HardLabs

AI TARS

fcolapicchioni·AI_TARS·hardware/electronics/tars/tars.kicad_sch

AI TARS

About the AI TARS PCB

AI TARS is an open source Raspberry Pi PCB design by fcolapicchioni, published on GitHub under the CC-BY-NC-4.0 license. It is a board, with 7 components from 4 distinct parts.

Its main chip is the ComputeModule5-CM5, from the Raspberry Pi family. By type, the board carries 3 modules, 2 ICs and 1 battery holder.

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

From the project

Walking robot with a fully offline voice AI: LLM, speech-to-text and text-to-speech all run on-board an NVIDIA Jetson — no cloud, no API keys. Inspired by Interstellar's TARS, with custom CAD and a rack-and-pinion gait. Maturità 2025.

Federico Colapicchioni · Liceo Cantonale di Mendrisio · February – December 2025 Lavoro di Maturità (final-year research project), Mathematics & Computer Science

- What it is - The robot at a glance - How it works - The AI pipeline - The motion system - Hardware - Mechanical design and manufacturing - Engineering problems and how I solved them - Repository structure - Running it - What I learned - Roadmap - Credits and license

AI TARS bill of materials (BOM)

7 components, 4 distinct parts.

QtyPartRefs
2
~
U1, U2
3
Motor_Servo
M1, M2, M3
1
3S 12,6V
BT1
1
ComputeModule5-CM5
Module1

AI TARS design files

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

AI TARS: common questions

What microcontroller does the AI TARS use?

The AI TARS is built around the ComputeModule5-CM5, from the Raspberry Pi family.

How many components are on the AI TARS?

7 components, from 4 distinct parts. The full bill of materials is listed on this page.

Where can I download the AI TARS design files?

From the fcolapicchioni/AI_TARS repository on GitHub, which has the schematic; the links under Design files point to each one.

Can I use the AI TARS design in my own project?

It is published under CC-BY-NC-4.0, which limits how it may be reused; read the license before building on it.

Can I test firmware for the AI TARS without the hardware?

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

Similar boards