Motion Belief Action: From a Visual Scene Map to Physical Decisions
cs.RO
Submitted: 2026-11-09
Updated: 2026-11-09
Terminology
Sources
- PreSIST: Vision-Language-Informed Object Persistence Prediction in Open-World Scenes
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Which Objects Stay? Learning Hierarchical Persistence Beliefs for Lifelong Open-Vocabulary Object Maps
- Hoi! - A Multimodal Dataset for Force-Grounded, Cross-View Articulated Manipulation
- You've Got to Feel It To Believe It: Multi-Modal Bayesian Inference for Semantic and Property Prediction
- PhysVLMM: Interaction-Conditioned Physical Belief Maps for Articulated Objects in Robot Scene Maps
- Vision-Language-Motion Maps: An Open-Vocabulary, Uncertainty-Aware, Queryable Motion Attribute for 3D Scene Maps
- Nudge Before You Push: Physics-Aware Navigation via Tactile Probing
- AquaMend: Minimal Re-probing and Conditional Rollback for Latent-Belief Failures in Embodied Agents
- Open-World Law-to-Action: Vision-Language Priors and Touch for Parts with Hidden Physics
- Object- and Task-Aware Active Perception for Safe Navigation of Mobile Manipulators in Semi-Static Environments
- Perpetua: Multi-Hypothesis Persistence Modeling for Semi-Static Environments
- SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
- BOKBO (Best of K Bad Options): Calibrated Abstention for VLA Policies
- Phys2Real: Fusing VLM Priors with Interactive Online Adaptation for Uncertainty-Aware Sim-to-Real Manipulation
- I Won't Know Until I Try: Interactive Information Gathering for Long-Horizon Manipulation
- Do Not Cut When Uncertain: Rejectable and Calibrated Decision Heads for VLA Policies in Robotic Harvesting
- Trading Transparency for Stability: Friction-Cone-Constrained Bilateral Teleoperation for Opening Doors of Unsecured Furniture
- PhysVLM-AVR: Active Visual Reasoning for Multimodal Large Language Models in Physical Environments
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation