Hardware Podcasts

249. Harvard’s Smartwatch Makes You Run Faster & Safer

The Next Byte Podcast · 21 Jul 2026 · 21m

AI in practice: one real use of AI described

What this episode covers

The hosts discuss research from Harvard’s School of Engineering and Applied Sciences, led by Connor Walsh, Daniel Lieberman, and Lauren Baker, which uses low-cost inertial measurement units (IMUs) to estimate ground reaction forces and running biomechanics. They explain how machine learning models trained on these inexpensive sensors can predict braking and propulsion forces with high accuracy, allowing for real-time feedback on running form and injury risk without laboratory equipment. The conversation highlights the potential for democratizing gait analysis through affordable wearables, noting the system's ability to adapt to new users within just eight steps.

AI in practice

Where this conversation describes AI being used to build or deliver a product. Part of the AI in practice tracker.

Engineering & simulationworked within 8 steps for new runners

The researchers trained a machine learning model to predict ground reaction forces (braking and propulsion) using data from low-cost inertial measurement units (IMUs) worn on the hip and ankle, eliminating the need for laboratory-grade force plates.

“what they did is they trained a machine learning model to be able to predict the forces that an IMU is experiencing based off of its installation on a runner. … They found that this machine learning model was really, really good at predicting force from the IMU data alone.”

Speaker 1 · Hear it at 8:06

Most relevant to

makers and hobbyists

Topics

Mentioned

Companies
Mouser Electronics, Harvard School of Engineering and Applied Sciences
Products
Aura Ring, Whoop, Apple Watch, AirPods, Fitbit

Related episodes from other shows

Other shows on the same ground, closest first.

  • Embedded.fm

    27: You Are Blowing My Mind

    Ivo Stivoric, co-founder of Body Media (now part of Jawbone), discusses the shift from simple pedometers to multisensor wearable systems that fuse data from motion, skin temperature, and heat flux to provide accurate health insights and behavior modification. Sam Guilaume and David Rothenberg of Movea explain their indoor navigation algorithm, which uses smartphone inertial sensors for dead reckoning at ultra-low power, and their strategy to harden parts of the sensor fusion logic into ASICs for efficiency. Stephen Walsh of ISKN presents iSketchnote, a MEMS-based pen and paper digitizer that captures handwriting and sketches in real-time, highlighting its successful Kickstarter campaign and transition from prototype to manufacturing.

    Sensors & measurement in productsEmbedded firmware
    7 chapters

  • Embedded.fm · 55m

    65: Resonant Frequency of My Butt

    Dr. Junhao Hu and Sharif Kassatly, founders of Darma, discuss their optical sensor-based smart cushion designed to monitor posture, heart rate, and stress levels. They detail their experience in the Haxlr8r accelerator, the technical challenges of measuring heart rate variability through body movement, and their strategic decision to choose between Kickstarter and Indiegogo for their crowdfunding campaign. The episode also covers their advisory team, including NASA's Dr. Joan Vernikos, and their long-term vision for a 'smart health home.'

    Crowdfunding & preordersSensors & measurement in products
    7 chapters

  • Hard Tech Podcast · 1h 32m

    Alex Villanueva: Asteroid Mining, Virtual Apparel Fitting, Biomimicry Inspired Tech | Hard Tech Podcast #17

    Alex Villanueva, founder and CEO of Eclo, explains how his AI platform reduces apparel returns by predicting shoe fit through a smartphone foot scanner and user preferences. He details the technical challenges of capturing 3D foot data and the business insight that increasing conversion rates is more valuable to retailers than just reducing returns. Villanueva also reflects on his graduate research building biomimetic robotic jellyfish at Virginia Tech and his internship at NASA working on pulse plasma thrusters.

    Connected products & IoTAI & machine learning
    8 chapters

  • Hard Tech Podcast · 59m

    Julia Parker: AI To Talk To Animals, Horse Pain Detection, Equestrian Riding | Hard Tech Podcast #15

    Julia Parker, founder of Intuitive HorseWare, explains her technology for detecting pain in horses using sensors and AI, inspired by her 30 years as a farrier and a rescue horse named Beauty. She discusses how abnormal movement patterns indicate underlying issues, aiming to reduce the estimated 6.3 million cases of unnoticed pain in US performance horses. Parker details the use of accelerometers, gyroscopes, and magnetometers to create baselines for normal gait, allowing riders to address problems before they become chronic.

    Sensors & measurement in productsAI & machine learning
    9 chapters

  • The Robot Report Podcast · 1h 03m

    Jeremiah Robison from Cionic creates bionic clothing to help patients walk better

    Jeremiah Robison, founder and CEO of Psionic, explains how his daughter’s cerebral palsy diagnosis inspired the creation of the Psionic Neurosleeve, a bionic garment that uses functional electrical stimulation (FES) and surface EMG sensors to augment walking for patients with mobility impairments. Robison details the engineering challenges of replacing bulky exoskeleton motors with a non-invasive, wearable system that reads neural intent and delivers real-time stimulation to four major leg muscle groups. He discusses the company's journey from garage-based prototyping to receiving FDA clearance and selling out its initial founders program, highlighting the therapeutic benefits of reinforcing neural pathways rather than just providing passive assistance.

    Medical & health devicesPrototyping & iteration
    7 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.