# 187: Self-Driving Arm (Repeat)

- Show: [Embedded.fm](https://hardwarepodcasts.com/podcast/embedded-fm)
- Published: 2019-05-02
- Length: 1h 12m
- Episode: 187
- Page: https://hardwarepodcasts.com/podcast/embedded-fm/2019-05-02-187-self-driving-arm-repeat
- Listen: https://makingembeddedsystems.libsyn.com/187-self-driving-arm-repeat

## Summary

Patrick Pilarski, a Canada Research Chair in Machine Intelligence for Rehabilitation at the University of Alberta, discusses the development of smart prosthetic limbs that use machine learning to restore function for amputees. He explains how reinforcement learning allows prosthetics to learn from trial-and-error or by observing a user's healthy limb, addressing the challenge of mapping limited biological signals to complex robotic movements. Pilarski highlights the shift from traditional myoelectric controls to systems that predict user intent and context, such as using cameras to identify objects like soup or doorknobs to automate grip patterns.

## Chapters

- [0:06](https://hardwarepodcasts.com/podcast/embedded-fm/2019-05-02-187-self-driving-arm-repeat#t=6) Introduction and Guest Background
- [8:05](https://hardwarepodcasts.com/podcast/embedded-fm/2019-05-02-187-self-driving-arm-repeat#t=485) The Challenge of Controlling Smart Prosthetics
- [16:40](https://hardwarepodcasts.com/podcast/embedded-fm/2019-05-02-187-self-driving-arm-repeat#t=1000) Machine Intelligence vs. Artificial Intelligence
- [28:10](https://hardwarepodcasts.com/podcast/embedded-fm/2019-05-02-187-self-driving-arm-repeat#t=1690) Reinforcement Learning and Real-Time Adaptation
- [34:02](https://hardwarepodcasts.com/podcast/embedded-fm/2019-05-02-187-self-driving-arm-repeat#t=2042) Sensors, IoT, and Predictive Context
- [50:37](https://hardwarepodcasts.com/podcast/embedded-fm/2019-05-02-187-self-driving-arm-repeat#t=3037) User Preferences and Cybathlon Competition
- [1:03:46](https://hardwarepodcasts.com/podcast/embedded-fm/2019-05-02-187-self-driving-arm-repeat#t=3826) Getting Started with Robotics and ML

## Topics

- [Embedded firmware](https://hardwarepodcasts.com/topic/embedded-firmware)
- [AI & machine learning](https://hardwarepodcasts.com/topic/ai-and-machine-learning)
- [Sensors & measurement in products](https://hardwarepodcasts.com/topic/sensors)
- [Robotics & autonomy](https://hardwarepodcasts.com/topic/robotics-and-autonomy)
- [Medical & health devices](https://hardwarepodcasts.com/topic/medical-devices)

## Most relevant to

early-stage companies

## Mentioned

- University of Alberta (company)
- Alberta Machine Intelligence Institute (company)
- Weka (tool)
- OpenIA Gym (tool)
- Robotis (company)
- Coapt (company)
- Thalmic Labs (company)
- Myo (product)
- Cybathlon (other)

## Related episodes from other shows

- [Episode 90: Robotically Augmented People - Robot Talk Live](https://hardwarepodcasts.com/podcast/robot-talk/2024-06-21-episode-90-robotically-augmented-people-robot-talk-live) (Robot Talk)
- [184. Bionics Help Amputees Take Big Strides Forward](https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2024-07-23-184-bionics-help-amputees-take-big-strides-forward) (The Next Byte Podcast)
- [156. 2023 Recap & First Annual Saucies!🥫🍾](https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2024-01-09-156-2023-recap-first-annual-saucies) (The Next Byte Podcast)
- [155. Why Robotic Limbs Are Critical To The Human Race](https://hardwarepodcasts.com/podcast/the-next-byte-podcast/2024-01-02-155-why-robotic-limbs-are-critical-to-the-human-race) (The Next Byte Podcast)
- [Episode Twenty: Paul Dominick Baniqued](https://hardwarepodcasts.com/podcast/robot-talk/2022-10-07-episode-twenty-paul-dominick-baniqued) (Robot Talk)

## 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/2019-05-02-187-self-driving-arm-repeat. 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.