Zhenghao Peng

PhD Candidate

Los Angeles, California, United States
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
Zhenghao Peng is a CS PhD candidate at UCLA with nine years of software engineering experience, specializing in backend systems for simulation and robotics. Based in Los Angeles, he has contributed core functionality and utility tooling to the popular open-source MetaDrive driving simulator, improving shaders, map restoration, and configurable randomization to make simulations more accurate and user-friendly. His work shows a blend of research rigor and practical engineering—refining simulation logic while adding example scripts that lower the barrier for new users. Comfortable navigating complex codebases, he focuses on maintainability and reproducible experiments, an asset for teams building real-world autonomous driving stacks.
code9 years of coding experience
stackoverflow-logo

Stackoverflow

Stats
1reputation
0reached
0answers
0questions
github-logo-circle

Github Skills (7)

game-development10
python10
procedural-generation9
c-language8
algorithms8
algorithm8
cprogramming-language8

Programming languages (17)

C#JavaCSSC++CTeXVueHTML

Github contributions (5)

github-logo-circle
metadriverse/metadrive

Dec 2020 - Jan 2023

MetaDrive: Lightweight driving simulator for everyone
Role in this project:
userBack-end Developer
Contributions:4 releases, 22 reviews, 316 commits in 2 years 1 month
Contributions summary:Zhenghao primarily focused on modifying and improving the core functionalities of the driving simulator, including modifications to the shaders, and the restoration of maps, and also the addition of example scripts to improve the user experience. Moreover, the user was responsible for the implementation of various utility functions, and configuration updates, reflecting a deep understanding of the system. The contributions suggest a focus on refining the core simulation logic, ensuring accurate representation, and introducing functionalities such as support for different levels of randomization.
diversegeneralizationreinforcement-learningcomputer-visiondeep-reinforcement-learning
中国航天任务徽章大赏
Contributions:17 commits, 24 PRs, 30 pushes in 5 months
zonesthunderbirdvuegrav-plugin
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial
Zhenghao Peng - PhD Candidate