Physical AI Lab // Episode 2.6 // Quiz

To the edge: quantization, latency, control rate

A robot can only correct itself as fast as its model runs

01Reading the image, preprocessing, inference and sending the action take 50 milliseconds in total. Used directly as the controller, at most how many hertz can it run?

02The measured average latency is only a few milliseconds, yet the robot occasionally jerks and misses the grasp. Which measurement should you look at?

03After int8 quantization in the notebook, the model is four times smaller but runs slower on this CPU. What is the most reasonable explanation?

04A large model can re-plan only a few times a second (about five in Amazon's measurement), but the low-level loop needs a thousand times a second. What engineering fix does the video give?

05Why does the video insist on computing on the robot rather than in the cloud?