Hardware Podcasts

229. Teaching Robots to Play Badminton

The Next Byte Podcast · 23 Sept 2025 · 15m

What this episode covers

The hosts discuss ETH Zurich's development of a quadruped robot playing badminton, highlighting the integration of Anymal robots and DINA robotic arms. They explain how this system uses a single reinforcement learning control policy to coordinate leg movement and arm swinging in real-time, stress-testing perception and planning capabilities. The episode connects this research to practical applications in surgical robotics, search and rescue, and collaborative manufacturing (cobots), emphasizing the transition from academic theory to industrial practice.

Most relevant to

early-stage companies

Topics

Mentioned

Companies
Mouser Electronics, ETH Zurich, Machina
Products
Anymal, DINA

Related episodes from other shows

Other shows on the same ground, closest first.

  • The Robot Report Podcast · 1h 07m

    ANYbotics ANYmal quadruped with Enzo Wälchli

    Enzo Wälchli, Chief Commercial Officer at ANYbotics, discusses the commercialization and North American expansion of the ANYmal quadruped robot, an explosion-proof inspection platform spun out of ETH Zurich. Wälchli explains how the robot’s ATEX certification and autonomous capabilities allow it to operate safely in hazardous oil, gas, and chemical environments, performing predictive maintenance tasks like thermal scanning and gauge reading. The conversation highlights the shift from novelty to industrial utility, emphasizing the robot's ability to work autonomously in extreme conditions where human access is dangerous or costly.

    Robotics & autonomyScaling production
    10 chapters

  • The Robot Report Podcast · 1h 18m

    Practical Applications of Embodied AI and Humanoid Robots

    Dr. Russ Tedrake of Toyota Research Institute and Scott Kuindersma of Boston Dynamics discuss their collaboration to integrate TRI's large behavior models into the Atlas humanoid robot, focusing on using imitation learning and data to enable general-purpose manipulation skills. The episode also covers the FIRA 2024 ag-robotics event, highlighting Advanced Farms' apple-harvesting robot, the Reservoir Farms incubator, and new ventures like Rotate 8 and Blue White's autonomous tractor solutions.

    Robotics & autonomyAI & machine learning
    7 chapters

  • Embedded.fm · 1h 13m

    534: I Think We'll Add a Head

    Aaed Musa, co-founder of the robotics startup Mecha and a popular YouTube creator, discusses his journey from 3D-printing servo robots in his parents' garage to designing advanced quadrupedal robots. He details the mechanical evolution from high-backlash servos to custom capstan drives using Dyneema DM20 rope, and explains how his startup uses NVIDIA Isaac Sim and reinforcement learning to train expressive, home-friendly robot dogs. Musa also shares insights on his YouTube storytelling process, the importance of industrial design in making robots approachable, and his vision for a platform-based home robot that bridges the gap between toys and industrial tools.

    Robotics & autonomyMaterials & manufacturing processes
    8 chapters

  • The Robot Report Podcast · 1h 09m

    Editors Pick: Best Robots of CES 2023; Boston Dynamics Atlas video review

    Hosts Steve Crowe and Mike Oitzman review the new Boston Dynamics Atlas video, highlighting its use of simulation and model predictive control to achieve complex athletic maneuvers. Oitzman then recaps his trip to CES 2023, featuring interviews with Dan Haddick of Aeolus Robotics about their Gen 2 humanoid service robot and Tony Crisp of Robosen regarding their programmable Optimus Prime toy. The episode concludes with a discussion on recent industry layoffs and an interview with Paul Mitchell, founder of the IAC autonomous car race, about the event's evolution.

    Robotics & autonomyEmbedded firmware
    6 chapters

  • Embedded.fm · 1h 12m

    187: Self-Driving Arm

    Patrick Pilarski, a Canada Research Chair at the University of Alberta, discusses his work on smart prosthetic limbs that use machine intelligence to bridge the gap between limited biological signals and complex robotic actuators. He explains how reinforcement learning allows prostheses to learn from trial and error in real-time, using techniques like 'prosthetic falconry' where a robotic limb learns by observing a user's healthy biological arm. Pilarski highlights the shift from simple myoelectric controls to systems that predict user intent and context, such as using cameras to identify objects like soup or doorknobs to pre-shape grips. He also outlines accessible tools for engineers, including Weka, OpenIA Gym, and Robotis Dynamixel servos, to get started with reinforcement learning robotics.

    Embedded firmwareRobotics & autonomy
    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.