Liu Cao — accepted AI-conference papers

2025

Fine-Tuning Hard-to-Simulate Objectives for Quadruped Locomotion: A Case Study on Total Power Saving

Ruiqian Nai, Jiacheng You, Liu Cao, Hanchen Cui, Shiyuan Zhang, Huazhe Xu +1

ICRA 2025

Legged locomotion is not just about mobility; it also encompasses crucial objectives such as energy efficiency, safety, and user experience, which are vital for real-world applications. However, key factors such as battery power consumption and stepping noise are often inaccurately modeled or missin

Cited by 2 Source ↗code ↗Scholar ↗

2024

Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Response

Junfeng Long, ZiRui Wang, Quanyi Li, Liu Cao, Jiawei Gao, Jiangmiao Pang

ICLR 2024poster

Robust locomotion control depends on accurate state estimations. However, the sensors of most legged robots can only provide partial and noisy observations, making the estimation particularly challenging, especially for external states like terrain frictions and elevation maps. Inspired by the class…

Cited by 21 Source ↗PDF ↗code ↗Scholar ↗