# 234: The Good Word About AI

- Show: [Embedded.fm](https://hardwarepodcasts.com/podcast/embedded-fm)
- Published: 2018-02-14
- Length: 50m
- Episode: 234
- Page: https://hardwarepodcasts.com/podcast/embedded-fm/2018-02-14-234-the-good-word-about-ai
- Listen: https://makingembeddedsystems.libsyn.com/234-the-good-word-about-ai

## Summary

Dusty Franklin, a developer evangelist at NVIDIA, discusses the Jetson TX2, a low-power embedded module designed to bring AI and computer vision to edge devices like robots and drones. He explains how the platform's GPU enables parallel processing for tasks such as autonomous navigation, object detection, and reinforcement learning, often using simulation environments like ROS Gazebo to train agents safely. Franklin also details the 'Two Days to a Demo' tutorial, which guides developers through deploying and retraining neural networks using NVIDIA's TensorRT and DIGITS tools, and mentions the Redtail Project as an example of autonomous drone navigation.

## Chapters

- [0:06](https://hardwarepodcasts.com/podcast/embedded-fm/2018-02-14-234-the-good-word-about-ai#t=6) Introduction and Lightning Round
- [5:23](https://hardwarepodcasts.com/podcast/embedded-fm/2018-02-14-234-the-good-word-about-ai#t=323) Jetson TX2 Hardware and Power Profile
- [9:45](https://hardwarepodcasts.com/podcast/embedded-fm/2018-02-14-234-the-good-word-about-ai#t=585) GPU Parallel Processing and Computer Vision
- [11:21](https://hardwarepodcasts.com/podcast/embedded-fm/2018-02-14-234-the-good-word-about-ai#t=681) AI, Deep Learning, and Reinforcement Learning
- [21:22](https://hardwarepodcasts.com/podcast/embedded-fm/2018-02-14-234-the-good-word-about-ai#t=1282) Simulation and Training Workflows
- [24:28](https://hardwarepodcasts.com/podcast/embedded-fm/2018-02-14-234-the-good-word-about-ai#t=1468) Two Days to a Demo Tutorial and Tools
- [33:45](https://hardwarepodcasts.com/podcast/embedded-fm/2018-02-14-234-the-good-word-about-ai#t=2025) Redtail Project and Autonomous Drones
- [34:32](https://hardwarepodcasts.com/podcast/embedded-fm/2018-02-14-234-the-good-word-about-ai#t=2072) GTC Conference and Developer Challenge

## Topics

- [Embedded firmware](https://hardwarepodcasts.com/topic/embedded-firmware)
- [Microcontrollers & dev platforms](https://hardwarepodcasts.com/topic/microcontrollers-and-platforms)
- [AI & machine learning](https://hardwarepodcasts.com/topic/ai-and-machine-learning)
- [Robotics & autonomy](https://hardwarepodcasts.com/topic/robotics-and-autonomy)
- [PCB design & layout](https://hardwarepodcasts.com/topic/pcb-design)

## Most relevant to

early-stage companies

## Mentioned

- NVIDIA (company)
- Jetson TX2 (product)
- Jetson TX1 (product)
- Connect Tech (company)
- Redtail Project (product)
- TensorRT (tool)
- DIGITS (tool)
- ROS (tool)
- Gazebo (tool)
- Alex Net (product)
- Google Net (product)
- ResNet (product)
- OpenCV (tool)
- Caffe (tool)
- Torch (tool)
- TensorFlow (tool)
- PX4 (product)
- Pixhawk (product)
- Udacity (company)
- NVIDIA GPU Technology Conference (other)

## Related episodes from other shows

- [Ep009: On the Edge of AI, Comment Your Code, Big Big Wheels, and Makers of Munich](https://hardwarepodcasts.com/podcast/hackaday-podcast/2019-03-08-ep009-on-the-edge-of-ai-comment-your-code-big-big-wheels-and-makers-of-munich) (Hackaday Podcast)
- [AI & Computer Vision’s Role in IoT | Drover AI's Alex Nesic](https://hardwarepodcasts.com/podcast/iot-for-all-podcast/2022-07-21-ai-computer-visions-role-in-iot-drover-ais-alex-nesic) (IoT For All Podcast)
- [NVIDIA GTC24 and R-24 recap](https://hardwarepodcasts.com/podcast/the-robot-report-podcast/2024-03-22-nvidia-gtc24-and-r-24-recap) (The Robot Report Podcast)
- [AI at the Edge: Justin Schneck on the Future of Embedded Devices](https://hardwarepodcasts.com/podcast/over-the-air/2025-05-29-ai-at-the-edge-justin-schneck-on-the-future-of-embedded-devices) (Over the Air)
- [Episode Forty-Two: Thom Kirwan-Evans](https://hardwarepodcasts.com/podcast/robot-talk/2023-03-24-episode-forty-two-thom-kirwan-evans) (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/2018-02-14-234-the-good-word-about-ai. 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.