Hardware Podcasts

S5E48 Kordel France | Olfactory AI

Being an Engineer · 29 Nov 2024 · 49m · Episode 48

What this episode covers

Kordel France, an AI architect currently working at Toyota, discusses the nascent field of machine olfaction, or teaching robots to smell. He explains that while applications in automotive HVAC, aerospace leak detection, and quality control are promising, reliable consumer-grade olfactory AI is likely 10 years away due to a lack of data standards and complex aerodynamic challenges. France highlights the difficulty of detecting air molecules amidst environmental noise and argues for the need to integrate AI with precise mechanical hardware to create robust sensors.

Most relevant to

early-stage companies

Topics

Mentioned

Companies
Toyota, Boston Dynamics, Neuralink, Tesla, Pipeline Design & Engineering
Products
ChatGPT
Also
Elon Musk

Related episodes from other shows

Other shows on the same ground, closest first.

  • IoT For All Podcast · 26m

    Detecting Scents & Smells With IoT Sensors | Altered Carbon's Ali Rohafza

    Ali Rohafza, CEO and co-founder of Altered Carbon, explains how his company developed digital vapor detection sensors that replicate the human nose to identify and fingerprint smells. He details the technology's origin at the Bristol Robotics Laboratory, the use of graphene-based sensors for low-power operation, and the challenge of creating standardized testing methods for mass production. Rohafza discusses key applications in food spoilage detection, industrial safety, and potential future uses in agriculture and medical diagnostics.

    Sensors & measurement in productsMaterials & manufacturing processes
    7 chapters

  • EE Times Current · 37m

    Machine Vision: Seeing is Believing

    Jeff Bier, president of BDTI and founder of the Edge AI and Vision Alliance, discusses the evolution of machine vision from constrained manufacturing environments to complex natural settings. He explains how the industry shifted from handcrafted algorithms to data-driven deep learning, enabling applications like mask detection and elder care monitoring. Bier also highlights the necessity of sensor fusion, such as combining vision with radar or LiDAR, to overcome environmental limitations like fog or darkness.

    AI & machine learningSensors & measurement in products
    7 chapters

  • The Circuit · 40m

    Episode 49: CES Semiconductor Trends, Where was AI? 2024 Outlook

    Ben Bajarin and Jay Goldberg analyze CES 2024, noting a muted presence of AI in major vendor booths compared to the hype-filled Eureka Park. They discuss how semiconductor companies like Nordic Semi and Intel are re-architecting roadmaps for on-device AI and sensor fusion, while John Deere demonstrates advanced autonomous compute without marketing it as AI. The hosts conclude that 2024 will be a cyclically good year for semiconductors, but significant consumer AI hardware shifts are delayed until 2025-2026 due to long silicon design cycles.

    Chips, FPGAs & semiconductorsAI & machine learning
    7 chapters

  • EE Times Current · 19m

    CES 2019 Special: Day 1 recap with Brian Santo, Editor-in-Chief of EDN

    Brian Santo, Editor-in-Chief of EDN, joins David Finch to recap Day 1 of CES 2019, highlighting innovations from Solari’s Bluetooth-enabled lightsabers to wearable breast pumps from Willow and LV. Santo discusses the proliferation of small robots like QT and Groove X, while noting the current limitations of autonomous vehicle AI, citing a Tesla collision with a robot as evidence of sensor and processing challenges. The conversation covers the technical trade-offs in 5G infrastructure, specifically millimeter-wave propagation issues, and the enabling technologies required for future autonomous driving.

    Robotics & autonomyIndustrial & consumer product design
    5 chapters

  • EE Times Current · 24m

    Self-Driving Skeptic | Supercharged PCI | Sensors Everywhere | Edge AI

    EE Times editors report on CEA Letty's conference on edge AI, highlighting the European focus on local processing for data privacy and the debut of a Type 1 diabetes autonomous medical device. They also cover PCI-SIG's rapid development of Gen 6 PCI Express, noting the challenges of copper interconnects and board redesigns. Additionally, the episode discusses the hyper-fragmented sensor market at Sensors Expo and Colin Barnden's argument that Level 2+ driver assist systems are more viable for mass-market cars than fully autonomous vehicles.

    AI & machine learningPCB design & layout
    5 chapters

The summary, chapters and topics are generated from the episode’s audio by this directory, not written by Being an Engineer. The episode itself belongs to its publisher.