GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

No menu could be recovered. Follow the blue links in the page.

This view

  • Original page
  • New address

GeezerVison is showing btx0424.github.io — Botian XU - Robotics & Reinforcement Learning Researcher

Botian XU

Botian XU (许博添)

Hi, there. I am currently a PhD student at CUHK MAE. I received my B.S. in Computer Science from SUSTech in 2022. After that, I spent 3 gap years at Tsinghua University, with Prof. Yi Wu and Prof. Huazhe Xu, working on reinforcement learning and robotics.

Interests:

  • Reinforcement Learning for Legged Robots
  • 3D Modeling and Perception for Robot Agents

I am lucky to work closely with Liu Cao, Qingzhou Lu, and Haoyang Weng.

Google Scholar GitHub [email protected]

News

  • Sept. 2025: Our paper FACET: Force-Adaptive Control via Impedance Reference Tracking for Legged Robots is accepted for oral presentation at CoRL 2025 in Seoul, Korea.
  • Aug. 2025: I ended my journey at TEA Lab and became a PhD student at CUHK MAE.

Selected Publications

Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3D Constrained Terrains
Reinforcement Learning Perceptive Locomotion
Qingwei Ben*, Botian Xu*, Kailin Li*, Feiyu Jia, Wentao Zhang, Jingping Wang, Jingbo Wang, Dahua Lin, Jiangmiao Pang
CVPR 2026 (Highlight)
FACET: Force-Adaptive Control via Impedance Reference Tracking for Legged Robots
Reinforcement Learning Locomotion
Botian Xu*, Haoyang Weng*, Qingzhou Lu*, Yang Gao, Huazhe Xu
CoRL 2025 (Oral, top 10%)
ArtFormer: Controllable Generation of Diverse 3D Articulated Objects
3D Modeling and Generation
Jiayi Su*, Youhe Feng*, Zheng Li, Jinhua Song, Yangfan He, Botao Ren, Botian Xu
CVPR 2025 (top 15%)
OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Control
Simulation Environment Reinforcement Learning
Botian Xu*, Feng Gao*, Chao Yu, Ruize Zhang, Yi Wu, Yu Wang
IEEE RA-L & IROS 2024

Projects

OmniDrones
[GitHub] [Docs]
An efficient and flexible platform for reinforcement learning in drone control, built on Isaac Sim and supporting various multi-rotor configurations.
You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.