> My research goal is to train models using various hardware telemetry data with the hope that the models learn to interpret sensor inputs and control actuators based on the insights they glean from the sensor inputs. This research direction may open up exciting possibilities in fields such as automation, space, robotics and IoT, where L2E can play a pivotal role in bridging the gap between AI and physical systems.
This part was easy to miss but quite interesting, could you expand a bit here? What does L2E stand for?
thanks! I am still curious about the sensor inputs part.
I am trying to replace the 2.4ghz controller on my electric skateboard to make 0 to 5kmh and braking more pleasant and maybe use gyroscopes to do away with the controller altogether. What would tokens be in that case? Do you create a CAN style representation and feed that to the llm? What kind of throughput do you foresee being possible on which hardware?
In this case, I would ask the LLM to suggest an algorithm to minimize acceleration, jerk and snap based on the expected sensor input data, and then just implement that. Probably in memory on whatever runs the board.
Straightforward control problem of bringing the board from 5-0kmh smoothly?
Basic control theory will work better than AI here. The mathematical models used in control theory have been used in computing since at least the 50's (Kalman Filters). I suspect you won't have issues with computational power.
Figuring out exactly which model to use and how, may take some work. Also understanding control theory will allow you to do things like traction control, etc.
cat /dev/llama is not yet implemented. However we have a module to which you can give a prompt as parameter. It's buggy now.
Our goal is to write a proper kernel module to implement three things:
1. a character device
2. 1st backend is a LLMZip ie you write to say /dev/l2ezip, you get a compressed stream out
3. 2nd backend is a LLM, ie you write a prompt to say /dev/llama2, you get a completion back
So the 1st backend could be useful for compressed telemetry
The second backend could be useful for IoT LLM, or our ambitious plan of responding to telemetry, ie take action, such as control motor speed etc.
