AutoTech est un projet du Club de robotique INTech de Telecom SudParis et IMT Business School. Il a pour but de concevoir un véhicule autonome pour la compétition CoVAPSy.
Hat is an open-source printed circuit board by Association-INTech, from the Association-INTech/CoVAPSy repository on GitHub, published under the MIT licence. It is a 2-layer board of 66 × 58.7 mm with 47 parts on 78 nets, routed with 151 tracks and 3 vias.
It is built around the PCA9517D and BAT54S. Its parts include 22 resistors, 7 diodes and 1 IC. It belongs with the STM32 and AVR (ATmega, ATtiny) boards of this library.
AutoTech is a project from the INTech robotics club (Telecom SudParis and IMT Business School). Our goal is to design and build an autonomous vehicle for CoVAPSy (Course de Voitures Autonomes de Paris-Saclay) competition.
This repository contains the source code for our autonomous vehicle for the 2025 and 2026 competitions.
We chose to use a full Reinforcement Learning approach. We train an agent to drive the vehicle in a simulation of the race based directly on sensor inputs.
We train the AI model in parallel remote environments through nammed pipes connections between the main python script and the multiple webots instances.
Inside the simulations, each vehicle has access to data comming from a LiDAR and a camera.
We use uv for Python environment management. So if it's not already installed go check the official installation guide
Then, just uv sync to create the virtual environment and get all the dependencies.
# dependencies for AI training
uv sync --extra simu
# dependencies for AI inference on the Raspberry PI 5
uv sync --extra rpiNavigate to the simulator directory.
cd src/SimulateurRun the multi-process training script.
uv run launch_train_multiprocessing.pyThis will launch the Webots instances and begin the SB3 PPO training loop. All the checkpoints will be in the checkpoints directory. At every checkpoint, a compiled ONNX model will be stored as model.onnx.
To change the parameters of the simulation, just modify the config.py file.
(WIP)
For detailed information on architecture, hardware specifics and technical choices, please refer to the INTech wiki.
(Note: The Wiki is currently private and reserved to INTech members)
libcap-dev python3-libcamera
This project is distributed under the MIT License. See the Licence file for details.
| Qty | Value | Footprint | References |
|---|---|---|---|
| 19 | 560 | Resistor_SMD:R_1206_3216Metric_Pad1.30x1.75mm_HandSolder | R1, R2, R3, R20, R24, R51, R52, R53, R54, R57, R58, R71, R72, R73, R74, R75 +3 |
| 6 | Jumper_3_Open | Connector_PinHeader_2.54mm:PinHeader_1x03_P2.54mm_Vertical | J_BUZZER0, J_DIR0, J_PROP0, J_RX0, J_TX0, J_VDD0 |
| 4 | LEDSML1206 | Diode_SMD:D_1206_3216Metric_Pad1.42x1.75mm_HandSolder | LED1, LED2, LED3, LED4 |
| 3 | BAT54S | Package_TO_SOT_SMD:SOT-23 | D20, D22, D24 |
| 2 | @HOLE0, @HOLE1 | ||
| 2 | 4.7k | Resistor_SMD:R_1206_3216Metric_Pad1.30x1.75mm_HandSolder | R5, R6 |
| 2 | Conn_01x04 | Connector_JST:JST_XH_B4B-XH-AM_1x04_P2.50mm_Vertical | X_UART_MCU0, X_UART_RPI0 |
| 1 | 1k | Resistor_SMD:R_1206_3216Metric_Pad1.30x1.75mm_HandSolder | R4 |
| 1 | ARDUINO_NANO_STM32_NUCLEO | Module:Arduino_Nano | X_ARDUINO_NANO_OU_STM32 |
| 1 | CONN_ALIM_3TROUS | CONN_ALIM_3TROUS | X_ALIM0 |
| 1 | Conn_01x04 | Connector_Molex:Molex_KK-254_AE-6410-04A_1x04_P2.54mm_Vertical | X_I2C0 |
| 1 | Conn_02x05 | Connector_IDC:IDC-Header_2x05_P2.54mm_Vertical | X_SIGNAUX0 |
| 1 | Conn_02x20 | Connector_PinHeader_2.54mm:PinHeader_2x20_P2.54mm_Vertical | Raspberry_Pi_2/3/4/5 |
| 1 | PCA9517D | PCA9517D_112:SOIC127P600X175-8N | U1 |
| 1 | TestPoint | TestPoint:TestPoint_Loop_D3.50mm_Drill0.9mm_Beaded | J_GND0 |
| 1 | ~ | Connector_Molex:Molex_KK-254_AE-6410-08A_1x08_P2.54mm_Vertical | X_MEZZANINE0 |
It measures 66 × 58.7 mm and has 2 copper layers, 1.6 mm thick.
47 parts, built around the PCA9517D and BAT54S. The full list of its parts is on this page, with links to each part's symbol and footprint where PCBKit's library has them.
From the Association-INTech/CoVAPSy repository on GitHub, at the commit this page was made from: the board is docs/Hardware/Hat/Hat.kicad_pcb and its schematic docs/Hardware/Hat/Hat.kicad_sch. PCBKit opens the board in the browser, with nothing to install.
Its repository publishes it under the MIT licence: you may reuse it on that licence's terms (keep the author's notice, and for a copyleft licence share your changes alike).
BioMEMS/OpenDMS
Hardware developed in Prof. Cristina Davis' Bioinstrumentation and BioMEMS laboratory. Publications (i.e. articles, book chapters, etc.) that use this hardware are required to cite the related article…
Ardumower/ardumower
Develop an open source robotic lawn mower (HW+SW reference platform)
ataradov/usb-sniffer
Low-cost LS/FS/HS USB sniffer with Wireshark interface
Twisted-Fields/rp2040-motor-controller
A dual channel brushless motor controller based on the RP2040 microcontroller, designed in Kicad.
corygrant/dingoPDM
Hardware - dingoPDM is an open source, affordable automotive PDM (Power Distribution Module). Pre-assembled and tested units are available or the design can be used to build a DIY version.
