Robot Failure Detection

Generative robot policies fail unpredictably at deployment: they hesitate at critical moments, drift off-task, or commit to unrecoverable actions. Existing online failure detectors either require white-box access to policy internals or add runtime overhead through resampling and observation-side signals. Our empirical analysis shows that emitted action chunks themselves already carry strong predictive signal for impending failures in generative robot policies. Motivated by this observation, we introduce ActProbe, a lightweight, pure action-space detector that uses two compact signals available from a single forward pass: Temporal Consistency Error (TCE) between consecutive action chunks and Action Chunk Magnitude (ACM) of the current chunk. ActProbe maps these signals to per-step failure probabilities with a task-conditioned LSTM-MLP architecture. Across a diverse suite of generative robot policies and benchmarks, ActProbe raises alerts before failures become visually recognizable, improving the accuracy (F1)-timeliness Pareto frontier of failure detection by an average hypervolume gain of +12.7% over both internal- and external-feature baselines, with a +9.0% early-detection ROC-AUC lead on unseen tasks. ActProbe further transfers to deployment, predicting failures on unseen real-robot pick tasks and accelerating RL fine-tuning (PPO) with 2.9x fewer environment interactions.

Long-horizon robot manipulation tends to fail gradually: one bad step degrades the state, and the policy spirals into a basin from which it cannot recover. The failure is often visible before it happens. We introduce AEGIS (Activation-probe Early-warning, Gated Inference Switching), a selective escalation method that uses a lightweight probe on a weak policy's frozen activations to detect high-risk steps while there is still time to act. When the probe flags a step, control switches to a stronger separate policy, but only for the steps that need it. On LIBERO-Spatial, AEGIS recovers 10.1% of the trajectories the weak policy alone loses, versus 4.6% for budget-matched blind escalation and 5.1% for a random-trigger placebo. These gains are significant under one-sided exact paired McNemar tests with Holm-Bonferroni adjustment over three pre-registered contrasts: +5.4pp over blind escalation, p=8.5e-6; +5.0pp over random triggering, p=1.0e-4; paired-trajectory bootstrap CIs exclude zero. AEGIS activates the stronger policy on only 38% of steps, so the lever is timing rather than compute. The probe clears its precondition with an early-window AUROC of 0.764, 95% CI [0.70, 0.84], read from the weak-policy path over the first 30% of trajectory steps before any handoff. We pre-register the full analysis plan, including a conditional recovered-task-rate estimand and explicit kill criteria, and confirm the result on 700 common-random-number episodes per arm, with nA-fail=646.

Low-cost 2D LiDARs lack the intensity channel that higher-end sensors use to diagnose measurement failures, yet they are widely used on educational and budget robotics platforms. We present SENTINEL, a training - free, label - free reliability estimation framework that gives range - only LiDAR an effective diagnostic signal. SENTINEL combines geometry-based scan statistics with cross - modal depth consistency between LiDAR and an RGB - D camera to compute a per - scan reliability score between 0 and 1. When the score falls below a threshold, corrupted scans are rejected and the robot falls back to calibrated wheel odometry, preventing silent SLAM corruption. We evaluate SENTINEL on a GEFIER R1 four - wheel skid-steer robot equipped with an RPLidar A2M12 and an Intel RealSense D435i in a 185 cm by 245 cm arena containing controlled transparent and reflective failure elements on a central obstacle. Spatial reliability maps across five surface conditions, including glass, mirror, shiny paper, and a mixed mirror and shiny-paper condition, show clear separation between clean and failure cases, allowing affected regions to be identified as reject or noise. Because these failure modes are absent in simulation, validation is performed entirely on real hardware.

Imitation-learning policies for robot manipulation inherit the quality of the success labels attached to their training episodes, and those labels are usually produced by the robot's own success check. A particularly damaging error is the false success: an episode the robot logs as a success when the task outcome was actually wrong. We ask a narrow but practical question about these episodes. Once an episode has already been flagged as a success, how much of the information needed to overturn that label is present in proprioception, and how much requires vision? We build a simulated testbed on two bimanual ALOHA tasks, induce failures through environment perturbations rather than label edits, label every episode by privileged simulator state that the detector never sees, and keep only episodes the robot flagged as successful. We then compare detectors restricted to proprioception against a vision-based detector. We find that recoverability spans a wide range: in cube transfer the false successes are almost fully recoverable from joint data alone, while in peg insertion proprioception recovers only part of them and a vision detector closes most of the gap. We also show that the proprioceptive separability we measure rests on velocity differences far below any realistic sensor noise floor, so it is best read as an optimistic upper bound that a noiseless simulator inflates. We release the generation and evaluation pipeline.

