- Việc làm
CVTạo CV online chuyên nghiệp, miễn phí
PortfolioTrình bày kỹ năng chuyên môn và dự án đã thực hiện một cách sinh động, trực quan.CVTạo CV online chuyên nghiệp, miễn phíTạo CVTạo CV online chuyên nghiệp, miễn phíMẫu CVTruy cập kho mẫu CV online ấn tượng, chuẩn quốc tế.CV mẫuTham khảo các CV mẫu đẹp đã được người dùng CakeResume ứng tuyển thành công.Cẩm nang nghề nghiệpTìm hiểu cách viết CV cho từng ngành nghề và vị trí.Trợ giúp viết CVTham khảo lời khuyên từ các chuyên gia tuyển dụng của CakeResume.- Kho tài nguyênCẩm nang ứng viênThế giới công sởVề đối tácCẩm nang doanh nghiệpVề CakeResumeBài viết nổi bật
- Tuyển dụng
- Tải app CakeResume
CakeResume Talent Search
Kế hoạch tuyển dụng đơn giản và hiệu quả nhất
Tìm kiếm 40k+ CV và chủ động liên hệ với ứng viên để đạt hiệu quả tuyển dụng cao hơn. Sự lựa chọn của hàng trăm công ty.
- Duyệt tất cả kết quả tìm kiếm
- Bắt đầu trò chuyện không giới hạn
- CV chỉ có thể truy cập bởi các công ty trả phí
- Xem địa chỉ email và số điện thoại của người dùng
Definition of Reputation Credits
許修瑋 Hsu Hsiu
I am a motivated and results-driven person currently contributing to the self-driving department at the Industrial Technology Research Institution (ITRI) in Taiwan. My expertise lies in developing self-driving vehicle behavior, maintaining scenario simulation systems, creating tools for self-driving system testing, and problem-solving during field tests. I have gained valuable experience and expertise in deep reinforcement learning and deep learning during my master's degree, allowing me to stay well-versed in the latest advancements in self-driving technology.
https://www.linkedin.com/in/hsiu-wei-hsu-49516271/
Work Experience
Education
M.Eng, Dept. of Mechanical Engineering, National Chiao Tung University, Hsinchu, Taiwan, 2018 - 2020.
B.S.Eng, Dept. of Mechanical Engineering, National Chiao Tung University, Hsinchu, Taiwan, 2014 - 2017.
Skills
Programming Languages
Python, C/C++, Arduino, Visual Basic 6
Robotic Systems
Robot Operating System (ROS), Gazebo, Carla, Control System, Behavior Tree
Deep Learning Frameworks
PyTorch, Tensorflow, Keras, Keras-rl, OpenAI-Gym, OpenAI-baselines, stable-baselines
Operating Systems
Linux (Ubuntu), macOS
Software Tools and Packages
Tools: Docker, Git, SVN, GitHub Copilot, MySQL, Markdown, Latex, Regular Expression, ChatGPT
Python Packages: NumPy, Requests, FastAPI, Matplotlib, cv2, unittest, Pygame, Pyglet, BeautifulSoup4
C++ Libraries: behavior_tree_cpp_v3, Box2D
Soft Skills
Attention to detail, Teamwork, Leadership, Responsibility, Time management, TOEIC - 910
Projects
Pending Patent: Electronic Device and Method for Determining Scenario Data of Self-Driving Car, 2022-
keywords: Scenario Search, Self-Driving, Operational Design Domain (ODD)
- Provide a solution on finding operational design domain (ODD) of a self-driving system, which represents a significant contribution to the field of autonomous vehicles
- Leading a team of three NYCU master students to implement the first stage of the entire system.
- Leveraging multiple optimization techniques and deep learning concepts to enable precise scenario understanding, scenario searching and ODD defining.
Enhanced Parking Behavior for the Self -Driving System, 2023
keywords: Behavior Tree, Self-Driving, ROS
- Revamped the parking module of a self-driving system to overcome sensor occlusion challenges and optimize parking space selection based on occupancy to enhance its ability to navigate through occluded environments.
- Improving the overall parking performance of the self-driving system.
Refactor of Simulation System, 2020-
keywords: Scenario Simulation, Box2D, Carla, ROS, Self-Driving, SUMO, MR-ViL
- Restructuring the simulation system architecture to ensure effortless integration of different physics engines (Box2D and CARLA).
