|
I'm a 4th year undergraduate student at UIUC . I love robots. I want to do strong science, and help people feel able to do it, too. I'm currently visiting Yilun Du 's lab. I've had the opportunity to be advised by Kris Hauser , Yunzhu Li , Maxim Likhachev . I build robots that act intelligently. I began with kinodynamic motion planning (IxG) , which assumes a reliable model of the environment. To handle broader settings without accurate models, I moved to learned dynamics for planning— graph-based neural dynamics (GBND) and pixel-space video predictors (HMA) . In practice, GBND required heavy hand-engineering for graph instantiation, and contemporary video models were not accurate or controllable enough for planning, so I pivoted to learning to act directly—focusing on modular policies and studying implicit factorization of the action distribution (FDP) and explicit factorization by sensory modality (MMPC) . This line of work crystallized a view: raw action space is the wrong abstraction. Thus, my recent research pursues action tokenization that imposes causal ordering structure on actions (OAT) , enables autoregressive reasoning over semantically meaningful actions. Currently, I am focused on principled ways to compress action signals to facilitate robotic reasoning and planning. I am also interested in robot memory, spanning implicit forms like state-space models to explicit representations such as scene graphs and maps. I view explicit and persistent memory as the essential interface for coupling planning and learning. I'm always excited to explore new ideas in robotics. Feel free to reach out if you are interested in my research or just want to chat! |
|
|
|
* indicates equal contribution. Representative papers are highlighted . |
|
Chaoqi Liu , Xiaoshen Han , Jiawei Gao , Yue Zhao , Haonan Chen , Yilun Du 2026 website / arXiv / code / blog / Ordered Action Tokenization (OAT) is an ordered action tokenization framework for autoregressive robot policies that achieves high compression, total decodability, and causal token ordering. |
|
Chaoqi Liu , Haonan Chen , Sigmund H. Høeg* , Shaoxiong Yao* , Yunzhu Li , Kris Hauser , Yilun Du IEEE Robotics and Automation Letters (RA-L), 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026 Spotlight at RSS 2025 2nd Workshop on Semantic Reasoning and Goal Understanding in Robotics [Link] website / arXiv / Factorized Diffusion Policy (FDP) is a modular robot policy framework that composes specialized diffusion components through score aggregation, enabling scalable multitask learning, interpretable behavior decomposition, and efficient task adaptation. |
|
Haonan Chen , Jiaming Xu* , Hongyu Chen* , Kaiwen Hong , Binghao Huang , Chaoqi Liu , Jiayuan Mao , Yunzhu Li , Yilun Du* , Katherine Driggs-Campbell* IEEE International Conference on Robotics and Automation (ICRA), 2026 website / arXiv / code / Multi-Modal Policy Consensus (MMPC) decomposes control across diffusion experts specialized for vision, touch, and other modalities, with a router network that adaptively balances their influence—achieving flexible multimodal fusion. |
|
Sigmund H. Høeg , Aksel Vaaler , Chaoqi Liu , Olav Egeland , Yilun Du IEEE Robotics and Automation Letters (RA-L), 2026 website / arXiv / code / Hybrid Diffusion Policy (HDP) is a long-horizon robot planning framework that composes discrete high-level plans and continuous low-level trajectories through a unified diffusion process, enabling robust multimodal behavior generation, improved decision-making over long horizons, and flexible conditioning for complex tasks. |
|
Chaoqi Liu , Yunzhu Li , Kris Hauser IEEE International Conference on Robotics and Automation (ICRA), 2026 website / arXiv / A scalable and efficient graph-based neural terrain dynamics (GBND) by introducing fine-grained adaptive and automatic particle selection. The proposed framework is both orders of magnitude efficient and more accurate than previous GBND. |
|
Lirui Wang , Kevin Zhao* , Chaoqi Liu* , Xinlei Chen 2025 website / arXiv / code / Heterogeneous Masked Autoregression (HMA) is a real-time robotic video simulation for high-fidelity and controllable interactions, leveraging masked autoregressive models and heterogeneous training. |
|
Ramkumar Natarajan , Chaoqi Liu , Howie Choset , Maxim Likhachev Robotics Science and Systems (RSS), 2024 website / arXiv / A scalable and efficient way to plan on Graphs of Convex Sets (GCS) with stronger theoretical properties. We plan on GCS using a previously developed hybrid search-optimization framework called INSAT. |
|
I have consistently maintained a perfect 4.0 GPA, excelling with top grades of A/A+ in all of my Computer Science, Mathematics, and Statistics courses. A complete list can be found here . |
|
Template credit to Jon Barron and Kaifeng Zhang |