Changliu Liu
Associate Professor
- Pittsburgh PA UNITED STATES
Changliu Liu's work focuses on assured autonomy, specifically trustworthy robotics systems that work with people.
Biography
Areas of Expertise
Media Appearances
Could robots play sports professionally? Carnegie Mellon researcher says yes
TribLive online
2026-07-21
An expert on humanoid robot motion learning, Liu leads the Intelligent Control Lab at Carnegie Mellon University’s Robotics Institute, where she’s an associate professor.
Liu is teaching robots to move dynamically for sports and entertainment. Factory robots have a single purpose. She is working to make robots that adjust and maneuver in real time.
The AI tool that could make manufacturing faster and more efficient – by using LEGO bricks
Pittsburgh Business Times online
2025-08-25
“This could be a huge benefit to the manufacturing world,” claims Changliu Liu, Ph.D., an associate professor at the Robotics Institute. “It takes a long time to turn ideas into a physical design and prototype. But, if you can integrate generative AI into the process, it can significantly improve efficiency and reduce the roadblocks to kicking off projects.”
Carnegie Mellon University students develop robot to mimic human movements
WTAE ABC News Pittsburgh tv
2024-11-18
"Suppose we have a very narrow door and narrow crowded space. Can the robot safely navigate through it without hurting itself or damaging the environment?" said Changliu Liu, assistant professor at CMU.
Media
Social
Education
University of California at Berkeley
Ph.D.
Engineering
2017
University of California at Berkeley
M.S.
Engineering
University of California at Berkeley
M.S.
Mathematics
Tsinghua University
B.S.
Engineering and Economics
2012
Articles
Trends in motion prediction toward deployable and generalizable autonomy: a revisit and perspectives
Foundations and Trends® in RoboticsLetian WangCorresponding Author; Marc-Antoine Lavoie; Sandro Papais; Barza Nisar; Yuxiao Chen; Wenhao Ding; Boris Ivanovic; Hao Shao; Abulikemu Abuduweili; Evan Cook; Yang Zhou; Peter Karkus; Jiachen Li; Changliu Liu; Marco Pavone; Steven L. Waslander
2026-04-21
Motion prediction, recently popularized under the term world models, refers to anticipating the future states of agents or the future evolution of a scene, which is rooted in human cognition to bridge perception and decision-making, enabling us to anticipate, adapt, and act within an everchanging world.
Implicit Safe Set Algorithm for Provably Safe Reinforcement Learning
Journal of Artificial Intelligence ResearchW Zhao, F Li, T He, C Liu
2025-12-14
Deep reinforcement learning (DRL) has demonstrated remarkable performance in many continuous control tasks. However, a significant obstacle to the real-world application of DRL is the lack of safety guarantees.
VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation
arXivTairan He, Zi Wang, Haoru Xue, Qingwei Ben, Zhengyi Luo, Wenli Xiao, Ye Yuan, Xingye Da, Fernando Castañeda, Shankar Sastry, Changliu Liu, Guanya Shi, Linxi Fan, Yuke Zhu
2025-11-19
A key barrier to the real-world deployment of humanoid robots is the lack of autonomous loco-manipulation skills. We introduce VIRAL, a visual sim-to-real framework that learns humanoid loco-manipulation entirely in simulation and deploys it zero-shot to real hardware.
Time-Optimal Trajectory Generation with Multi-level Continuous Kinodynamics Constraints
IEEERuixuan Liu, Changliu Liu, Jessica Leu
2025-10-19
Time-optimal trajectory generation (TOTG) is critical in robotics applications to minimize travel time and increase robot task efficiency.
ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills
arXiv preprint2025-02-03
Humanoid robots hold the potential for unparalleled versatility in performing human-like, whole-body skills. However, achieving agile and coordinated whole-body motions remains a significant challenge due to the dynamics mismatch between simulation and the real world.