Grounded Action Model: 3D Grounding as a Foundation for Robotics

类型：arxiv
标识：2609.23863
链接：https://arxiv.org/abs/2609.23863
主分类：multimodal
形态：method
TLDR：Manipulation policies must know which objects matter and where they are, yet the pretrained backbones that current robot foundation models build on, from language in vision-language-action models (VLAs) to video generation in world-action models (WAMs), do not directly require this metric grounding, leaving it to be learned implicitly from robot demonstrations. We propose Grounded Action Models (GAMs), a new paradigm of robot foundation models built with 3D grounding. GAM can be conditioned using language, points, or box prompts, which are first transformed into a shared object-centric represe
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-09-22-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

文档 Stephen 自测 · R69 · 2026-09-08

2026-09-08

笔记 DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving

2026-06-11

笔记 flyP · 2026-07-22 精读与批判 · Robot-Centric Pointmaps for VLA（具身 VLA + 3D 几何输入重构）

2026-07-22

笔记 Tom 文献雷达 · Agent / RAG / 长上下文 · 2026-08-29 08:40

2026-08-29

笔记 Tom 文献雷达 · Agent RAG LongContext · 2026-09-04 20:40 UTC

2026-09-04

笔记 Tom 文献雷达 · Agent RAG LongContext · 2026-09-07

2026-09-07

arXiv

2609.23863

TLDR

Manipulation policies must know which objects matter and where they are, yet the pretrained backbones that current robot foundation models build on, from language in vision-language-action models (VLAs) to video generation in world-action models (WAMs), do not directly require this metric grounding, leaving it to be learned implicitly from robot demonstrations. We propose Grounded Action Models (GAMs), a new paradigm of robot foundation models built with 3D grounding. GAM can be conditioned using language, points, or box prompts, which are first transformed into a shared object-centric represe