TIMID: Time-Dependent Mistake Detection in Videos of Robot Executions

TL;DR

TIMID is a novel video anomaly detection architecture designed to identify complex, time-dependent mistakes in robot execution videos, enabling weakly supervised training and effective zero-shot sim-to-real transfer for high-level task failure detection.

Contribution

The paper introduces TIMID, a VAD-inspired model capable of detecting temporal mistakes in robot videos using weak supervision and a new multi-robot dataset for zero-shot evaluation.

Findings

TIMID effectively detects temporal errors in robot videos.

Out-of-the-box VLMs lack temporal reasoning for this task.

The dataset supports zero-shot sim-to-real transfer.

Abstract

As robotic systems execute increasingly difficult task sequences, so does the number of ways in which they can fail. Video Anomaly Detection (VAD) frameworks typically focus on singular, low-level kinematic or action failures, struggling to identify more complex temporal or spatial task violations, because they do not necessarily manifest as low-level execution errors. To address this problem, the main contribution of this paper is a new VAD-inspired architecture, TIMID, which is able to detect robot time-dependent mistakes when executing high-level tasks. Our architecture receives as inputs a video and prompts of the task and the potential mistake, and returns a frame-level prediction in the video of whether the mistake is present or not. By adopting a VAD formulation, the model can be trained with weak supervision, requiring only a single label per video. Additionally, to alleviate the problem of data scarcity of incorrect executions, we introduce a multi-robot simulation dataset with controlled temporal errors and real executions for zero-shot sim-to-real evaluation. Our experiments demonstrate that out-of-the-box VLMs lack the explicit temporal reasoning required for this task, whereas our framework successfully detects different types of temporal errors. Project: https://ropertunizar.github.io/TIMID/