.
Flashmagic would than be a tool of choice to download the program.
Pro: No additional hardware needed.
Con: The bootloader pin and USART (normally USART0) need to be accessable.
1.Use the Keil compiler to compile your code and
generate hex file
2.Download and Install Flash Utility
3.In flash utility
Select Com port ,Board, Baud rate (may be default) and file
4.Now click on Upload to flash

Inputting analogue data via USB

I am trying to build this device which takes analogue input from the earth , converts them into electrical impulses which I wish to input into a android smartphone for data analysis. I initially thought about using the 3.5mm jack of the android device. Apparently Android does not support input through the 3.5mm jack. So I decided to use the USB cord as the input.
Now my question is will my android phone or tablet directly able to read the USB data, or has it to be fed through some microcontroller??
I'm not sure I'm understanding your question correctly, are trying to measure soil conductivity and find out if your plants need water? which is easy. Or are you trying to build a heart monitor? which is a bit more complex.
Anyway if you are interested in conductivity measurement with Android, you may want to have a look at this device, it is driver free and works on Android.
http://www.yoctopuce.com/EN/products/usb-sensors/yocto-knob
I believe V-Alarm is using them as well
http://www.valarm.net/blog/use-valarm-sensor-for-flood-warning-and-water-detection

Simulation framework

I am working on embedded software for an industrial System. The system consists of several stepper-motors, sensors, cameras, etc. Currently, the mechanics as well as the electronics are not available - only specification.
I've implemented the simulation for some parts of mechanics/elektronics, but it takes a consiredable amount of efort. So my question:
Are there good portable (Win/Linux) Hardware simulation frameworks? Easy to install/use and affordable in prise?
My basic requirements are:
Send command to stepper -get interrupt from light-barrier
recognize object with camera ( not necessary)
mechanical parts should move according to steppers but stop
on obstacles.
objects should fall, if there is no ground underneath
fluids should increase/decrease volume in bassins according to
physical laws
My Application is in C++/Qt, so it would be the best, if such a framework had C/C++ bindings.
Thank you for any advice!
I face the same problem as I have to develop systems to interface with several types of automation devices (robots, firmware devices, etc). I still want to provide unit test for my code, but after writing 3 or 4 simulated devices, I thought it got to be a better way.
Fortunately in my case, my code was all in C# and the final solution was to use Moq to create simple mocks of those devices. I'm not familiar with mocking frameworks for C++/Qt, but a simple search rendered a couple of results, including one made by google (googlemock).

What are some ideas for an embedded and/or robotics project?