Vision-Language-Action (VLA) models enable robots to follow natural language instructions and generalize across diverse tasks, but they remain vulnerable to execution failures that compromise reliability in real-world deployment. Detecting such failures during execution is therefore critical for the robust deployment of embodied systems. Existing failure detection methods either rely on expensive action resampling or external models, while alternatives propagate trajectory-level labels uniformly across every timestep, obscuring localized failure signals. In this paper, we propose Hide-and-Seek, a framework that formulates VLA failure detection as a coarsely supervised learning problem. By combining inter-trajectory and intra-trajectory contrastive objectives, Hide-and-Seek localizes failure-indicative actions and induces temporally structured failure signals from trajectory-level supervision alone, without any step-level annotation. We evaluate Hide-and-Seek on LIBERO, VLABench, and a real-world robotic platform across three representative VLA policies: OpenVLA, $π_0$, and $π_{0.5}$.Our method achieves state-of-the-art multi-task failure detection performance with a practical accuracy--timeliness trade-off under conformal prediction, and generalizes well to both seen and unseen tasks.

We discover that VLA architectures fail in fundamentally different, predictable ways at the motor-command level. Running VQ-BeT, Diffusion Policy, and ACT on identical evaluation protocols (n=450 episodes across PushT and ALOHA 14-DOF bimanual manipulation), we find: (1) direction reversal rate is a universal failure predictor across all three architectures (AUROC=0.93, 0.79, 0.91; p<0.001); (2) jerk monitoring is predictive only for discrete-token architectures, following a discrete-to-continuous gradient (0.88, 0.69, 0.41); (3) velocity violations alone are non-predictive everywhere (AUROC 0.41-0.69), yet velocity checking is the most common safety mechanism in VLA deployment code; and (4) for continuous-family VLAs, velocity monitoring provides effectively zero predictive signal (AUROC=0.52 on ACT, 0.41 on Diffusion), proving that architecture-matched monitor selection is essential. These results quantify a monitoring consequence of the well-known discrete/continuous VLA distinction: the two families produce qualitatively different failure signatures that require different monitors. No single monitor works universally; architecture-matched selection is required. This finding was enabled by SafeContract, a training-free, black-box action monitoring toolkit with conformal calibration. Code: https://github.com/krishnam94/vla-edge

Imitation learning has enabled robots to acquire complex visuomotor manipulation skills from demonstrations, but deployment failures remain a major obstacle, especially for long-horizon action-chunked policies. Once execution drifts off the demonstration manifold, these policies often continue producing locally plausible actions without recovering from the failure. Existing runtime monitors either require failure data, over-trigger under benign feature drift, or stop at failure detection without providing a recovery mechanism. We present Rewind-IL, a training-free online safeguard framework for generative action-chunked imitation policies. Rewind-IL combines a zero-shot failure detector based on Temporal Inter-chunk Discrepancy Estimate (TIDE), calibrated with split conformal prediction, with a state-respawning mechanism that returns the robot to a semantically verified safe intermediate state. Offline, a vision-language model identifies recovery checkpoints in demonstrations, and the frozen policy encoder is used to construct a compact checkpoint feature database. Online, Rewind-IL monitors self-consistency in overlapping action chunks, tracks similarity to the checkpoint library, and, upon failure, rewinds execution to the latest verified safe state before restarting inference from a clean policy state. Experiments on real-world and simulated long-horizon manipulation tasks, including transfer to flow-matching action-chunked policies, demonstrate that policy-internal consistency coupled with semantically grounded respawning offers a practical route to improved reliability in imitation learning. Supplemental materials are available at https://sjay05.github.io/rewind-il

