Real-time chunking (RTC) is an inference-time algorithm for executing action chunks from diffusion- or flow-based policies without pauses or jumps at chunk boundaries. It was introduced by Black, Galliker and Levine of Physical Intelligence in "Real-Time Execution of Action Chunking Flow Policies" (2025).
The policy starts generating the next chunk while the robot is still executing the current one. Because of inference latency, the first actions of the new chunk will already have been executed by the time it arrives. RTC "freezes" those actions to match the previous chunk and treats the rest as an inpainting problem, guiding the denoising so that the new chunk joins the old one smoothly. It needs no retraining. The paper reports precise tasks such as lighting a match succeeding "even in the presence of inference delays in excess of 300 milliseconds, corresponding to more than 30% of the model's prediction horizon".
LeRobot v0.6.1 documents RTC for flow-matching policies such as π0, π0.5 and SmolVLA. Measurements in this matrix record it with an rtc_enabled flag, because the same model on the same hardware behaves differently with and without it.
RTC is often confused with asynchronous inference. Async inference decides when to request a new chunk so that the action queue never empties. RTC changes how the new chunk is generated so that it agrees with what is already executing. Naive asynchronous execution without RTC can switch abruptly between chunks that disagree. RTC also differs from temporal ensembling, which averages overlapping chunks; the paper reports RTC as smoother than all compared methods, including temporal ensembling.