INSPECT is a system that learns how a robot should choose its camera view during assembly inspection by observing a smart‑glasses assistant that answers part queries and guides the user. It uses techniques such as Presence‑Invariant TwinSwap for object evidence calibration, claim‑indexed supervision to separate evidence needs from camera changes, and object‑centered calibration to adapt view preferences to robot poses. In experiments on gearbox assemblies and angle‑grinder recordings, INSPECT outperforms other non‑oracle policies, improving view utility and decision accuracy.
arXiv:2605.07943v2 Announce Type: replace-cross Abstract: Active vision -- where a policy controls its own gaze during manipulation -- has emerged as a key capability for imitation learning, with mul...
arXiv:2610.03710v1 Announce Type: cross Abstract: Inspired by human vision, we introduce a framework using active gaze to enable fine-grained bimanual manipulation with only a single stereo camera. E...
The paper introduces Rendering-Free Lookahead (RFL), a method for active robot vision that selects camera motions to reveal information needed for viewpoint-dependent question answering. RFL predicts future answerability—how well a view can answer a question—using a student model trained via distillation from a privileged teacher that renders future views with 3D Gaussian Splatting. In deployment, RFL chooses camera motions without rendering, achieving a 43% improvement in mean judge score over a baseline on 377 unseen test episodes.
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:2606. 26443v1 Announce Type: cross Abstract: A robot working alongside people must reason about what they have done, in what order, and with what intent.
arXiv:2606. 03134v1 Announce Type: cross Abstract: 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.
arXiv:2610.17521v1 Announce Type: cross Abstract: Evaluating VLA policies on real robots is costly, time-consuming, and difficult to reproduce, making real-to-sim simulation essential for scalable ev...
RoboJev-27B is an open‑weight vision‑language model that predicts whether a robot has successfully completed a manipulation task by analyzing a task instruction, ten frames of the attempt, and optional auxiliary camera frames. Trained with a rank‑32 LoRA adapter on 52,598 episodes, it achieves 95.2% balanced accuracy and 0.993 AUROC on held‑out episodes of the same robot model, and maintains strong performance on unseen labs, robots, and community‑collected data. The model runs in 0.26 seconds per episode on an H100 GPU and is released with inference code and a large, transparent evaluation dataset for reproducible benchmarking.
The paper introduces Evidence‑Gated Regularization (EGR), a modality‑agnostic training objective that mitigates modality entanglement in Vision‑Language‑Action (VLA) policies. EGR uses per‑frame, per‑sensor task‑relevance signals to enforce invariance on low‑evidence sensors and single‑sensor sufficiency on high‑evidence ones, adding no inference‑time overhead. Evaluations on a BEHAVIOR‑1K benchmark and two real‑robot setups (bi‑manual Kinova arms with RGB cameras and a single‑arm MELFA ASSISTA with vision and GelSight tactile sensors) show significant improvements in success rates across various corruption and fallback scenarios.
WARP-VLA is a Vision‑Language‑Action model designed to be robust to variations in wrist‑camera viewpoints. It uses a Mixture‑of‑Experts architecture where each expert learns a view‑specific feature transformation, and a router selects the appropriate expert based on implicit view cues, eliminating the need for explicit camera extrinsic parameters. Experiments on the LIBERO benchmark show that WARP‑VLA doubles the success rate of pi‑0.5 from 39.2% to 78.3% under wrist‑view perturbations, and real‑robot tests confirm that the simulation‑learned adaptation transfers to diverse deployment settings.
arXiv:2606. 24472v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have made rapid progress in generalist robot manipulation by harnessing semantic knowledge from pretrained vision-language backbones, but their visual tokens remain grounded in 2D image coordinates rather than the calibrated geometry of the robot's cameras -- a mismatch especially pronounced in multi-camera setups, where views are coupled by known intrinsics and extrinsics yet processed as independent images.
arXiv:2605. 21862v2 Announce Type: replace-cross Abstract: Chunked vision-language-action (VLA) policies predict multi-step robot controls, conditioning each update on the current visual observation alone.