Hardware Podcasts

196. Saving America’s Collapsing Infrastructure

The Next Byte Podcast · 15 Oct 2024 · 15m

What this episode covers

Hosts Daniel and Forbode discuss research from EPFL on using AI to detect cracks in America's aging infrastructure, specifically focusing on railroads and bridges. They explain how a new 'explainable AI' method reduces labeling effort by 90% compared to traditional pixel-by-pixel classification, allowing for continuous monitoring via instrumented rail cars or potentially buses. The hosts highlight the shift from subjective, costly manual inspections to a complementary model where automation flags issues for human experts to verify.

Most relevant to

makers and hobbyists

Topics

Mentioned

Companies
EPFL, Uber, Lyft
Products
Google Maps

Related episodes from other shows

Other shows on the same ground, closest first.

  • Robot Talk · 34m

    Episode 76: Robots on the railways - Andrew Starr

    Andrew Starr, Professor of Maintenance Systems at Cranfield University, discusses the application of robotics in industrial maintenance and railway inspection. He details his early work at Ford monitoring car assembly robots for positioning errors and component degradation, highlighting the limitations of pure data-driven AI in predicting physical failures like corrosion. Starr then describes the development of autonomous railway inspection robots, from small-scale Arduino models to a full-sized Clearpath Warthog UGV and a retrofitted proprietary track trolley, emphasizing the challenges of GPS denial in tunnels and the necessity of data fusion.

    Robotics & autonomyDebugging & failure analysis
    5 chapters

  • IoT For All Podcast · 22m

    How Computer Vision Ensures Grid Reliability | Noteworthy AI's Chris Ricciuti | Internet of Things Podcast

    Chris Ricciuti, Founder and CEO of Noteworthy AI, explains how the company uses vehicle-mounted smart cameras and edge AI to help electric utilities inspect the grid at scale. He details the transition from manual binocular inspections to automated computer vision, highlighting challenges like aging infrastructure, extreme weather, and increased demand from EVs and data centers. Ricciuti describes real-world applications, including identifying deteriorating wood poles and accelerating storm damage assessments to reduce restoration times from hours to minutes. The conversation covers the necessity of high-quality data for training models across varying environmental conditions and advises utilities to start with defined, high-ROI use cases rather than seeking silver bullets.

    Connected products & IoTAI & machine learning
    8 chapters

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