Hardware Podcasts

53. Mind-Control and Bug-Like Robots

The Next Byte Podcast · 18 Jan 2022 · 25m

What this episode covers

Daniel Farbod and Daniel discuss brain-computer interfaces from EPFL, explaining how inverse reinforcement learning allows users to control robotic arms with just 3-5 iterations by providing error signals rather than direct control commands. They then cover MIT's development of soft, bio-inspired artificial muscles for bug-sized robots, which use layered electrodes and elastic materials to achieve flight times over 20 seconds for robots under one gram, addressing durability and power constraints of traditional rigid actuators.

Most relevant to

makers and hobbyists

Topics

Mentioned

Companies
Mouser Electronics, EPFL, Neuralink, Cyber Foundation, MIT
Also
Neil Harbison

Related episodes from other shows

Other shows on the same ground, closest first.

  • Robot Talk · 44m

    Episode Seventeen – Bioinspired Robots: learning from nature

    Valentina Lo Gatto, a PhD student at the Bristol Robotics Lab, explains her jellyfish-inspired soft robot and salt-inspired colony robots designed for exploring subsurface oceans on moons like Europa. David Hardman, a PhD student at the University of Cambridge, discusses bio-inspired soft sensors and biodegradable gelatin-based materials for agricultural and medical applications. Adrian Thomas, founder of Animal Dynamics, describes how his company uses bio-inspiration to design the 'Stork' cargo drone and 'Skeeter Dragonfly' surveillance drone, focusing on aerodynamic efficiency and control bandwidth derived from animal flight.

    Robotics & autonomyMaterials & manufacturing processes
    8 chapters

  • Robot Talk · 20m

    Episode Twenty-Seven: Simon Wanstall

    Simon Wanstall, a PhD student at the Edinburgh Centre for Robotics and R&D engineer at TouchLab, discusses his work on soft robotic prosthetics and bio-inspired design. He explains how current myoelectric arms are heavy and slow due to hard materials, and details his development of rapid-manufacture strain sensors using laser-etched graphene and silicone to improve sensory feedback. Wanstall also describes Wayne, a bio-inspired soft robot inspired by ragworms, and his industrial placement at TouchLab creating e-skin technologies like the Eidermis and triaxial shear sensors for hazardous environment robotics.

    Medical & health devicesSensors & measurement in products
    8 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

  • Robot Talk · 28m

    Episode 96: Soft robots in medicine and healthcare - Maria Elena Giannaccini

    Maria Elena Giannaccini, a lecturer in robotics at the University of Aberdeen, discusses her research into soft and bio-inspired robotics for healthcare applications. She details the development of a wearable rehabilitation device for stroke survivors that uses decoupled soft actuators to allow natural elbow movement, addressing the challenges of nonlinear control and user variability. Giannaccini also highlights her earlier work on an artificial larynx and the use of soft robots to test biological theories, such as those regarding octopus arm mechanics.

    Robotics & autonomyMaterials & manufacturing processes
    5 chapters

  • Robot Talk · 20m

    Episode 153: Origami-inspired robots - Chenying Liu

    Chenying Liu, a Junior Research Fellow at the University of Oxford, explains how embedding intelligence into robot bodies through geometry and materials enhances autonomy. She details the design of an origami-inspired robotic gripper that uses mechanical bifurcation to achieve eight grasping modes with only two motors, and discusses a reconfigurable millipede robot for disaster rescue. Liu also explores unconventional materials, including inflatable fabrics for wearables and living muscle cells to power hybrid robots, aiming to reduce computational load and increase resilience.

    Robotics & autonomyMechanical engineering
    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.