187: Self-Driving Arm

Engineering & simulationCo-AP

A company called Co-AP uses pattern recognition, a form of machine learning, to map muscle contraction patterns to prosthetic limb movements, allowing users to control their limbs more intuitively and reliably than with traditional methods.

“There's a company … spun off a company called Co-AP … doing, essentially, uh, pattern recognition. So they're using a classification system that allows people to um, essentially deploy pattern recognition. That's what it's called, as a form of machine learning, in prosthetic limb control.”

Engineering & simulationWeka

The guest recommends using the Weka data mining toolkit to help engineers understand their sensor data and experiment with supervised learning methods without needing to write complex code from scratch.

“I usually point them in the direction of something like uh, Weka. It's the data mining toolkit from New Zealand. It's a free open source Java toolkit. It has almost every major sort of supervised learning, machine learning method that you might want to play with.”

Engineering & simulationOpenAI Gym

The guest suggests OpenAI Gym as a platform for students and engineers to try out reinforcement learning algorithms and get familiar with machine learning methods in a simulated environment.

“Open AI gym is another really great, great resource. Open AI gym is a new platform where you can try out things like reinforcement learning as well. My students have been using it, and it's really, really, um, pretty functional in a very, Quick amount of, in a quick ramp up cycle.”