- Successfully integrating the traffic flow generator SUMO into the simulation system, enabling realistic traffic scenarios.
- Refactor the simulation system to accommodate parallel operation of diverse self-driving algorithms.
- Developing a Mixed-Reality Vehicle-in-the-Loop (MR-ViL) capability based on the simulation system, enabling realistic testing and validation of self-driving systems.
Innovative Toolset for Efficient Self-Driving Vehicle Testing and Analysis, 2020-
keywords: ROS, Self-Driving, Google Map API, ChatGPT
- Creation of tools that enable the replay of real-world scenarios encountered during field tests, facilitating iterative improvements to the self-driving system.
- Development of sophisticated analysis tools capable of evaluating camera occlusion caused by road geometry using HD Maps. These tools were successfully deployed and utilized in our Australia project.
- Integration of the Google Maps API into a specialized tool to estimate the power consumption of electric vehicles based on specific routes, cargo weights, and power models.
- Developed a custom Sublime plugin with the help of ChatGPT that provides users with the ability to visualize the structure of a behavior tree directly from the tree construction .cpp file. This plugin offers a seamless integration within the Sublime Text editor, allowing users to gain a comprehensive understanding of the behavior tree's hierarchical organization.
Researches
Image-Based Control of Quadrotors Using Deep Reinforcement Learning, Jan 2018 ~ 2020
keywords: PyTorch, TD3, RNN, VAE, Markov Decision Process, Quadcopter, DRL
- A project of the Ministry of Science and Technology leads by Prof. Jen-Hui Chuang.
- The goal of the DRL controller was to control the quadrotor with forward-looking images to pass gates with different sizes.
Deep Reinforcement Learning-Based Mapless Motion Planning
keywords: Tensorflow, keras-rl, DDPG, pyglet, DRL
- Utilizing an MDP model to address the challenging problem of mapless motion planning with limited local information.
- Introducing a sub-optimal numerical expert as a demonstration to guide the DRL agent towards discovering improved policies.
Enhancing Shoe-Making Production Line Automation Through Shape Forming and Board Lasting Automation, Dec 2017 ~ Jul 2018
keywords: Scikit-Learn, Random Forest, OpenCV, Machine Learning
- An industry-university cooperation project aimed to enhance the automation of shoe-making production line.
- My part was to correct the position and orientation of unformed shoes feeding by a 6-axis robot arm.
Gate Pose Estimation Using PilotNet, Jul 2019 ~ Dec 2019
keywords: Deep Learning, RVIZ, ROS, CNN
- Utilizing a single image to estimate the position and pose of gates in the body frame.
- Leveraging the power of PilotNet, a proven deep learning model, to achieve high accuracy in gate pose estimation.
Side Projects
Ticket Monitor
keywords: Line Bot, Beautiful Soup, UI
A project that automates the process of tracking user-assigned events on ticket-selling websites. Objective of the project is to notify users via Line notification where tickets become available due to users ordering but not completing the payment within the specified time frame.
Project Link:
Lan-NCTU
keywords: Midi Protocol, MCU, VCV Rack
A modern midi instrument with RGB programmable lights patterns and 9DOF imu sensor.
Project Link:
https://github.com/showaykerker/lan_nctu
Home Security Project
keywords: IOT, Flask, RPi, MCU, Line Bot
A home security project that monitors unauthorized door opening event constructed by Linkit 7697, Raspberry Pi, and IFTTT service.
Project Link:
https://github.com/showaykerker/Linkit7697_DoorMonitor
許修瑋 Hsu Hsiu
I am a motivated and results-driven person currently contributing to the self-driving department at the Industrial Technology Research Institution (ITRI) in Taiwan. My expertise lies in developing self-driving vehicle behavior, maintaining scenario simulation systems, creating tools for self-driving system testing, and problem-solving during field tests. I have gained valuable experience and expertise in deep reinforcement learning and deep learning during my master's degree, allowing me to stay well-versed in the latest advancements in self-driving technology.
https://www.linkedin.com/in/hsiu-wei-hsu-49516271/
Work Experience
Education
M.Eng, Dept. of Mechanical Engineering, National Chiao Tung University, Hsinchu, Taiwan, 2018 - 2020.
B.S.Eng, Dept. of Mechanical Engineering, National Chiao Tung University, Hsinchu, Taiwan, 2014 - 2017.