Vision-language-action (VLA) models have emerged as generalist robotic controllers that map visual observations and language instructions to continuous actions. However, pretrained VLAs typically provide limited information about the reliability of their generated actions, making deployment challenging when execution failures must be anticipated. We address this problem by introducing SentryVLA, a lightweight runtime wrapper for frozen VLA policies. At the action level, SentryVLA uses conformalized quantile regression to estimate a calibrated upper bound on the deviation between sampled VLA actions and expert-like behavior under the calibration distribution. The predicted deviation is then used to rank multiple stochastic candidates for action selection. At the execution-monitoring level, SentryVLA applies a Mahalanobis-distance-based anomaly score to the contextualized latent execution state extracted before final action prediction, providing a complementary signal for detecting abnormal execution states during closed-loop control. The framework does not require retraining or architectural modification of the underlying VLA policy. Experiments in simulation and on a physical robot show that SentryVLA improves action selection and provides useful runtime warning signals for abnormal execution states. These findings demonstrate the practical value of post-hoc reliability scoring for improving the runtime behavior of pretrained VLA policies. Project webpage: https://robotic-vision-lab.github.io/sentryvla/.

Imitation learning (IL) policies in robotics deliver strong performance in controlled settings but remain brittle in real-world deployments: rare events such as hardware faults, defective parts, unexpected human actions, or any state that lies outside the training distribution can lead to failed executions. Vision-based Anomaly Detection (AD) methods emerged as an appropriate solution to detect these anomalous failure states but do not distinguish failures from benign deviations. We introduce FIDeL (Failure Identification in Demonstration Learning), a policy-independent failure detection module. Leveraging recent AD methods, FIDeL builds a compact representation of nominal demonstrations and aligns incoming observations via optimal transport matching to produce anomaly scores and heatmaps. Spatio-temporal thresholds are derived with an extension of conformal prediction, and a Vision-Language Model (VLM) performs semantic filtering to discriminate benign anomalies from genuine failures. We also introduce BotFails, a multimodal dataset of real-world tasks for failure detection in robotics. FIDeL consistently outperforms state-of-the-art baselines, yielding +5.30% percent AUROC in anomaly detection and +17.38% percent failure-detection accuracy on BotFails compared to existing methods.

This position paper looks briefly at the way we attempt to program robotic AI systems. Many AI systems are based on the idea of trying to improve the performance of one individual system to beyond so-called human baselines. However, these systems often look at one shot and one-way decisions, whereas the real world is more continuous and interactive. Humans, however, are often able to recover from and learn from errors - enabling a much higher rate of success. We look at the challenges of building a system that can detect/recover from its own errors, using the example of robotic nuclear gloveboxes as a use case to help illustrate examples. We then go on to talk about simple starting designs.

We present KITE, a training-free, keyframe-anchored, layout-grounded front-end that converts long robot-execution videos into compact, interpretable tokenized evidence for vision-language models (VLMs). KITE distills each trajectory into a small set of motion-salient keyframes with open-vocabulary detections and pairs each keyframe with a schematic bird's-eye-view (BEV) representation that encodes relative object layout, axes, timestamps, and detection confidence. These visual cues are serialized with robot-profile and scene-context tokens into a unified prompt, allowing the same front-end to support failure detection, identification, localization, explanation, and correction with an off-the-shelf VLM. On the RoboFAC benchmark, KITE with Qwen2.5-VL substantially improves over vanilla Qwen2.5-VL in the training-free setting, with especially large gains on simulation failure detection, identification, and localization, while remaining competitive with a RoboFAC-tuned baseline. A small QLoRA fine-tune further improves explanation and correction quality. We also report qualitative results on real dual-arm robots, demonstrating the practical applicability of KITE as a structured and interpretable front-end for robot failure analysis. Code and models are released on our project page: https://m80hz.github.io/kite/

Operations in hazardous environments put humans, animals, and machines at high risk for physically damaging consequences. In contrast to humans and animals, quadruped robots cannot naturally identify and adjust their locomotion to a severely debilitated limb. The ability to detect limb damage and adjust movement to a new physical morphology is the difference between survival and death for humans and animals. The same can be said for quadruped robots autonomously carrying out remote assignments in dynamic, complex settings. This work presents the development and implementation of an off-line learning-based method to detect single limb faults from proprioceptive sensor data in a quadrupedal robot. The aim of the fault detection technique is to provide the correct output for the controller to select the appropriate tripedal gait to use given the robot's current physical morphology.

