Comment by YuechenLi
5 hours ago
Running a full LLM to actuate a robot is way too heavy, the minimum latency they can get down to is probably 1-2 seconds even with powerful GPUs, which is not very useful for practical robotics applications.
Machine vision should definitely be handled by ML, but motion actuation should be relegated in the realm of traditional PID style linear/nonlinear control. Again, the tech is cool, but the practical usefulness of using a full LLM as a controller will probably run into hardware limitations.
On latency: that is true now but likely false in the near future. There is so much potential left over for optimizing inference further.
On PID: the field has been stuck trying to do analytical/optimization-based control for decades, and end-to-end control has shown incredible performance (e.g., SoTA cost of transport in legged locomotion) and robustness (e.g., not falling over when stepping on a pile of leaves) - while being far scalable (in terms of how fast it is to get a new robot up and running). Which is not to say it's perfect but it seems like it's a step in the right direction.
Better yet, companies like Physical Intelligence are doing good with hierarchical ("fast-slow") architecture to address both the intelligence and latency fronts.
AFAIK NVidia has a VLA running on their chips with 2B params at 10Hz. They’ve openly published a .5B model running at 10Hz
10Hz is still a 0.1s of latency, which doesn't seem like a lot until you realize that an Arduino typically runs at 16 Mhz, which is literally a million times faster than running a full LLM.
So, yeah, for complex reasoning and sensory processing, LLMs are the correct choice, and Gemini is especially strong at spatial reasoning over ChatGPT/Claude. But for actual motion/actuation? LLMs are the wrong tool for the job, probably easier to have LLMs program a reusable workflow in a script for repeated tasks instead of invoking LLMs after the first time.
For this operating domain the latency comparison is human reaction time and not arduino reaction time.
Also the process that’s running at 16MHz is not the same as a full VLA. VLA is much more expressive. You think the processor that is running the VLA system is running at 10Hz or some GHz?
16 MHz is the chip's clock speed. Arduino PID is more like 100 Hz to 1 kHz.
Human deliberate movement runs around 2-10 Hz I think.