Robot Talk · 21 Jun 2024 · 51m · Episode 90
Milia Hasbani of Imperial College London, Benjamin Metcalfe of the University of Bath, and Dani Clode of Cambridge University discuss robotic prosthetics and human augmentation. Hasbani explains her active prosthetic arm research using EMG and computer vision to select grasp types, while Metcalfe details a hybrid exoskeleton combining robotic support with functional electrical stimulation for rehabilitation. Clode presents her 'Third Thumb' and the Alternative Limb Project, exploring neuroplasticity, embodiment, and the ethical implications of augmenting able bodies.
Where this conversation describes AI being used to build or deliver a product. Part of the AI in practice tracker.
Engineering & simulation
A camera mounted on a prosthetic hand uses computer vision to analyze the object in front of it and automatically selects the most appropriate grasp type, reducing the manual effort required from the user to cycle through options.
“what we've done is we added a camera. … that looks at the object in front of it and decides potentially, which is the most appropriate grass type to use, based on which part of the object it's looking at.”
Speaker 2 · Hear it at 3:31
Engineering & simulation
Machine learning algorithms process EMG signals and environmental data to assess user intention and make decisions for controlling the prosthetic, integrating sensory input with movement commands.
“Similar to how in my research we're using camera and using human intention. So there's a lot of machine learning and AI that goes into that. And I can see us moving forwards and integrating different kinds of senses. … and making decisions based on that is technically AI…”
Speaker 2 · Hear it at 35:58
Engineering & simulation
AI is used to adapt and learn over time to changes in the interface between the technology and the human, helping to translate lab-optimized brain-computer interfaces into usable home or field environments.
“where we're seeing, I think, the real benefit of AI is in being able to adapt and to learn over time changes to that interface between the technology and the human being.”
Speaker 3 · Hear it at 35:05
early-stage companies
Other shows on the same ground, closest first.
Hosts Daniel and Forbode discuss research from MIT’s Extreme Bionics Lab, led by Professor Hugh Herr and postdoc Hung Yun Song, on a new surgical technique called Agonist-Antagonist Myoneural Interface (AMI). The AMI surgery reconnects opposing muscle groups in the residual limb to restore neural feedback, allowing amputees to control robotic prosthetics with their own nervous system. The hosts highlight clinical trials showing that AMI patients achieved natural gait, obstacle navigation, and walking speeds comparable to non-amputees, significantly improving quality of life and reducing phantom pain.
Hosts Daniel and Forbode discuss research from EPFL on controlling a third robotic limb using diaphragm movements to augment human capability without interfering with natural motor functions. They explore the cognitive load, neuroplasticity, and potential applications in manufacturing and emergency response, noting that users adapted to the control scheme intuitively. The conversation also touches on future control schemes like ear wiggling and the broader implications of human-machine integration.
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.
Hosts Daniel and Forbode of The Next Byte Podcast present their 1st annual 'Saucies' awards, reviewing their top episodes from 2023. They highlight EPFL's technology allowing amputees to feel warmth in prosthetic hands, Machina's robotics for sheet metal forming, and a University of Michigan/Copenhagen Business School study on keeping humans in the AI loop. The hosts also discuss an MIT implantable diabetes device and smart retail technologies from Wevolver, while outlining goals for more in-person interviews and multi-channel growth in 2024.
Patrick Pilarski, a Canada Research Chair in Machine Intelligence for Rehabilitation at the University of Alberta, discusses the development of smart prosthetic limbs that use machine learning to restore function for amputees. He explains how reinforcement learning allows prosthetics to learn from trial-and-error or by observing a user's healthy limb, addressing the challenge of mapping limited biological signals to complex robotic movements. Pilarski highlights the shift from traditional myoelectric controls to systems that predict user intent and context, such as using cameras to identify objects like soup or doorknobs to automate grip patterns.
The summary, chapters and topics are generated from the episode’s audio by this directory, not written by Robot Talk. The episode itself belongs to its publisher.