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/

Autonomous inspection robots for monitoring industrial sites can reduce costs and risks associated with human-led inspection. However, accurate readings can be challenging due to occlusions, limited viewpoints, or unexpected environmental conditions. We propose a hybrid framework that combines supervised failure classification with anomaly detection, enabling classification of inspection tasks as a success, known failure, or anomaly (i.e., out-of-distribution) case. Our approach uses a world model backbone with compressed video inputs. This policy-agnostic, distribution-free framework determines classifications based on two decision functions set by conformal prediction (CP) thresholds before a human observer does. We evaluate the framework on gauge inspection feeds collected from office and industrial sites and demonstrate real-time deployment on a Boston Dynamics Spot. Experiments show over 90% accuracy in distinguishing between successes, failures, and OOD cases, with classifications occurring earlier than a human observer. These results highlight the potential for robust, anticipatory failure detection in autonomous inspection tasks or as a feedback signal for model training to assess and improve the quality of training data. Project website: https://autoinspection-classification.github.io

Reasoning about failures is crucial for building reliable and trustworthy robotic systems. Prior approaches either treat failure reasoning as a closed-set classification problem or assume access to ample human annotations. Failures in the real world are typically subtle, combinatorial, and difficult to enumerate, whereas rich reasoning labels are expensive to acquire. We address this problem by introducing ARMOR: Adaptive Round-based Multi-task mOdel for Robotic failure detection and reasoning. We formulate detection and reasoning as a multi-task self-refinement process, where the model iteratively predicts detection outcomes and natural language reasoning conditioned on past outputs. During training, ARMOR learns from heterogeneous supervision - large-scale sparse binary labels and small-scale rich reasoning annotations - optimized via a combination of offline and online imitation learning. At inference time, ARMOR generates multiple refinement trajectories and selects the most confident prediction via a self-certainty metric. Experiments across diverse environments show that ARMOR achieves state-of-the-art performance by improving over the previous approaches by up to 30% on failure detection rate and up to 100% in reasoning measured through LLM fuzzy match score, demonstrating robustness to heterogeneous supervision and open-ended reasoning beyond predefined failure modes. We provide additional visualizations on our website: https://sites.google.com/utexas.edu/armor

Bolting operations are critical in industrial assembly and in the maintenance of scientific facilities, requiring high precision and robustness to faults. Although robotic solutions have the potential to improve operational safety and effectiveness, current systems still lack reliable autonomy and fault management capabilities. To address this gap, we propose a control framework for dependable robotized bolting tasks and instantiate it on a specific robotic system. The system features a control architecture ensuring accurate driving torque control and active compliance throughout the entire operation, enabling safe interaction even under fault conditions. By designing a multimodal human-robot interface (HRI) providing real-time visualization of relevant system information and supporting seamless transitions between automatic and manual control, we improve operator situation awareness and fault detection capabilities. A high-level supervisor (SV) coordinates the execution and manages transitions between control modes, ensuring consistency with the supervisory control (SVC) paradigm, while preserving the human operator's authority. The system is validated in a representative bolting operation involving pipe flange joining, under several fault conditions. The results demonstrate improved fault detection capabilities, enhanced operator situational awareness, and accurate and compliant execution of the bolting operation.

Imitation learning has shown promise in learning from large-scale real-world datasets. However, pretrained policies usually perform poorly without sufficient in-domain data. Besides, human-collected demonstrations entail substantial labour and tend to encompass mixed-quality data and redundant information. As a workaround, human-in-the-loop systems gather domain-specific data for policy post-training, and exploit closed-loop policy feedback to offer informative guidance, but usually require full-time human surveillance during policy rollout. In this work, we devise ARMADA, a multi-robot deployment and adaptation system with human-in-the-loop shared control, featuring an autonomous online failure detection method named FLOAT. Thanks to FLOAT, ARMADA enables paralleled policy rollout and requests human intervention only when necessary, significantly reducing reliance on human supervision. Hence, ARMADA enables efficient acquisition of in-domain data, and leads to more scalable deployment and faster adaptation to new scenarios. We evaluate the performance of ARMADA on four real-world tasks. FLOAT achieves nearly 95% accuracy on average, surpassing prior state-of-the-art failure detection approaches by over 20%. Besides, ARMADA manifests more than 4$\times$ increase in success rate and greater than 2$\times$ reduction in human intervention rate over multiple rounds of policy rollout and post-training, compared to previous human-in-the-loop learning methods.