SCOUT: Planning under Occlusion via Object-Centric World Model Rollouts
cs.RO, cs.AI, cs.CV
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- SceneComplete: Open-World 3D Scene Completion in Cluttered Real World Environments for Robot Manipulation
- LGMCTS: Language-Guided Monte-Carlo Tree Search for Executable Semantic Object Rearrangement
- Robo2VLM: Visual Question Answering from Large-Scale In-the-Wild Robot Manipulation Datasets
- Partially Observable Task and Motion Planning with Uncertainty and Risk Awareness
- Large-Language-Model-Guided State Estimation for Partially Observable Task and Motion Planning
- Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
- OK-Robot: What Really Matters in Integrating Open-Knowledge Models for Robotics
- RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots
- PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs
- SAM 3D: 3Dfy Anything in Images
- Qwen2.5 Technical Report
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