Embedded.fm · 31 Dec 2021 · 1h 01m · Episode 397
Elecia White discusses her recent contract work on autonomous off-road trucks, where she implemented reinforcement learning for a safety system and debugged a critical color-space issue in TensorFlow. She also details her preparation for the second cohort of her Making Embedded Systems course, focusing on firmware update security and IoT management. Christopher White shares his experience building a radar data collection system using an NVIDIA Xavier and Python GUIs, and reflects on the importance of practice and exercise.
early-stage companies
Other shows on the same ground, closest first.
Hackaday editors Mike Szczys and Elliot Williams discuss new AI-on-the-edge hardware from BeagleBone and Google, the reverse engineering of a keytar firmware, and a critical analysis of Tesla's self-driving safety data. They also cover a custom smart lamp build, flexible PCB contests, and Elliot provides an audio tour of the Make Munich maker fair.
Hosts Minja, Costillo, and Alvaro review their year, highlighting conferences like Supercon and DEFcon, and discussing the rise of edge machine learning on microcontrollers like the Arduino Nano 33 BLE Sense. They detail hands-on reverse engineering experiences, including using an X-ray van from True View to inspect PCBs and learning chip decapping with John McMaster and Nanographs. The conversation also covers the implications of deep fakes, the repeal of net neutrality, and future goals involving KiCad PCB design and open-source robotics.
Ari Mahpour, an Embedded Systems Engineer at Rivian with prior experience at NASA JPL and Virgin Hyperloop, discusses the integration of AI and DevOps into embedded hardware development. He demonstrates 'vibe coding' with an Arduino using voice commands and LLMs, explaining how AI agents can autonomously write, compile, and test firmware. Mahpour also covers the challenges of managing hardware revisions, the importance of Model Context Protocol (MCP) for tool guardrails, and the future of AI in automated PCB design and testing.
Colin Barnden of Semicast Research discusses Tesla's Smart Summon feature, arguing it is a gimmick that beta-tests software on public roads and creates legal ambiguity regarding OEM liability for autonomous driving failures. Sanjay Gupta, VP of Engineering at NXP Semiconductors, explains how India has evolved from back-office support to leading global semiconductor design projects, including ADAS products, driven by government policy and deep engineering talent. Researchers at Deep Mind used reinforcement learning to train an AI to draw human faces, demonstrating that machines can identify facial features without labeled data, though the output is not considered true art due to a lack of intent.
Hosts Elliot Williams and Dan Maloney review a week of hacks, including Lawrence Trat’s open API integration for a Milo washing machine, Jeff Lau’s Bluetooth adapter for a 1993 Mitsubishi 3000 GT analog phone, and Stephen Gong’s autonomous F1/10th scale racing car using a Jetson and LiDAR. The episode also covers Denny’s microwave-powered forge using silicon carbide crucibles, Nicholas Depatri’s automated Gaggia espresso machine, and Patrick Williams’ social engineering of Bing Chat. Finally, they discuss the Vintage Computer Festival East and grid capacity issues with renewable energy.
The summary, chapters and topics are generated from the episode’s audio by this directory, not written by Embedded.fm. The episode itself belongs to its publisher.