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

TL;DR

This paper introduces TZPP, a training-free, adaptable multi-robot navigation framework using large language models, demonstrated on quadruped and humanoid robots in varied environments.

Contribution

The paper presents TZPP, a novel zero-training, zero-simulation collaborative navigation framework for heterogeneous robots utilizing multimodal large language models.

Findings

Achieves robust navigation comparable to humans in diverse environments.

Eliminates the need for training or simulation in multi-robot coordination.

Demonstrates effectiveness on real robots in indoor and outdoor scenarios.

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