AI & ML New Capability

Achieves zero-shot, zero-training collaborative navigation between humanoid and quadruped robots.

March 24, 2026

Original Paper

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

Yaxuan Wang, Yifan Xiang, Ke Li, Xun Zhang, BoWen Ye, Zhuochen Fan, Fei Wei, Tong Yang

arXiv · 2603.21723

The Takeaway

It introduces a framework where heterogeneous robots (humanoid and dog) can collaborate in complex environments without any prior simulation or training. By leveraging multimodal LLMs for coordination, it bypasses the massive compute typically required for multi-agent robotic systems.

From the 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 environme