Mulligan: Can Failure-Focused Data Improve Robot Imitation Learning?

Podcast: Embodied AI 101 · Shaoqing Tan

Opublikowano: 2026-10-11

Can a robot learn more from the same collection budget by revisiting the situations it gets wrong? This episode explains what Mulligan demonstrates about focused robot data collection—and why better learning per episode is not automatically better learning per operator hour. We examine three questions: how failed-state retries and counterfactual demonstrations differ from ordinary DAgger corrections; what value-based action selection adds beyond the imitation policy; and how to interpret the blinded, paired real-robot results. The experiments cover marker insertion, nut placement, and cable routing on a Franka Panda, alongside simulated square-nut insertion. We also unpack a consequential simulation caveat: so...