Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents (opens in new tab)

Long-horizon tasks are common in real-world robotic deployments, yet failure detection for such tasks remains underexplored. Detecting failures in long-horizon robotic tasks is particularly challenging because failure onset is often ambiguous and dense temporal annotations are typically unavailable. We present Foresight, a failure detection framework that monitors manipulation trajectories using latent representations from an action-conditioned ...