Knowing Where to Look: Interactive Object Search via Spatial-Semantic Fusion
cs.RO
Submitted: 2026-10-31
Updated: 2026-10-31
Project page: https://skymanaditya1.github.io/objsearch-website
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Multi-Resolution POMDP Planning for Multi-Object Search in 3D
- CuriousBot: Interactive Mobile Exploration via Actionable 3D Relational Object Graph
- RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation
- Object Goal Navigation using Goal-Oriented Semantic Exploration
- Visual Semantic Navigation using Scene Priors
- IPPON: Common Sense Guided Informative Path Planning for Object Goal Navigation
- SAM 3: Segment Anything with Concepts
- Gemini: A Family of Highly Capable Multimodal Models
- TiPToP: A Modular Open-Vocabulary Robot Manipulation System That Plans
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