Summary
TANGO is a whole-body vision-language navigation framework for humanoid robots traversing cluttered indoor environments. Unlike conventional 2D path-planning approaches, TANGO handles continuous geometry-aware whole-body adaptation, including coordinated arm placement, torso adjustment, and gait modulation for collision-free movement. Given a natural-language instruction and egocentric RGB observations, it directly predicts 29-DoF joint-space actions for downstream whole-body control. The model is trained entirely in simulation by synthesizing diverse collision-free traversal behaviors through global path planning, kinematic whole-body motion generation, obstacle-aware motion editing, and RL-based tracking, providing dynamically feasible action supervision. In simulation, TANGO achieves state-of-the-art vision-language navigation performance and outperforms strong modular baselines in scenes requiring obstacle negotiation. It was deployed zero-shot on a Unitree G1 humanoid robot, showing robust language-guided traversal in cluttered real-world scenes without any real-world navigation data. Paper: arXiv 2609.09158.
Overview
- Research areas: cs.RO, cs.AI
- Authors: Anqi Li, Yuxin Chen, Zhaobo Li, Zhuo Cao, Junli Ren, Masayoshi Tomizuka, Dhruv Shah
- Published: 2026-09-08
- arXiv: 2609.09158
Abstract
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 egocentric RGB observations, TANGO directly predicts 29-DoF joint-space actions for downstream whole-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 in vision-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.Key points
- TANGO addresses humanoid navigation in cluttered indoor environments as a whole-body, language-conditioned problem rather than 2D path planning.
- It predicts 29-DoF joint-space actions directly from natural-language instructions and egocentric RGB observations.
- Training data is synthesized entirely in simulation via global path planning, kinematic whole-body motion generation, obstacle-aware motion editing, and RL-based tracking.
- TANGO achieves state-of-the-art vision-language navigation results and beats modular baselines in obstacle-negotiation scenarios.
- Zero-shot deployment on a Unitree G1 humanoid robot yields robust language-guided traversal in cluttered real-world scenes, with no real-world navigation training data.
*Auto-collected on 2026-09-10*
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/178634673