I'd like to start messing around programming and building something with an Arduino board, but I can't think of any great ideas on what to build. Do you have any suggestions?
I show kids, who have never programmed, or done any electronics before, to make a simple 'Phototrope', a light sensitive robot, in about a day. It costs under £30 (GBP) including Arduino, electronics and off-the-shelf mechanics. If folks really get into mobile robots, the initial project can grow and grow (which I feel is part of the fun).
There are international robot competitions which require relatively simple mechanics to get started, e.g. in the UK http://www.tic.ac.uk/micromouse/toh.asp
Ultimate performance require specially built machines (for lightness) , but folks would get creditable results with an Arduino Nano, the right electronics, and a couple of good motors.
A line following robot is the classic mobile robot project. The track can be as simple as electrical tape. Pololu have some fun videos about their near-Arduino 3PI robot. The sensors are about £1, and there are a bunch of simple motor+gearbox kits from lots of places for under £10. Add a few £ for motor control, and you have autonomous robot mechanics, in need of programming! Add an Infrared Remote receiver (about £1), and you can drive it around using your TV remote. Add a small solar cell, use an Arduino analogue input to measure voltage, and it can find the sun. With a bit more electronics, it can 'feed' itself. And so it gets more sophisticated. Each step might be no more than a few hours to a few days effort, and you'll find new problems to solve and learn from.
IMHO, the most interesting (low-cost) competitions are maze solving robots. The international competition rule require the robot to explore a walled maze, usually using Infrared sensors, and calculate their optimal route. The challenges include keeping track of current position to near-millimeter accuracy, dealing with real world's unpredictably noisy environment and optimising straight-line speed with shortest distance cornering.
All that in 16K of program, and 1K RAM, with real-time interrupt handling (as much as 100K interrupts/second for some motor systems), sensor sampling, motor speed control, and maze solving is an interesting programming challenge. (You might make it 'easy' with 32K of program, and 2K RAM :-)
I'm working on a 'constrained' robot challenge (based on Arduino) so that robot performance is mainly about programming rather than having a big budget.
Start small and build up to something more complex. Control servos. Blink LEDs. Debounce inputs. Read analog sensors. Display text on an LCD. Then put it together.
Despite the name, I like the "Evil Genius" book for PIC microcontrollers because of the small, easily digestible projects that tend to build on one another. It is, of course, aimed at PIC programmers rather than the Arduino, but the material covered will be useful no matter what you're developing on.
I know Arduino is trendy right now, but I also like the Teensy++ development board because of its low price-point ($24), breadboard-compatible PCB, relatively high pin count, Linux development environment, USB connectivity, and not needing a programmer. Worth considering for smaller projects.
If you come up with something cool, let me know. I need an excuse to do something fun :)
Bicycle-related ideas:
theft alarm (perhaps with radio link to a base station which is connected to a PC by Ethernet)
fancy trip computer (with reed switch or opto sensor on wheel)
integrate with a GPS telematics unit (trip logging) with Ethernet/USB download of logged data to PC. Also has an interesting PC programming component--integrate with Google Maps.
Other ideas:
Clock with automatic time sync from:
GPS receiver
FM radio signal with embedded RDS data with CT code
Digital radio (DAB+)
Mobile phone tower (would it require a subscription and SIM card for this receive-only operation?)
NTP server via:
Ethernet
WiFi
ZigBee (with a ZigBee coordinator that gets its time from e.g. Ethernet or GPS)
Mains electricity smart meter via ZigBee (I'm interested now that smart meters are being introduced in Victoria, Australia; not sure if the smart meters broadcast the time info though, and whether it requires authentication)
Metronome
Instrument tuner
This reverse-geocache puzzle box was an awesome Arduino project. You could take this to the next step, e.g. have a reverse-geocache box that gives out a clue only at a specific location, and then using physical clues found at that location coupled with the next clue from the box, determine where to go for the next step.
You could do one of the firefighting robot competitions. We built a robot in university for my bachelor's final project, but didn't have time to enter the competition. Plus the robot needed some polish anyway... :)
Video here.
Mind you, this was done with a Motorola HC12 and a C compiler, and most components outside the microcontroller board were made from scratch, so it took longer than it should. Should be much easier with prefab components.
Path finding/obstacle navigation is typically a good project to start with. If you want something practical, take a look at how iRobot vacuums the floor and come up with a better scheme.
Depends on your background and if you want practical or cool. On the practical side, a remote control could be a simple starting point. It's got buttons and lights but isn't too demanding.
For a cool project maybe a Simon-style memory game or anything with lights & noises (thinking theremin-style).
I don't have suggestions or perhaps something like a line follower robot. I could help you with some links for inspiration
Arduino tutorials
Top 40 Arduino Projects of the Web
20 Unbelievable Arduino Projects
I'm currently developing plans to automate my 30 year old model train layout.
A POV device could be fun to build (just google for POV Arduino). POV means persistence of vision.

