Failure Prediction at Runtime for Generative Robot Policies

Ralf Römer, Adrian Kobras, Luca Worbis, Angela P. Schoellig

Keywords: Imitation Learning, Diffusion Policies, Robotics, Safety, Generative Models

TL;DR: We propose FIPER, a framework to predict failures of generative imitation learning policies by detecting consecutive OOD observations and high action uncertainty, achieving more accurate and faster detection than prior approaches.

Abstract: Imitation learning (IL) with generative models, such as diffusion and flow matching, has enabled robots to perform complex, long-horizon tasks. However, distribution shifts from unseen environments or compounding action errors can still cause unpredictable and unsafe behavior, leading to task failure. Therefore, early failure prediction during runtime is essential for deploying robots in human-centered and safety-critical environments. We propose FIPER, a general framework for Failure Prediction at Runtime for generative IL policies that does not require failure data. FIPER identifies two key indicators of impending failure: (i) out-of-distribution (OOD) observations detected via random network distillation in the policy’s embedding space, and (ii) high uncertainty in generated actions measured by a novel action-chunk entropy score. Both failure prediction scores are calibrated using a small set of successful rollouts via conformal prediction. A failure alarm is triggered when both indicators, aggregated over short time windows, exceed their thresholds. We evaluate FIPER across five simulation and real-world environments involving diverse failure modes. Our results demonstrate that FIPER better distinguishes actual failures from benign OOD situations and predicts failures more accurately and earlier than existing methods. We thus consider this work an important step towards more interpretable and safer generative robot policies. Code, data, and videos are available at [tum-lsy.github.io/fiper_website](https://tum-lsy.github.io/fiper_website).

Primary Area: Reinforcement learning (e.g., decision and control, planning, hierarchical RL, robotics)

Submission Number: 24343