Can a Robot Walk the Robotic Dog: Triple-Zero Collaborative Navigation for Heterogeneous Multi-Agent Systems

2026-03-23

AI Summary

This work proposes the Triple Zero Path Planning (TZPP) framework to address the challenge of collaborative navigation in heterogeneous multi-robot systems under conditions of zero training, zero prior knowledge, and zero simulation. TZPP employs a coordinator–explorer architecture, wherein a humanoid robot (Unitree G1) acts as the task coordinator while a quadrupedal robot (Go2) autonomously explores feasible paths guided by a multimodal large language model. To the best of our knowledge, this is the first demonstration of real-world heterogeneous robotic collaboration achieving “zero training, zero priors, zero simulation” navigation. Experimental results across diverse indoor and outdoor environments show that TZPP achieves human-level navigation efficiency and strong generalization, significantly enhancing the system’s deployability, adaptability, and robustness in unknown settings.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

We present Triple Zero Path Planning (TZPP), a collaborative framework for heterogeneous multi-robot systems that requires zero training, zero prior knowledge, and zero simulation. TZPP employs a coordinator--explorer architecture: a humanoid robot handles task coordination, while a quadruped robot explores and identifies feasible paths using guidance from a multimodal large language model. We implement TZPP on Unitree G1 and Go2 robots and evaluate it across diverse indoor and outdoor environments, including obstacle-rich and landmark-sparse settings. Experiments show that TZPP achieves robust, human-comparable efficiency and strong adaptability to unseen scenarios. By eliminating reliance on training and simulation, TZPP offers a practical path toward real-world deployment of heterogeneous robot cooperation. Our code and video are provided at: https://github.com/triple-zeropp/Triple-zero-robot-agent

Problem

• heterogeneous multi-agent systems
• collaborative navigation
• zero-training
• zero-prior-knowledge
• zero-simulation

Innovation

• Triple Zero Path Planning
• heterogeneous multi-agent systems
• zero training
• multimodal large language model
• coordinator-explorer architecture