# 534: I Think We'll Add a Head

- Show: [Embedded.fm](https://hardwarepodcasts.com/podcast/embedded-fm)
- Published: 2026-09-17
- Length: 1h 13m
- Episode: 534
- Page: https://hardwarepodcasts.com/podcast/embedded-fm/2026-09-17-534-i-think-well-add-a-head
- Listen: https://embedded.fm/episodes/534

## Summary

Aaed Musa, co-founder of the robotics startup Mecha and a popular YouTube creator, discusses his journey from 3D-printing servo robots in his parents' garage to designing advanced quadrupedal robots. He details the mechanical evolution from high-backlash servos to custom capstan drives using Dyneema DM20 rope, and explains how his startup uses NVIDIA Isaac Sim and reinforcement learning to train expressive, home-friendly robot dogs. Musa also shares insights on his YouTube storytelling process, the importance of industrial design in making robots approachable, and his vision for a platform-based home robot that bridges the gap between toys and industrial tools.

## Chapters

- [0:06](https://hardwarepodcasts.com/podcast/embedded-fm/2026-09-17-534-i-think-well-add-a-head#t=6) Introduction: Aaed Musa and Mecha
- [4:14](https://hardwarepodcasts.com/podcast/embedded-fm/2026-09-17-534-i-think-well-add-a-head#t=254) From Ares to CARA 2.0: Actuator Evolution
- [8:12](https://hardwarepodcasts.com/podcast/embedded-fm/2026-09-17-534-i-think-well-add-a-head#t=492) Capstan Drives and Dyneema DM20
- [11:17](https://hardwarepodcasts.com/podcast/embedded-fm/2026-09-17-534-i-think-well-add-a-head#t=677) Reinforcement Learning with NVIDIA Isaac Sim
- [19:56](https://hardwarepodcasts.com/podcast/embedded-fm/2026-09-17-534-i-think-well-add-a-head#t=1196) YouTube Storytelling and Video Production
- [32:40](https://hardwarepodcasts.com/podcast/embedded-fm/2026-09-17-534-i-think-well-add-a-head#t=1960) Self-Taught Engineering vs. Academic Theory
- [53:25](https://hardwarepodcasts.com/podcast/embedded-fm/2026-09-17-534-i-think-well-add-a-head#t=3205) Mecha's Vision for Home Quadrupeds
- [1:07:10](https://hardwarepodcasts.com/podcast/embedded-fm/2026-09-17-534-i-think-well-add-a-head#t=4030) Designing a Head and Biological Aesthetics

## Topics

- [Robotics & autonomy](https://hardwarepodcasts.com/topic/robotics-and-autonomy)
- [Materials & manufacturing processes](https://hardwarepodcasts.com/topic/materials-and-processes)
- [AI & machine learning](https://hardwarepodcasts.com/topic/ai-and-machine-learning)
- [Industrial & consumer product design](https://hardwarepodcasts.com/topic/industrial-design)
- [Creator business](https://hardwarepodcasts.com/topic/creator-business)

## Most relevant to

founders before launch, early-stage companies

## Mentioned

- Mecha (company)
- Dyneema DM20 (material)
- NVIDIA Isaac Sim (tool)
- OpenMV (tool)
- Boston Dynamics Spot (product)
- Sony AIBO (product)
- Ghost Robotics (company)
- Unitree Go2 (product)

## Related episodes from other shows

- [Robots Everywhere with Aaed Musa](https://hardwarepodcasts.com/podcast/the-amp-hour/2026-01-20-robots-everywhere-with-aaed-musa) (The Amp Hour)
- [Episode 109: Building robots at home - Dan Nicholson](https://hardwarepodcasts.com/podcast/robot-talk/2025-02-14-episode-109-building-robots-at-home-dan-nicholson) (Robot Talk)
- [Niels Jul Jacobsen, CEO, Capra Robotics; Spider-Man Robot Fail](https://hardwarepodcasts.com/podcast/the-robot-report-podcast/2022-06-17-niels-jul-jacobsen-ceo-capra-robotics-spider-man-robot-fail) (The Robot Report Podcast)
- [Editors Pick: Best Robots of CES 2023; Boston Dynamics Atlas video review](https://hardwarepodcasts.com/podcast/the-robot-report-podcast/2023-01-21-editors-pick-best-robots-of-ces-2023-boston-dynamics-atlas-video-review) (The Robot Report Podcast)
- [An Interview with James Bruton](https://hardwarepodcasts.com/podcast/the-amp-hour/2018-11-19-an-interview-with-james-bruton) (The Amp Hour)

## Citing this page

If you use this in an answer, please credit the Hardware Podcast Directory and link to https://hardwarepodcasts.com/podcast/embedded-fm/2026-09-17-534-i-think-well-add-a-head. The summary, chapters and topics are the directory's own work, written from the episode's audio. The episode itself, its title and its audio belong to Embedded.fm.