--- title: 鄭聖文 categories: User ... 簡介 ==== - 2025-2027 德州大學奧斯汀分校 電腦科學碩士 - 2022-2024 國立臺灣大學 電機所博士生 (肄) - 2019-2021 國立陽明交通大學 機器人碩士 - 2015-2019 靜宜大學 資訊工程學系 - 2013-2018 非在校生參與成大航太、資工及工科系之研究活動 - 個人網頁: [shengwen-tw.github.io](https://shengwen-tw.github.io/) 專長 ==== - 機器人系統、無人飛行器、無人地面載具 - 動態系統與控制、數值最佳化、科學計算 - 嵌入式系統、即時作業系統、I/O 虛擬化 工作經驗 ======= - 2024-Now [NVIDIA](https://www.nvidia.com/zh-tw/) - 2018-2021 [奧榮科技](https://www.avilon.co/?lang=zh) 文章 ==== - [California Trip, 2026](https://shengwen-tw.github.io/posts/cal2026/) - [Open Source Summit North America 2026](https://shengwen-tw.github.io/posts/ossna2026/) - [Embedded Open Source Summit 2024](https://shengwen-tw.github.io/posts/20240416_eoss/) 主要作品 ======= - [NCRL-Flight-Control](https://www.youtube.com/watch?v=hBBe1Kj82B4): 多軸飛行器飛控，技術包含非線性控制、慣性導航、SLAM 及軌跡規劃。產學合作授予[國家太空中心 (TASA)](https://www.tasa.org.tw/) - [UrsusPilot](https://www.youtube.com/watch?v=_DsNQWP7UXo): 2013–2015 年期間參與之四軸飛行器專案。原核心成員來自成大航太林清一實驗室、後續創辦奧榮科技 - [PU-01](https://www.youtube.com/watch?v=vZy3Hgsk0nU): 雙尾桿後推式定翼機設計。成大航太林清一實驗室指導下完成 [[簡報]](https://drive.google.com/file/d/1hEJ8q8cbePwxY358UeMr3Z0nmIqtdnKo/view) - [Tenok](https://github.com/tenok-rtos/tenok): Linux-style 的即時作業系統，適用於機器人與物聯網應用 [[共筆]](https://hackmd.io/@shengwen/tenok) [[影片]](https://www.youtube.com/watch?v=byWihWcMP00) 開放原始碼 ========= - [semu](https://github.com/sysprog21/semu): 增加 GPU、Keyboard、Mouse、RNG、Block device 的 VirtIO 虛擬化 - [DirectFB2](https://github.com/directfb2/DirectFB2): 修正 RV32 相容性問題及 DRM 圖層渲染問題 - [Mado](https://github.com/sysprog21/mado): 增加 Linux framebuffer device 的支援 **Upstream:** - [Linux kernel](https://www.kernel.org/): 修正 Linux RV32 KVM PMU（Performance Monitoring Unit）的 out-of-bounds read 問題 [[Patch]](https://patchwork.ozlabs.org/project/kvm-riscv/patch/20260626054051.3360865-1-shengwen1997.tw@gmail.com/) - [glibc](https://sourceware.org/glibc/): 修正 RV32 libthread_db 上使 GDB 不正確解析 thread pointer 的問題 [[Patch]](https://inbox.sourceware.org/libc-alpha/20260623180252.2400811-1-shengwen1997.tw@gmail.com/T/#u) 數值模擬 ======= 四軸飛行器: - [rotor-bench](https://github.com/shengwen-tw/rotor-bench): SE(3) 公平基準下的四軸飛行器控制器 Benchmark (幾何控制、最佳控制、強健控制、模型預測控制、強化學習) - [四軸飛行器幾何控制](https://github.com/shengwen-tw/qaudrotor_geometry_ctrl_simulator): 穩定性經 Lyapunov theory 證明的 SE(3) 的非線性控制方法 [[簡報]](https://drive.google.com/file/d/1ZyqSpjSTDKI8-ypz8bvnjUU6N7ipMHDt/view?usp=sharing) - [四軸飛行器 LQR 控制](https://github.com/shengwen-tw/quadrotor_lqr_simulator): SDA [(保結構加倍收斂法)](https://shengwen-tw.github.io/posts/sda/) 求解 LQR / Riccati 控制問題. 