TANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model
Summary
TANGO is a vision-language-action framework for humanoid robots to navigate cluttered environments using simulated training data, demonstrating state-of-the-art performance and zero-shot real-world deployment.
View Cached Full Text
Cached at: 09/09/26, 08:33 AM
Paper page - TANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model
Source: https://huggingface.co/papers/2609.09158
Abstract
TANGO is a vision-language framework that predicts whole-body joint actions for humanoid robots to navigate cluttered indoor environments using only simulated training data.
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-bodyvision-language navigationframework for language-conditioned humanoid traversal in cluttered environments. Given a natural-language instruction and egocentric RGB observations, TANGO directly predicts 29-DoFjoint-space actionsfor downstreamwhole-body control. We train TANGO entirely in simulation by synthesizing diverse collision-free traversal behaviors via global path planning, kinematic whole-body motion generation,obstacle-aware motion editing, and RL-based tracking. This pipeline provides dynamically feasible action supervision for learning language-conditioned whole-body policies. In extensive simulation experiments, TANGO demonstrates state-of-the-art performance invision-language navigation, while outperforming strong modular baselines in navigating challenging scenes requiring obstacle negotiation. Lastly, we deploy TANGO zero-shot on a Unitree G1 humanoid robot, and observe robust language-guided traversal in cluttered real-world scenes without training on any real-world navigation data.
View arXiv pageView PDFProject pageAdd to collection
Get this paper in your agent:
hf papers read 2609\.09158
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2609.09158 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2609.09158 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2609.09158 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
N_0-VTLA: Scaling Vision-Tactile-Language-Action Model with Latent Tactile Tokens
Introduces N_0-VTLA, a vision-tactile-language-action foundation model for contact-rich manipulation, featuring large-scale tactile pretraining and advantage-conditioned offline policy improvement, with strong results on real-robot and simulation benchmarks.
τ_0-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation
A hierarchical vision-language-action model improves long-horizon robot manipulation by using world-model-guided test-time search to scale computation for high-level subtask decisions.
ABot-N1: Toward a General Visual Language Navigation Foundation Model
ABot-N1 is a visual language navigation foundation model that decouples cognition from control using a slow-fast architecture with dual visual-language signals, achieving new state-of-the-art results across indoor and outdoor navigation tasks.
HumanCLAW: Can Vision-Language Models Act Through a Body?
This paper introduces HumanCLAW, an evaluation framework that decouples action decision-making from low-level execution to assess whether vision-language models can act through a physical body. Testing nine state-of-the-art VLMs on 1,218 episodes across 41 scenes, the best model achieves only a 16.8% success rate, revealing that current VLMs lack embodied self-awareness.
HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System
HiVLA introduces a hierarchical vision-language-action framework that decouples semantic planning from motor control using a diffusion transformer action expert for improved robotic manipulation. The system combines a VLM planner for task decomposition and visual grounding with a specialized DiT action expert using cascaded cross-attention, outperforming end-to-end baselines particularly in long-horizon tasks and fine-grained manipulation.