Max Robotics — Global Service Robot Directory + US Certification

About

Zhaocheng Liu is a robotics researcher whose work bridges the gap between hierarchical learning, agile manipulation, and physics-inspired AI. His primary research areas include robotic manipulation, reinforcement learning, and embodied intelligence, with a particular focus on enabling robots to perform complex, long-horizon tasks. Liu’s most impactful contribution is the development of **ROMAN**, a hybrid hierarchical learning framework for solving complex sequential manipulation tasks, which has already garnered **37 citations** since its 2023 publication. This work addresses a critical challenge in embodied AI: enabling robots to execute diverse, multi-step tasks with broad manipulation skills. In a complementary vein, Liu has explored the intersection of deep learning and statistical physics, notably applying a **Deep Convolutional Generative Adversarial Network** to simulate the **Ising Model** (16 citations), demonstrating AI’s utility beyond traditional robotics. His more recent work includes a modular neural network policy for **in-flight object catching** with a robot hand-arm system, and a **kernel-based residual learning** framework for agile quadrupedal locomotion. Through these contributions, Liu is advancing the frontier of robots that can learn, adapt, and react with human-like dexterity and speed.