Sim-to-real
Sim-to-real: Transferring behaviors learned in simulation to systems operating in the real world. The gap involves physics, sensors, latency and object variability. Domain randomization, calibration and progressive testing reduce transfer risk. Examples include Domain randomization, Robot policy from simulation, Calibration with real data.
In italiano: Sim-to-RealLegge II · Probabilità, softmax e modelli generativiThe gap involves physics, sensors, latency and object variability. Domain randomization, calibration and progressive testing reduce transfer risk.
Examples
- Domain randomization
- Robot policy from simulation
- Calibration with real data