Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report

2026-07-08

AI Summary

This work addresses the scarcity of scalable, physically plausible motion data for quadrupedal robots and the fragility of cross-morphology motion transfer by constructing a behavior foundation integrating multi-source data—including video generation, motion capture, teleoperation, and hand-designed trajectories—and establishes, for the first time, a scaling law for quadrupedal motion tracking. The approach introduces a conditional video generation–based data pyramid, a Flow-Matching universal policy, and a three-stage privileged-to-perceptual learning framework, augmented with temporal LiDAR memory and terrain prediction supervision. This enables zero-shot tracking of unseen motions and robust locomotion across diverse terrains. The system demonstrates product-level behavioral intelligence in urban autonomous navigation and multimodal companion interaction, supporting coordinated multi-policy execution, smooth transitions, energy-efficient control, and safety assurance.

Abstract

In embodied intelligence systems, the motion controller serves as the critical bridge between semantic reasoning and physical execution. Humanoid control has progressed rapidly through large-scale human motion-capture data and motion-tracking paradigm. However, producing quadruped robots motion corpora with scalability and physical feasibility faces more fundamental obstacles: animal motion data is scarce, and cross-embodiment retargeting remains fragile. We present ABot-C0, a generalist motion-control system for quadruped robots that establishes three complementary behavior foundations: a scalable multi-source motion-data pipeline, robust policy learning across motion tracking, locomotion, and scene interaction, and a unified deployment stack for reliable real-world operation. Fundamentally, we construct a data pyramid through conditional video-generation synthesis, annotated motion capture, teleoperation and human design, producing 16,074 physically feasible motion clips as the data foundation for various motion learning demands. We then train a Flow-Matching generalist policy that demonstrates for the first time quadruped motion tracking scaling law that its performance improves consistently as training scales up, with zero-shot capability to track unseen motions. Then, we push a step further for robust all-terrain traversal locomotion by adopting a three-stage privileged-to-perceptive framework with temporal LiDAR memory and terrain-predictive supervision. Collectively, these components form a motion generalist that coordinates multi-policy execution, smooth behavior transitions, energy-efficient control, and safety mechanisms for real-world deployment. Extensive experiments on urban-terrain autonomous navigation and companion-style multimodal interaction demonstrate that quadruped robots move beyond single-function demos toward product-level behavioral intelligence.

Problem

• quadruped robots
• motion data scarcity
• cross-embodiment retargeting
• behavioral intelligence
• scalable motion control

Innovation

• quadruped robot
• motion generalist
• scaling law
• multi-source motion data
• privileged-to-perceptive learning