HardLabs

NeuroBot

viktorvano·NeuroBot·KiCad/Neural Robot/NeuralRobot.kicad_pcb

NeuroBot PCB layout, top view — open source STM32 board by viktorvano
Simulate this board

About the NeuroBot PCB

NeuroBot is an open source STM32 PCB design by viktorvano, published on GitHub under the MIT license. It is a 2-layer board measuring 70 × 90 mm, with 70 components from 30 distinct parts.

Its main chip is the STM32F103RET6, from the STM32 family. Other key parts include the BSL316C, MIC5504-3.3YM5 and DRV8833PWP. By type, the board carries 31 capacitors, 10 resistors, 7 ICs, 3 connectors, 3 LEDs and 1 crystal.

It belongs with the robotics & motion designs in this gallery.

From the project

Robot With Deep Neural Network

Demo video: https://www.youtube.com/watch?v=UL9zreCno

Android App: https://play.google.com/store/apps/details?id=com.cyberpunktech.RobotController.app

If the content of "weights.txt" file is deleted, the neural network automatically retrain itself again. If the number of weights in the weights.txt file matches with topology, the Neural Network just loads them, and runs.

Main components on the NeuroBot

STM32F103RET6BSL316CMIC5504-3.3YM5DRV8833PWP

NeuroBot bill of materials (BOM)

70 components, 30 distinct parts.

QtyPartRefs
1
STM32F103RET6
MCU1
3
BSL316C
U1, U2, U12
2
MIC5504-3.3YM5
U9, U11
1
DRV8833PWP
U10
1
8MHz
Y1
1
Servo X
J1
1
Servo_Y
J2
1
USB_C_Receptacle
J3
1
ADC
ADC1
1
JDY-08
BT1
1
LiPol 3.7V
Battery1
1
TP4056
CHARGER1
5
SW_Push
DOWN1, OK1, POWER1, RESET1, UP1
1
TPS78233
LDO1
1
MOTORS
MOTOR_OUT1
1
SSD1306
OLED1
1
SWD
ST-Link1
1
VL53L0X module
ToF_connector1
1
TFP09-2-12B
microSD1
3
LED
BLUETOOTH1, LEARN1, RUN1
Show 10 more
QtyPartRefs
12
100nF
C1, C2, C3, C4, C40, C42, C46, C47 +4
2
18pF
C37, C38
12
1uF
C39, C41, C43, C44, C45, C48, C50, C51 +4
3
10uF
C53, C57, C63
1
2.2uF
C54
1
10nF
C58
1
1k2
R1
5
4k7
R2, R3, R4, R9, R10
1
1k5
R5
3
680R
R6, R7, R8

NeuroBot design files

The KiCad project lives in the viktorvano/NeuroBot repository on GitHub; these links point at the commit this page was built from.

NeuroBot: common questions

What microcontroller does the NeuroBot use?

The NeuroBot is built around the STM32F103RET6, from the STM32 family.

How big is the NeuroBot PCB?

The NeuroBot measures 70 × 90 mm, has 2 copper layers and is 1.6 mm thick.

How many components are on the NeuroBot?

70 components, from 30 distinct parts. The full bill of materials is listed on this page.

Where can I download the NeuroBot design files?

From the viktorvano/NeuroBot repository on GitHub, which has the KiCad layout; the links under Design files point to each one.

Can I use the NeuroBot design in my own project?

Yes, under the terms of its MIT license, which viktorvano chose for the repository.

Can I test firmware for the NeuroBot without the hardware?

Yes. HardLabs builds a simulation of the board from its netlist and BOM, so you can run and debug STM32 firmware against it before you order a PCB.

Similar boards