FARM: Reading Failure Signals from the Internal Predictive States of a Frozen Robotic World Model

2026-09-10

AI Summary

研究通过训练一个小型监督读出模型从冻结的机器人世界模型内部预测状态中解码故障信息，以实现可靠的在线故障监测。

Abstract

Reliable robot deployment requires online failure monitoring, yet existing monitors mainly derive risk from proxy signals or train dedicated monitoring components. We ask whether the internal predictive states of a frozen pretrained robotic world model already contain directly decodable failure information. Failure-Aware Readout from World Models (FARM) trains only a 33,985-parameter supervised readout over frozen VLA-JEPA predictive states, producing step-wise failure scores and causal trajectory risk. Five-fold out-of-fold evaluation across seven source tasks reaches 85.68/88.59 pooled AUROC/AUPRC, and FARM gives the best Seen performance among 15 matched baselines on the 10-task benchmark. Across four real-robot populations on PIPER X, SO-101, and Franka, fixed-readout transfer and readout-only adaptation test deployment shifts without updating the predictive backbone. FARM also discriminates failures from partial causal histories and adds 0.2256 ms mean CUDA latency once the frozen state is available. These results support frozen predictive world-model states as reusable features for causal, transferable, and low-overhead execution monitoring.

Problem

• robot deployment
• failure monitoring
• predictive states
• world model
• internal signals

Innovation

• Failure-Aware Readout
• Frozen World Models
• Causal Trajectory Risk
• Low-Overhead Monitoring