FEIJOA: Task-Driven Grounding and Execution for Mobile Manipulation
cs.RO
Submitted: 2026-11-02
Updated: 2026-11-02
Project page: https://williamshen-nz.github.io/feijoa
Terminology
Sources
- Agentic Scene Policies
- SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning
- ConceptFusion: Open-set Multimodal 3D Mapping
- Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation
- OK-Robot: What Really Matters in Integrating Open-Knowledge Models for Robotics
- DynaMem: Online Dynamic Spatio-Semantic Memory for Open World Mobile Manipulation
- Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimization
- MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Model for Embodied Task Planning
- VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- Inner Monologue: Embodied Reasoning through Planning with Language Models
- Memory Over Maps: 3D Object Localization Without Reconstruction
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