演算法具有平方收斂速度 [[技術報告]](https://drive.google.com/file/d/1u0T5Wb_mH0NUBVetOBdvIHdeCOP8Wde6/view?usp=sharing) - [四軸飛行器 H∞ 強健控制](https://github.com/shengwen-tw/quadrotor-h-infty-ctrl-simulator): 強健最佳控制，最小化擾動輸入至輸出增益 [[簡報]](https://drive.google.com/file/d/1573Td07_vohtVan2gHrCwDmQyY9ihr_w/view?usp=drivesdk) 馬達控制: - [三相馬達速度控制](https://github.com/shengwen-tw/bldc-control-simulator): 三相 BLDC 馬達速度控制模擬，包含 Field-Oriented Control（FOC）與方波控制 路徑規劃: - [Minimum-snap trajectory generation](https://github.com/shengwen-tw/minimum-snap-traj-matlab): 透過最小化位置四階導數（snap）產生平滑軌跡 - [Rapidly-Exploring Random Tree (RRT)](https://github.com/shengwen-tw/rrt-matlab): 基於隨機樹搜尋的路徑規劃演算法，用於避開環境中的障礙物 論文 ==== - 2027 - RotorBench: A Unified SE(3) Benchmark for Quadrotor Controllers under Disturbance and Model Uncertainty - 2026 - [Data-Driven Estimation of Quadrotor Motor Efficiency via Residual Minimization](https://arxiv.org/abs/2510.11388) - 2023 - [A Computationally Efficient GNSS/INS Design of Multirotor based on Error-state Kalman Filter](https://ieeexplore.ieee.org/abstract/document/10354209) - 2022 - [Robust State-Feedback H∞ Control of Quadrotor](https://ieeexplore.ieee.org/document/9969787) - 2018 - [Puyuma: Linux-based RTOS Experimental Platform for Constructing Self-Driving Miniature Vehicles](https://link.springer.com/chapter/10.1007/978-3-030-01174-1_75) 演講 ==== 國際會議: - [Demystifying VirtIO-GPU: Building a Graphics Virtualization Bridge from Scratch](https://osselcna2026.sched.com/event/2JQrw?fbclid=IwY2xjawQwdRlleHRuA2FlbQIxMABicmlkETFmMUhlSUdFWHJMMkc1TmdPc3J0YwZhcHBfaWQQMjIyMDM5MTc4ODIwMDg5MgABHoUlvXLBtUd4yALsr0xK-GXrMdikjN4z-xYAb6aOeQ4xLDfChkMGAWPbsUsT_aem_D5jjzd_PcbErdv7cCjhBXw) (OSSNA 2026) - [Crafting a Vision-Aided Software Stack for UAV](https://eoss24.sched.com/event/1aBF7) (EOSS 2024) 社群會議: - On the Tenth Anniversary of AlphaGo - An Introduction to Reinforcement Learning and Planning (Sciwork Conference 2026) - [Learning to Fly in Simulation: Quadrotor Reinforcement Learning from First Principles](https://drive.google.com/file/d/1c_4MA8ceyZF0MGvRW2RbgGcnUMv3Eu-h/view?usp=drive_link) (MOPCON 2026) - [The Illusion of Hardware - How Modern Virtual Machines Work](https://drive.google.com/file/d/1OwC0eo8sWeRmDrPONtk9EZb1jCm9hCAa/view?usp=sharing) (COSCUP 2026) - [From Optimal Control to Reinforcement Learning for Quadrotor Drones](https://drive.google.com/file/d/1Y3XgF9OthbjNDhyO93OfG7P_fOf9K6aa/view) (Sciwork Seminar 2026) - [Building a Quadrotor Simulator with Python - Modeling, Simulation, and Control](https://drive.google.com/file/d/1Oc-OfTaBOS4-Ut4LMXkFd4vc9sJBr5s8/view?fbclid=IwY2xjawM0sS9leHRuA2FlbQIxMABicmlkETFQS240alZ0d0pCS0hXRXN3AR4c9Y9pQykGagwCiAT0a84OlyRuoPozOFF2ng8ZyYwwvKGd4m7W91oPA3xw9A_aem_5FYP7iKGktVP1OJBBpa-mA) (OpenTechConf 2025) - [Trends in Machine Learning for Unmanned Aerial Vehicle Applications](https://drive.google.com/file/d/1UmSeU8Y63s4cASBFNWM_zi5ll2J9EIJx/view?fbclid=IwY2xjawGLSe9leHRuA2FlbQIxMAABHX9AjWq_vX6WXNQYPfsQp-BUFIM44uh6MBCdLFP4OAEdUsAF8zQptxDcdQ_aem_uvY1jloybOcTQEWV687_BA) (MOPCON 2024 Keynote) - [Creating a Linux-like real-time operating system for quadrotor drones](https://drive.google.com/file/d/16S8ZRC-lhT15CXwWIy-RIIWXl5Ertqo5/view) (COSCUP 2024) - [Tenok: Build a real-time operating system for Robotics](https://drive.google.com/file/d/1p8YJVPVwFAEknMXPbXzjj0y0p5qcqT2T/view) (COSCUP 2023)