Hacker News

thunderbong
Model Predictive Control in the Browser with WebAssembly garethx.com

mjburgess11 hours ago

I'd be interested, if any one had suggestions, on MPC applied to ML/AI systems -- it seems this is an underserved technique/concern in MLEng, and I'd expect to see more on it.

lagrange776 hours ago

There is a big overlap between Optimal Control and Reinforcement Learning, in case you didn't know.

Also Steve Brunton does a lot on the interface between control theory and ML on his channel: https://www.youtube.com/channel/UCm5mt-A4w61lknZ9lCsZtBw/pla...

szvsw5 hours ago

Another thing to keep in mind is that having AI/ML surrogates which can evaluate expensive functions faster can also be integrated as an information source in model predictive control algorithms.

lagrange774 hours ago

Exactly. ML models such as autoencoders can also be used for reduced order modeling / dimensionality reduction e.g. for MPC of fluid systems.

currymj5 hours ago

there's a lot of work in the broad area. most of it doesn't engage with the classical control theory literature (arguably it should).

some keywords to search for recent hot research would be "world model", "decision transformer", "active inference", "control as inference", "model-based RL".

gxcode10 hours ago

Author of the post here - happy to answer any questions.

beltranaceves9 hours ago

Great job! I'm working in a similar blog post and it was fun seeing how you approached it. I was surprised the wasm implementation is fast enough, I was even considering writing webGpu compute shaders for my solver

philzook10 hours ago

Beautiful stuff, great post!

gxcode10 hours ago

Thank you, really appreciate that.

HammadB2 hours ago

I've taken the linked Russ Tedrake class and have to say I loved this. Please make more!

klowrey12 hours ago

Here's a (hacky) demo of MPC using MuJoCo in the browser: https://klowrey.github.io/mujoco_wasm/

I hacked it using MPPI and it only works on the cartpole model so as to not have to dwell in Javascript too long; just click the 'MPPI Controller' button and you can perturb the model and see it recover.

tantalor11 hours ago

I love this kind of stuff because it seems like a roughly equal blend of art, science, and engineering.

hn-front (c) 2024 voximity
source