Speed on Demand: Faster-than-Demonstration Imitation via a Neural Robot Dynamics Model

Imitation policies trained on teleoperated demonstrations succeed on a broad range of manipulation tasks, but their execution speed is typically capped by the frequency at which human demonstrations are collected. Naively raising the execution frequency at deployment fails, as the tracking error between commanded and reached joint positions grows with frequency, so the executed trajectory deviates from the demonstration and the policy's observations fall out of distribution. We present Speed on Demand, a framework that enables a BC policy to operate faster than the demonstration by learning intentionally offset commands whose reached positions match the demonstrated trajectory after passing through the robot–controller dynamics. A neural dynamics model, trained using only 2 minutes of play data, captures the command-to-reached-state mapping of the robot–controller system. By fine-tuning the BC policy with this neural dynamics model in the loop, the policy learns to produce intentionally compensated commands whose resulting reached positions match the demonstrated trajectory under accelerated execution. A single policy, conditioned on a continuous speedup factor, executes at up to $5\times$ the demonstration frequency on CRANE-X7 with 80% task success, where both baselines fall to 27% or below. On Franka Research 3 with impedance control, the same method reaches $3.8\times$ the demonstration frequency, and task success is preserved up to $2.5\times$. Videos and code are available on the https://iclr90866-anonymous.github.io/project website.