arXiv AI
Jun 26
WatchAct: A Benchmark for Behavior-Grounded Robot Manipulation
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.
INSPECT: Learning Robot View Selection from Assistant Use
Related stories
arXiv Machine Learning
Jun 3
How Visible Are Silent Manipulation Failures? An Observability Study of False-Success Detection in Simulated Robot Episodes
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 Machine Learning
Sep 4
Sensing Which Modality Matters: Evidence-Gated Regularization for Robust VLA Policies
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.
arXiv AI
Jun 24
G$^3$VLA: Geometric inductive bias for Vision-Language-Action Models
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 AI
Aug 18
EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control
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.
arXiv AI
Jul 7
From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model
arXiv:2607. 05396v1 Announce Type: cross Abstract: Real-world robot deployment rarely maintains the training-stage camera setup, where cameras often experience repositioning or remounting depending on actual scenarios.
arXiv Computer Vision
1d ago
AnyviewMeter: Adapting Robotic Reward Models with Camera Geometry and Multi-View Attention
AnyviewMeter is a geometry‑conditioned adaptation framework that fine‑tunes pretrained robotic reward models to account for camera viewpoint and occlusion. It uses low‑rank fine‑tuning, token‑aligned Plücker rays, and synchronous block attention to fuse synchronized multi‑view observations. Experiments on PickCube and simulated manipulation tasks show significant reductions in mean absolute error and improved temporal ordering compared to single‑view or RGB‑only fine‑tuning.
Hugging Face Trending Papers
Jul 6
From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model
Real-world robot deployment rarely maintains the training-stage camera setup, where cameras often experience repositioning or remounting depending on actual scenarios. Existing view-robust Vision-Language-Action (VLA) policies tolerate such camera variations only when the camera extrinsics are explicitly provided, making them fragile and hard to use especially when view robustness is critical.
arXiv Computer Vision
1d ago
VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control
arXiv:2609.19554v1 Announce Type: cross Abstract: Spatial intelligence requires more than describing object locations. Under incomplete observation, models must identify and acquire missing evidence,...
arXiv Computer Vision
Sep 1
DARP: A Calibrated Dual-Arm RGB-D-IR Dataset for Multi-View Robotic Perception
arXiv:2608.31002v1 Announce Type: cross Abstract: Robotic perception from a single viewpoint is often limited by self-occlusion and incomplete surface visibility. This paper presents DARP(Dual-Arm Ro...
arXiv Computer Vision
Sep 10
DUET-DINO: Simultaneous Cross-View World Modeling for Latent Planning in Robot Manipulation
arXiv:2609.10506v1 Announce Type: cross Abstract: Action-conditioned latent world models predict future visual representations, enabling zero-shot goal-conditioned robot planning and control. However...
arXiv AI
1d ago
AntiGrounding: Executable Robot Trajectories as Visual Prompts for VLM-Guided Manipulation
AntiGrounding is a visual action-selection framework that turns short robot trajectories into both executable motion plans and rendered prompts for vision‑language model evaluation. After filtering for feasibility, each trajectory is scored on safety, task alignment, efficiency, and physical plausibility using structured multi‑view visual question answering, and the best trajectories are refined and validated by a digital twin before real‑world execution. In eight real‑world manipulation tasks, the system achieved a 71.25% success rate with a single GPT‑6 Astra evaluator, outperforming baseline methods.