arXiv:2606. 20118v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies have shown strong potential for general-purpose manipulation, yet they often fail on novel, out-of-distribution objects whose appearance or geometry deviates from the training distribution.
arXiv:2610.08220v1 Announce Type: cross Abstract: Portable mobile-manipulation demonstrations can help alleviate data scarcity for embodied intelligence, but obtaining reliable, low-cost, and robot-f...
InfiNoVA is a data‑augmentation framework that transforms synchronized multi‑camera demonstrations into a dense, geometrically consistent set of training views by reconstructing each manipulation trajectory as a time‑varying 3D Gaussian. The method renders novel observations from sampled camera poses while preserving the original state‑action pairs, improving frame‑level fidelity and temporal consistency compared to generative synthesis. Across four real‑world manipulation tasks, policies trained with InfiNoVA achieve 5.4× higher average success under unseen randomized viewpoints than VISTA‑based augmentation and 1.7× higher success than training on all five physical camera views.
MAVP (Map-Aware Visuomotor Policies) is a framework that enhances mobile manipulation by predicting explicit base-pose targets and tracking them with localisation feedback. It reconstructs a static map from teleoperated demonstrations, expressing base trajectories in a shared map frame to provide consistent spatial supervision. During execution, the policy uses RGB observations, joint states, and the robot’s current map-frame base pose to jointly predict target base poses, arm actions, and gripper actions, while a low‑level controller corrects deviations using feedforward motion and pose error feedback. Pose‑noise augmentation during training further improves robustness, and MAVP outperforms unanchored velocity control across six real‑world tasks and three policy families.
arXiv:2610.07511v1 Announce Type: cross Abstract: Mobile manipulators such as humanoid robots are increasingly deployed in dynamic, unstructured environments to perform dexterous manipulation tasks....
SMART introduces a scalable system for zero‑shot sim‑to‑real articulated object manipulation by leveraging large‑scale synthetic pretraining. The core component, SMART‑Sim, is an articulation‑aware simulation platform that facilitates efficient task generation and demonstration collection. Using SMART‑Sim, the authors synthesize SMART‑Data, comprising over 1 million demonstrations across 44 task types, 5 robot setups, and 2,507 articulated objects, and demonstrate that a vision‑language‑action model pretrained on this data achieves competitive simulation performance and zero‑shot transfer to real‑world tasks.
arXiv:2602.13444v2 Announce Type: replace-cross Abstract: Recent vision-language-action (VLA) models can generate plausible end-effector motions, yet they often fail in long-horizon, contact-rich tas...
arXiv:2606. 10614v1 Announce Type: cross Abstract: Robotic foundation models pre-trained on human demonstration videos have shown promise, but a significant embodiment gap remains when the resulting policies are deployed on real robots.
AffordSim is a scalable data generator and benchmark that integrates open‑vocabulary 3D affordance prediction into simulation‑based trajectory generation for robotic manipulation. Given a natural‑language task description, it synthesizes task‑relevant scenes, queries affordances, grounds them on object surfaces, samples region‑conditioned grasps, and selects executable candidates with motion planning, while randomizing pose, texture, lighting, noise, and backgrounds for sim‑to‑real transfer. The benchmark includes 50 tasks, five robot embodiments, and over 500 objects, achieving 93% of the success rate of manual contact annotations on affordance‑critical tasks and 89% on hard composite tasks, with policies trained on AffordSim transferring zero‑shot to a real Franka FR3 with 24% average success.
arXiv:2606. 00054v1 Announce Type: cross Abstract: Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models.
Dex-One2Many introduces a real-to-sim-to-real framework that learns a generalizable dexterous manipulation policy from a single human video. By abstracting the video into sequential scene graphs, the method guides reinforcement learning with dense rewards and diverse reset states, enabling efficient exploration while preserving broad generalizability. Trained entirely in simulation, Dex-One2Many achieves zero‑shot transfer to a real multi‑fingered hand and outperforms baselines by 6.5% on seen configurations and 71% on unseen scenarios across five tool‑use and manipulation tasks.
World models offer a promising route toward robot planning by enabling agents to imagine and verify the consequences of actions before execution. However, current video-based world models often struggle to capture the physical constraints that govern manipulation, particularly contact.