University of British Columbia

PhysAI Lab

Robotics, simulation
and physical AI.

We study how robots can model and interact with the physical world, led by Peter Yichen Chen at UBC Computer Science.

Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents — research result — Agentic Real2SimRobot interaction → physical world models · 2026

UBC Computer ScienceAI4Science Institute of Applied Mathematics

Research at PhysAI

We develop simulation and learning methods for robotics: recovering physical properties from interaction, modeling actuation and contact, and constructing worlds in which robots can learn.

Our work spans robot manipulation, Real2Sim, and contact-aware world models, supported by research in neural simulation, geometry, and scientific computing.

Research areas

Robotics and world models

We connect robot interaction, actuation modeling, and physical world construction to simulation and robot learning.

Neural simulation

We combine numerical methods and neural representations to simulate physical dynamics efficiently, across materials, geometries, and discretizations.

Geometry and scientific computing

We develop geometric representations and optimization tools for physical constraints, computational design, and scientific computing.

Selected research

All publications ↗

Robotics: Science and Systems (RSS) 2026 Outstanding Systems Paper Award

NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception

Zhiyang Dou, John U. Onyemelukwe, Hangxing Zhang, Heng Zhang, Minghao Guo, Yunsheng Tian, Michal Piotr Lipiec, Joshua Jacob, Chao Liu, et al.

Learned actuator dynamics for robot simulation and sensorless force perception.

Project Paper Code

arXiv preprint · 2026

Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents

Guanxiong Chen*, Qianjun Xia*, Jiawei Peng*, Heng Zhang*, Pengyu Jing*, Bole Ma*, Justin Qian, Yixian Cheng, Ziyi Jiao, Bingyang Zhou, Yiduo Qu, et al.

Recovering physics-based worlds from real interaction using vision-language agents.

PDF Paper Code Project