MoonshotAI
Featured
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
Qwen-RobotNav
Qwen-RobotNav is a scalable navigation model built on Qwen3-VL that unifies multiple navigation tasks (such as instruction following, object search, tracking, autonomous driving, and embodied QA) under a single waypoint-prediction interface with a controllable observation protocol.
Stars
124
7-day growth
No data
Forks
7
Open issues
2
License
No data
Last updated
2026-06-30
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It achieves strong benchmark results across diverse navigation domains (e.g., VLN-CE, ObjectNav, autonomous driving) and demonstrates zero-shot real-world deployment on a Unitree Go2 robot with on-device inference, all while exposing a tunable observation interface that makes it suitable as a primitive for higher-level agentic systems.
Who it is for
- Robotics researchers working on navigation and embodied AI
- Autonomous systems engineers building multi-task robot controllers
- Computer vision and VLM researchers interested in scalable navigation models
- Developers of agentic systems requiring a reconfigurable waypoint predictor
Use cases
- Instruction-following indoor navigation with natural language commands
- Object search and target tracking in unknown environments
- Autonomous driving simulation with multi-view input
- Embodied question answering that requires exploration and evidence gathering
Strengths
- Unified model covering many navigation tasks (VLN, PointNav, ObjectNav, tracking, driving, EQA) without task-specific fine-tuning
- Controllable observation protocol (token budget, temporal decay, camera weights) that enables task-adaptive behavior at inference time
- Trained on 15.6M samples with trajectory supervision and vision-language co-training, showing favorable scaling from 2B to 8B parameters
- Zero-shot real-world deployment on a Unitree Go2 robot with 5.1 Hz inference speed on Jetson Thor
Considerations
- Model weights are not publicly released and there is currently no plan to release them
- Real-world validation is limited to experiments with a single robot platform (Unitree Go2) and specific environments
- Possible trade-offs between long-horizon memory and recency depending on the observation configuration, as shown in ablation studies
README quick start
Qwen-RobotNav
A Scalable Navigation Model Designed for an Agentic Navigation System
Qwen Team
📑 Technical Report |
📖 Blog |
🖥️ Demo
Welcome to the official repository of Qwen-RobotNav. Here, you can find official information about Qwen-RobotNav and post your questions (Issues).
Note: There is currently no plan to release the model weights for Qwen-RobotManip or Qwen-RobotNav. We will continue adding report resources that can be publicly released to this repository.
🎬 Demo
If the video does not render in your browser, open the direct demo preview link. For the full-length high-resolution source, open big_agent.mp4.
Feature Highlights
This blog demo highlights the key design features of Qwen-RobotNav: unified multi-domain navigation, controllable observation context, agentic tool-call style execution, and zero-shot real-world deployment.
If the feature video does not render in your browser, open the direct feature preview link. For the full-length high-resolution source, open Nav_blog_demo.mov.
💡 Introduction
Qwen-RobotNav is a scalable navigation model built on Qwen3-VL. It unifies instruction following, point-goal and object-goal navigation, target tracking, autonomous driving, and embodied question answering under a shared waypoint-prediction interface.
The key idea is to treat navigation as context modeling. Different navigation tasks share a perception-planning backbone, but they require different strategies for consuming visual history: long-horizon instruction following needs memory, target tracking needs recent high-resolution frames, object search shifts between exploration and local approach, and driving depends on multi-view short-term motion context.
Qwen-RobotNav exposes this difference as a configurable observation protocol. An upper-level planner can call the same model with different task modes and context parameters, making Qwen-RobotNav a natural navigation primitive for
Description
Official Repo for Qwen-RobotNav
Related repositories
Similar projects matched by category, topics, and programming language.
xuchonglang
Featured
investing-for-beginners
A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.
Krishnagangwal
Featured
CS-Fundamentals
A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.