USB for embedded devices - designing a device driver/protocol stack

I have been tasked to write a device driver for an embedded device which will communicate with the micro controller via the SPI interface. Eventually, the USB interface will be used to download updated code externally and used during the verification phase.
My question is, does anyone know of a good reference design or documentation or online tutorial which covers the implementation/design of the USB protocol stack/device driver within an embedded system? I am just starting out and reading through the 650 page USB v2.0 spec is a little daunting at the moment.
Just as a FYI, the micro controller that I am using is a Freescale 9S12.
Mark
Based upon goldenmean's (-AD) comments I wanted to add the following info:
1) The embedded device uses a custom executive and makes no use of a COTS or RTOS.
2) The device will use interrupts to indicate data is ready to be retrieved from the device.
3) I have read through some of the docs regarding Linux, but since I am not at all familiar with Linux it isn't very helpful at the moment (though I am hoping it will be very quickly).
4) The design approach, for now at least, it to write a device driver for the USB device then a USB protocol layer (I/O) would reside on top of the device driver to interpret the data. I would assume this would be the best approach, though I could be wrong.
Edit - A year later
I just wanted to share a few items before they vanish from my mind in case I never work on a USB device again. I ran into a few obstacles when developing code and getting it up and running for the first.
The first problem I ran into was that when the USB device was connected to the Host (Windows in my case) was the host issues a Reset request. The USB device would reset and clear the interrupt enable flags. I didn't read the literature enough to know this was happening, thus I was never receiving the Set-Up Request Interrupt. It took me quite a while to figure this out.
The second problem I ran into was not handling the Set-Up Request for Set_Configuration properly. I was handling it, but I was not processing the request correctly in that the USB device was not sending an ACK when this Set-Up Request came in. I eventually found this out by using a hardware USB protocol analyzer.
There were other issues that I ran into, but these were the two biggest ones that took me quite a while to figure out. The other issue I had to worry about is big-endian and little-endian, Freescale 9S12 vs USB data format (Intel), respectively.
I ended up building the USB device driver similar to UART device drivers I had done in the past. I have posted the code to this at the following URL.
http://lordhog.wordpress.com/2010/12/13/usb-drive
I tend to use structures a lot, so people may not like them since they are not as portal as using #defines (e.g., MAX3420_SETUP_DATA_AVAIL_INT_REQR 0x20), but I like them since it makes the code more readable for me. If anyone has questions regarding it please feel free to e-mail and I can try to give some insight to it. The book "USB Complete: The Developer's Guide" was helpful, so long as you knew what areas to concentrate on. This was a simple application and only used low-speed USB.
While writing a device driver for any interface (USB, Parallel port, etc...) the code needed to be developed would depend upon whether there is any Operating System(OS), RTOS running on that Processor/Micro controller.
e.g. if thats going to run say WinCE - It will have its own Driver development Kit , and steps to be followed in the device driver development. Same for any other OS like Linux, symbian.
If its going to be a plain firmware code(No OS) which is going to control the processor/microcontroller, then it's a different situation altogether.
So based on either of the above situation u are in, one needs to read & understand:-
1.) The Hardware Specification of the processor/micro controller development board - Register files, ports, memory layout, etc.
2.) USB spec
3.) Couple of pointers i found quickly. Google shud be ur friend!
http://www.lrr.in.tum.de/Par/arch/usb/usbdoc/ - Linux USB device driver
http://www.microsoft.com/technet/archive/wce/support/usbce.mspx
-AD
I've used an earlier edition of USB Complete by Jan Axelson. Indeed very complete.
From the editorial review:
Now in its fourth edition, this developer's guide to the Universal Serial Bus (USB) interface covers all aspects of project development, such as hardware design, device firmware, and host application software.
I'm curious, why did you pick the 9S12? I used it at a previous job, and was not pleased.
It had lousy gcc support so we used Metrowerks
which may have been okay for C, but often generated buggy C++
had a lousy IDE with binary project files!
The 9s12 was also slow, a lot of instructions executed in 5 cycles.
Not very power efficient, either.
no barrel shifter, made operations that are common in embedded code slow
not that cheap.
About the only thing I dislike more is an 8051. I'm using an ARM CortexM3 at my current job, it's better than a 9S12 in every way (faster clock, more work done per clock, less power consumption, cheaper, good gcc support, 32-bit vs. 16-bit).
I don't know which hardware you're planning to use but assuming that's flexible, STMicro offers a line of microcontrollers with USB/SPI support and a library of C-code that can be used with their parts. -- I've used their ARM7 series micros for years with great success.
Here is an excellent site maintained by Jonathan Valvano, a professor at the University of Texas. He teaches four courses over there (three undergraduate, one graduate), all are about using a 9S12 microcontroller. His site contains all the lecture notes, lab manuals, and more importantly, starter files, that he uses for all his classes.
The website looks like it's from the 90's, but just dig around a bit and you should find everything you need.
users.ece.utexas.edu/~valvano/
Consider AVR for your next MCU project because of it's wonderful LUFA and V-USB libraries.
I'm working on a project using the Atmel V71. The processor is very powerful and among lot's of high end connectivity offered on chip is a USB engine that will do device or host modes for 480 Mhz or 48Mhz (not USB 3.0). The tools are free and come with a number of host and device USB example projects with all the USB stack code right there. It supports 10 end points and all the transfers are done via DMA so you have most of the processor horsepower available for other tasks. The Atmel USB stack works without needing an RTOS