研究库 论文知识库

内容库 / 论文

arXiv:2609.09158 · 多模态

TANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model

类型：arxiv
标识：2609.09158
链接：https://arxiv.org/abs/2609.09158
主分类：multimodal
形态：method
TLDR：We study the problem of navigating cluttered indoor environments with a humanoid robot. Unlike conventional methods that model navigation as a 2D path planning problem, humanoid traversal in cluttered environments requires continuous geometry-aware whole-body adaptation, including coordinated arm placement, torso adjustment, and gait modulation for collision-free movement through complex 3D spaces. We introduce TANGO, the first whole-body vision-language navigation framework for language-conditioned humanoid traversal in cluttered environments. Given a natural-language instruction and egocentr
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-09-09-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

笔记精读与批判：SenseNova-Vision — Vision as Unified Multimodal Generation

文档 Stephen 自测 · R69 · 2026-09-08

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

仓库 jlucasmcrell/ComfyUI-H3-Multishot

笔记批判性精读 v2 · SenseNova-SI 空间智能 + MERGE 时延感知多模态 MoE 双稿对照 · 2026-08-26

笔记 Tom 文献雷达 · Agent + RAG + Long Context · 2026-08-01 14:40 CST

arXiv

2609.09158

TLDR

We study the problem of navigating cluttered indoor environments with a humanoid robot. Unlike conventional methods that model navigation as a 2D path planning problem, humanoid traversal in cluttered environments requires continuous geometry-aware whole-body adaptation, including coordinated arm placement, torso adjustment, and gait modulation for collision-free movement through complex 3D spaces. We introduce TANGO, the first whole-body vision-language navigation framework for language-conditioned humanoid traversal in cluttered environments. Given a natural-language instruction and egocentr

arXiv ↗ 中文全文