The paper introduces behavior graphs, an unsupervised method that compresses high‑dimensional robot policy rollouts into a single directed graph. By clustering similar behavior modes, linking them temporally, and associating them with outcomes, the graphs provide an interpretable representation of deployment data. In a user study, participants preferred behavior graphs over raw videos, achieving comparable conclusions with less perceived effort, and across many datasets the graphs improved progress prediction accuracy.
Existing robot policies based on learned visual embeddings lack explicit structure and are sensitive to visual distractions. Thus, the representations that drive their behaviour are often opaque, making their decision-making process difficult to interpret.
The paper introduces RACE, a rollout‑free metric for selecting robot policy checkpoints that uses held‑out successful trajectories to calibrate action deviations against state‑conditional thresholds. By aggregating these calibrated scores with a running product, RACE reduces the influence of later reference predictions when early deviations occur, and averages the cumulative scores over time and across trajectories to produce a checkpoint score. Experiments in simulation and on real robots show that RACE outperforms baseline methods and its rankings correlate with deployment success across various policy backbones and tasks.
arXiv:2512.01946v4 Announce Type: replace-cross Abstract: Robust robotic manipulation requires reliable failure detection and recovery. Although recent Vision-Language Models (VLMs) show promise in r...
arXiv:2609.39665v1 Announce Type: new Abstract: Embodied agents must determine where to act, anticipate the resulting scene changes, and interpret observed outcomes to guide subsequent actions. This...
arXiv:2607. 05369v1 Announce Type: cross Abstract: For robots to work reliably in commercial and industrial applications, can recent advances in agentic coding systems combine interpretable robot programming with the open-world adaptability of model-free policies?
The paper introduces a method for quantifying epistemic uncertainty in flow‑matching based generalist robot policies, such as vision‑language‑action models and world‑action models. By measuring velocity‑field disagreement across a small ensemble, the authors obtain better‑calibrated uncertainty estimates that can detect deployment failures and guide active fine‑tuning. Their SAVE approach reduces the need for expert demonstrations, improving real‑world task success from 39 % to 47 % while maintaining a fixed demonstration budget.
arXiv:2607. 14439v1 Announce Type: new Abstract: Generalist robot manipulation policies trained on large, diverse datasets have shown remarkable promise across a wide range of tasks.
arXiv:2606. 18247v1 Announce Type: cross Abstract: Robots deployed in the real world should learn from their experience and improve over time.
IndustrialVLA-Bench evaluates six released vision‑language‑action (VLA) and world‑action (WAM) robot policy models using a unified reporting schema. It measures clean capability on LIBERO, non‑language robustness on LIBERO‑Plus, instruction sensitivity on LIBERO‑Para, and observed execution cost, aggregating results across three random seeds. The benchmark also reports inference latency, peak memory, runtime mode, and evidence status for each system, enabling traceable comparisons without claiming one paradigm is universally superior.
arXiv:2609.36518v1 Announce Type: cross Abstract: Robots must often continue a task after a target moves, the viewpoint shifts, or an obstacle appears, even though their earlier observations and comm...
arXiv:2606. 16690v1 Announce Type: cross Abstract: Learning-based manipulation policies have made substantial progress in real-world robot manipulation, particularly for short-horizon action generation.
The paper introduces HALTER, a graph-based system that automates the reset and evaluation of long-horizon robot manipulation tasks. HALTER constructs a spatial scene graph from point clouds and vision models, uses an LLM to score rollouts, plan resets, and verify success, all without labeled success images. In experiments on a Franka arm, HALTER restores scenes in 76% of episodes, improves skill completion estimation, and reduces operator time by 72% compared to manual reset.