TANGO: Traversability-Aware Navigation with Local Metric Control for Topological Goals
🤖 AI Summary
Traditional robotic visual navigation relies on global 3D maps or task-specific controllers, suffering from high computational overhead and poor cross-environment generalization. To address these limitations, we propose a pure-RGB-driven, object-level topological-metric hybrid navigation framework—enabling zero-shot, long-horizon, map-free, and controller-free end-to-end navigation for the first time. Our method integrates foundation-model-based monocular depth and traversability joint estimation, object-centric topological graph construction, local metric trajectory control, and an autonomous backtracking mechanism, augmented by a dynamic mode-switching strategy for enhanced robustness. Evaluated in both simulation and real-world settings, our approach significantly outperforms state-of-the-art methods, demonstrating strong open-set generalization, real-time performance, and practical deployability.
Application Category
📝 Abstract
Visual navigation in robotics traditionally relies on globally-consistent 3D maps or learned controllers, which can be computationally expensive and difficult to generalize across diverse environments. In this work, we present a novel RGB-only, object-level topometric navigation pipeline that enables zero-shot, long-horizon robot navigation without requiring 3D maps or pre-trained controllers. Our approach integrates global topological path planning with local metric trajectory control, allowing the robot to navigate towards object-level sub-goals while avoiding obstacles. We address key limitations of previous methods by continuously predicting local trajectory using monocular depth and traversability estimation, and incorporating an auto-switching mechanism that falls back to a baseline controller when necessary. The system operates using foundational models, ensuring open-set applicability without the need for domain-specific fine-tuning. We demonstrate the effectiveness of our method in both simulated environments and real-world tests, highlighting its robustness and deployability. Our approach outperforms existing state-of-the-art methods, offering a more adaptable and effective solution for visual navigation in open-set environments. The source code is made publicly available: https://github.com/podgorki/TANGO.
Problem
Research questions and friction points this paper is trying to address.
Enables zero-shot long-horizon robot navigation without 3D maps
Integrates global topological planning with local metric trajectory control
Uses monocular depth estimation for obstacle avoidance and traversability prediction
Innovation
Methods, ideas, or system contributions that make the work stand out.
RGB-only topometric navigation pipeline
Global topological with local metric control
Auto-switching mechanism with baseline controller
🔎 Similar Papers
No similar papers found.
