JoonHo (Brian) Lee

I'm a visting scholar at ARPL Lab in UC Berkeley, where I am working on world models and distributed perception. I'm interested in building world models for robots to physically understand the world as we do. My previous research include LiDAR perception and traversability estimation for off-road autonomous navigation. I received my Master's from the University of Washington, where I was advised by Byron Boots.

Email  /  CV  /  Scholar  /  Github

profile photo

Research

Visual traversability prediction V-STRONG: Visual Self-Supervised Traversability Learning for Off-road Navigation

Sanghun Jung, JoonHo Lee, Xiangyun Meng, Byron Boots, and Alexander Lambert
ICRA, 2024  
arXiv / code
LiDAR-UDA LiDAR-UDA: Self-ensembling Through Time for Unsupervised LiDAR Domain Adaptation

Amirreza Shaban*, JoonHo Lee*, Sanghun Jung*, Xiangyun Meng, and Byron Boots
ICCV, 2023   Oral Presentation (<1.8%)
arXiv / code
TerrainNet TerrainNet: Visual Modeling of Complex Terrain for High-speed, Off-road Navigation

Xiangyun Meng, Nathan Hatch, Alexander Lambert, Anqi Li, Nolan Wagener, Matthew Schmittle, JoonHo Lee, Wentao Yuan, Zoey Chen, Samuel Deng, Greg Okopal, Dieter Fox, Byron Boots, and Amirreza Shaban
RSS, 2023
arXiv / code
RACER Project DARPA Robotic Autonomy in Complex Environments with Resiliency (RACER)

University of Washington, 2022
BEVNet Semantic Terrain Classification for Off-Road Autonomous Driving

Amirreza Shaban*, Xiangyun Meng*, JoonHo Lee*, Byron Boots, and Dieter Fox
CoRL, 2022
arXiv / code
RACER Project ARL Scalable, Adaptive, and Resilient Autonomy (SARA)

University of Washington, 2021

Miscellanea

Tech Reports

KLOCR Exploring OCR-augmented Generation for Bilingual VQA

JoonHo Lee and Sunho Park
preprint, 2025
arXiv / code