Haoyang Fan
Tech Lead And Manager Of Planning And Control Algorithms Team at NIO
Sunnyvale, California, United States
Summary
🤩
Rockstar🎓
Top SchoolHaoyang Fan is a tech lead and manager of a planning and control algorithms team at NIO with eight years of industry experience building autonomous driving software. He has a strong academic foundation with a PhD in Statistics and a CS master's from University of Wisconsin–Madison, and progressed through engineering and architect roles at Baidu and Aurora before taking leadership at NIO. Haoyang combines research rigor and practical engineering, contributing to the high-profile Apollo open-source autonomous driving platform by improving planning modules, dynamic programming road graphs, and trajectory cost functions. He excels at translating probabilistic models and data-driven insights into robust real-world planning systems and has experience defining protobuf interfaces for autotuning decision-making. Based in Sunnyvale, he brings a rare mix of statistical depth and hands-on backend implementation to production AV stacks.
8 years of coding experience
10 years of employment as a software developer
Doctor of Philosophy (PhD) Statistics, Doctor of Philosophy (PhD) Statistics at University of Wisconsin-MadisonBachelor of Science (BS) Mathematical Statistics and Probability, Bachelor of Science (BS) Mathematical Statistics and Probability at Peking University
English, Chinese
Github Skills (5)
c-language10
cprogramming-language10
protobuffer10
autonomous-driving10
protobuf10
Programming languages (1)
Github contributions (5)
ApolloAuto/apollo
Jul 2017 - Oct 2018
An open autonomous driving platform
Role in this project:
Back-end Developer
Back-end DeveloperContributions:47 commits, 7 PRs, 2 pushes in 1 year 2 months
Contributions summary:Haoyang primarily contributed to the `apolloauto/apollo` repository by fixing bugs and implementing features related to the planning module, particularly within the `dp_road_graph.cc` file and `trajectory_cost.cc`. The changes included addressing issues in the dynamic programming road graph, refining the cost calculation for trajectories, and integrating reference line functions for lane width calculations. Furthermore, the user modified and introduced new protobuf definitions related to autotuning, suggesting involvement in improving the planning module's decision-making capabilities.
autonomousmachine-learningautonomyautonomous-drivingapollo
fanhaoyang002/apollo
Oct 2017 - Sep 2018
An open autonomous driving platform
Contributions:16 pushes, 5 branches in 10 months
autonomousmachine-learningautonomous-drivingmavlinkdriving
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.