LIBERO-VPro is a benchmark designed to assess the closed‑loop visual robustness of robotic foundation models by systematically perturbing visual inputs during task execution. It spans four dimensions—Visual Evidence Degradation, Camera Staleness, Visual Source Consistency, and Task‑Relevant Scene Variation—across 12 challenge categories, 96 settings, and 3,296 task‑condition cases. Evaluations on six models over 196,000 simulated episodes and 200 real‑world rollouts show that high nominal performance can hide significant weaknesses in visual grounding, adaptation, and sensitivity to stale or missing observations.
Robotic foundation models achieve impressive performance on standard manipulation benchmarks, yet these evaluations typically assume clean, timely, and consistent visual observations throughout execut...
arXiv:2606. 28385v1 Announce Type: cross Abstract: Recent advances in robot world models enable synthetic video generation for embodied prediction and planning.
arXiv:2603. 06001v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models enable robots to perform manipulation tasks directly from natural language instructions and are increasingly viewed as a foundation for generalist robotic policies.
arXiv:2610.18843v1 Announce Type: cross Abstract: Robot policies are expected to generalize across deployment environments, including variations in the robot itself: cameras are bumped and remounted,...
arXiv:2603. 25937v2 Announce Type: replace-cross Abstract: Visual Navigation Models (VNMs) promise generalizable, robot navigation by learning from large-scale visual demonstrations.
arXiv:2609.27076v1 Announce Type: new Abstract: Open-vocabulary visual grounding enables robots to localise task-relevant entities from natural-language queries without dependence on predefined perce...
RoboSPA is a large-scale robotic manipulation dataset and benchmark designed to evaluate Vision‑Language‑Action models on fine‑grained spatial reasoning and long‑horizon procedural planning. It contains 10 task categories, 56 base tasks, and 280 variants across five difficulty levels, with 527K trajectories collected from multiple embodiments and scenes. The benchmark introduces diagnostic metrics beyond binary success, revealing that current VLA models struggle with complex spatial relations, precise execution, and memory‑intensive planning.
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:2606.20092v3 Announce Type: replace Abstract: Memory remains a critical bottleneck for long-horizon robotic manipulation, as standard Vision-Language-Action (VLA) policies often fail when task-...
Vision‑Language‑Action models (VLAs) often fail to follow language instructions because they rely on vision shortcuts learned from biased datasets. The authors introduce LIBERO‑CF, a counterfactual benchmark that tests language following by providing alternative task instructions for the same scene layouts, revealing widespread counterfactual failures. They propose Counterfactual Action Guidance (CAG), a dual‑branch inference scheme that amplifies language conditioning, which consistently improves language grounding and task success across diverse VLAs without requiring extra data or architectural changes.
FailBench is a new benchmark for robot failure detection, containing 2,197 manipulation attempts from 14 public sources, with 75% of failures occurring naturally. The study evaluates 13 vision‑language model (VLM) detectors, finding the best model achieves only 0.77 mean balanced accuracy, and that fine‑tuned failure detectors often underperform general‑purpose VLMs. Performance varies with visual evidence, excelling when object motion is observable but dropping to near chance on contact‑intensive assembly tasks, and input‑level cropping of outcome‑relevant regions improves the top detector by 2.4 percentage points.
VABench is a benchmark that tests general‑purpose multimodal large language models (MLLMs) on embodied spatial intelligence by requiring them to observe, reason, act, and revise based on visual demonstrations and active perception. The benchmark includes 14 task families, a fixed model‑agnostic controller, and evaluates models on target localization, spatial relations, and long‑horizon composition tracks without providing privileged object poses or learned action heads. Results show that while the best model achieves perfect target localization, overall task success remains modest, and active camera control and geometric transfer significantly influence performance.