|
| ▲ | Jensson 14 hours ago | parent | next [-] |
| 1ms latency is more than fast enough, you probably have bigger latency than that between the cpu and the gpu. |
| |
| ▲ | Symmetry 12 hours ago | parent [-] | | We've got 10ms of latency between our brains and our hands along our nerve fibers and we function all right. |
|
|
| ▲ | UltraSane 4 hours ago | parent | prev | next [-] |
| The Figure robots use a two level control scheme with a fast LLM at 200Hz directly controlling the robot and a slow planning LLM running at 7Hz. This planning LLM could be very far away indeed and still have less than 142.8ms of latency. |
|
| ▲ | UltraSane 20 hours ago | parent | prev [-] |
| Latency would be kept low be keeping the compute nearby. One 1U or 2U server per robot would be reasonable. |
