University of California, Riverside

Motion Planning Lab

Understanding motion.
Building intelligent worlds.

Research in robotics, computer graphics, and AI — from navigating human crowds to learning lifelike movement.

  • Robot NavigationPhysics-Based Character Control
  • Motion SynthesisCrowd SimulationPath Planning
Explore our research Meet the lab
Physics-based basketball character control
Learning to move
Simulated crowd navigation
Navigating together
Human interactions with a service robot
Robots among people

Recent Projects

Crowds interacting in a virtual campus environment

Gen-C: Populating Virtual Worlds with Generative Crowds

Andreas Panayiotou, Panayiotis Charalambous, and Ioannis Karamouzas
Proceedings of the ACM on Computer Graphics and Interactive Techniques, 9(1), I3D, 2026.

I3D 2026 Best Paper Award

Generating high-level crowd behaviors and interactions from text descriptions.

[pdf] [project]

TERRAN routing plan with five colored vehicle routes, customers, depot, and charging stations

TERRAN: A Transformer-Based Electric Vehicle Routing Agent for Real-Time Adaptive Navigation

Maojie Tang, Nanpeng Yu, Ioannis Karamouzas, and Zuzhao Ye
IEEE Transactions on Automation Science and Engineering, 23:3889–3901, 2026.

Learning feasible electric vehicle delivery routes with battery, charging, and time-window constraints.

[pdf] [code]

More from the lab

Learning to Ball: Composing Policies for Long-Horizon Basketball Moves

Learning to Ball: Composing Policies for Long-Horizon Basketball Moves

Pei Xu, Zhen Wu, Ruocheng Wang, Vishnu Sarukkai, Kayvon Fatahalian, Ioannis Karamouzas, Victor Zordan, and C. Karen Liu
ACM Transactions on Graphics, (SIGGRAPH Asia), 2025.
[pdf] [code]
A Study in Zucker: Insights on Interactions Between Humans and Small Service Robots

A Study in Zucker: Insights on Interactions Between Humans and Small Service Robots

Alex Day Xu and Ioannis Karamouzas
IEEE Robotics and Automation Letters 9(3), 2024.
Also in IEEE ICRA@40 , 2024.
[pdf] [project]
AdaptNet: Policy Adaptation for Physics-Based Character Control

AdaptNet: Policy Adaptation for Physics-Based Character Control

Pei Xu, Kaixiang Xie, Sheldon Andrews, Paul G. Kry, Michael Neff, Morgan McGuire, Ioannis Karamouzas, and Victor Zordan
ACM Transactions on Graphics, 42(6),(SIGGRAPH Asia), 2024.
[pdf] [project] [code]
Context-Aware Timewise VAEs for Real-Time Vehicle Trajectory Prediction

Context-Aware Timewise VAEs for Real-Time Vehicle Trajectory Prediction

Pei Xu, Jean-Bernard Hayet, and Ioannis Karamouzas
IEEE Robotics and Automation Letters, 8(9), 2023.
Also in IEEE International Conference on Robotics and Automation , 2024.
[pdf] [project] [code]
Composite Motion Learning with Task Control

Composite Motion Learning with Task Control

Pei Xu, Xiumin Shang, Victor Zordan, and Ioannis Karamouzas
ACM Transactions on Graphics, 42(4),(SIGGRAPH), 2023.
[pdf] [project] [code]
SocialVAE: Human Trajectory Prediction using Timewise Latents

SocialVAE: Human Trajectory Prediction using Timewise Latents

Pei Xu, Jean-Bernard Hayet, and Ioannis Karamouzas
In the 17th European Conference on Computer Vision (ECCV 2022), 2022.
[pdf] [project] [code]
Human-Inspired Multi-Agent Navigation using Knowledge Distillation

Human-Inspired Multi-Agent Navigation using Knowledge Distillation

Pei Xu and Ioannis Karamouzas
In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021), 2021.
[pdf] [project] [code]
NH-TTC: A gradient-based framework for generalized anticipatory collision avoidance

NH-TTC: A gradient-based framework for generalized anticipatory collision avoidance

Bobby Davis, Ioannis Karamouzas, and Stephen J. Guy,
In Robotics: Science and Systems (RSS 2020), 2020.
[pdf] [project] [code]

Prospective Students

We welcome motivated students who are excited about robotics, computer graphics, and embodied AI. If you are interested in joining the Motion Planning Lab 🤖 as a Ph.D. student, consider applying to the UCR's Ph.D. program in CS and mention Prof. Ioannis Karamouzas as a potential advisor.

If you would like to reach out, please read David Evans' advice on contacting professors about graduate school. Please write two brief paragraphs in your own words: one explaining why you want to pursue a PhD and how your interests connect to our lab, and one describing your current work or research experience. Do not send AI-generated emails.

Sponsors

We would like to thank Amazon, the National Science Foundation, Roblox, and University of California, Riverside for supporting our research.

Web Analytics