Skills
Programming Languages
Python, C/C++, Arduino, Visual Basic 6
Robotic Systems
Robot Operating System (ROS), Gazebo, Carla, Control System, Behavior Tree
Deep Learning Frameworks
PyTorch, Tensorflow, Keras, Keras-rl, OpenAI-Gym, OpenAI-baselines, stable-baselines
Operating Systems
Linux (Ubuntu), macOS
Software Tools and Packages
Tools: Docker, Git, SVN, GitHub Copilot, MySQL, Markdown, Latex, Regular Expression, ChatGPT
Python Packages: NumPy, Requests, FastAPI, Matplotlib, cv2, unittest, Pygame, Pyglet, BeautifulSoup4
C++ Libraries: behavior_tree_cpp_v3, Box2D
Soft Skills
Attention to detail, Teamwork, Leadership, Responsibility, Time management, TOEIC - 910
Projects
Pending Patent: Electronic Device and Method for Determining Scenario Data of Self-Driving Car, 2022-
keywords: Scenario Search, Self-Driving, Operational Design Domain (ODD)
- Provide a solution on finding operational design domain (ODD) of a self-driving system, which represents a significant contribution to the field of autonomous vehicles
- Leading a team of three NYCU master students to implement the first stage of the entire system.
- Leveraging multiple optimization techniques and deep learning concepts to enable precise scenario understanding, scenario searching and ODD defining.
Enhanced Parking Behavior for the Self -Driving System, 2023
keywords: Behavior Tree, Self-Driving, ROS
- Revamped the parking module of a self-driving system to overcome sensor occlusion challenges and optimize parking space selection based on occupancy to enhance its ability to navigate through occluded environments.
- Improving the overall parking performance of the self-driving system.
Refactor of Simulation System, 2020-
keywords: Scenario Simulation, Box2D, Carla, ROS, Self-Driving, SUMO, MR-ViL
- Restructuring the simulation system architecture to ensure effortless integration of different physics engines (Box2D and CARLA).
- Successfully integrating the traffic flow generator SUMO into the simulation system, enabling realistic traffic scenarios.
- Refactor the simulation system to accommodate parallel operation of diverse self-driving algorithms.
- Developing a Mixed-Reality Vehicle-in-the-Loop (MR-ViL) capability based on the simulation system, enabling realistic testing and validation of self-driving systems.
Innovative Toolset for Efficient Self-Driving Vehicle Testing and Analysis, 2020-
keywords: ROS, Self-Driving, Google Map API, ChatGPT
- Creation of tools that enable the replay of real-world scenarios encountered during field tests, facilitating iterative improvements to the self-driving system.
- Development of sophisticated analysis tools capable of evaluating camera occlusion caused by road geometry using HD Maps. These tools were successfully deployed and utilized in our Australia project.
- Integration of the Google Maps API into a specialized tool to estimate the power consumption of electric vehicles based on specific routes, cargo weights, and power models.
- Developed a custom Sublime plugin with the help of ChatGPT that provides users with the ability to visualize the structure of a behavior tree directly from the tree construction .cpp file. This plugin offers a seamless integration within the Sublime Text editor, allowing users to gain a comprehensive understanding of the behavior tree's hierarchical organization.
Researches
Image-Based Control of Quadrotors Using Deep Reinforcement Learning, Jan 2018 ~ 2020
keywords: PyTorch, TD3, RNN, VAE, Markov Decision Process, Quadcopter, DRL
- A project of the Ministry of Science and Technology leads by Prof. Jen-Hui Chuang.
- The goal of the DRL controller was to control the quadrotor with forward-looking images to pass gates with different sizes.
Deep Reinforcement Learning-Based Mapless Motion Planning
keywords: Tensorflow, keras-rl, DDPG, pyglet, DRL
- Utilizing an MDP model to address the challenging problem of mapless motion planning with limited local information.
- Introducing a sub-optimal numerical expert as a demonstration to guide the DRL agent towards discovering improved policies.
Enhancing Shoe-Making Production Line Automation Through Shape Forming and Board Lasting Automation, Dec 2017 ~ Jul 2018
keywords: Scikit-Learn, Random Forest, OpenCV, Machine Learning
- An industry-university cooperation project aimed to enhance the automation of shoe-making production line.
- My part was to correct the position and orientation of unformed shoes feeding by a 6-axis robot arm.
Gate Pose Estimation Using PilotNet, Jul 2019 ~ Dec 2019
keywords: Deep Learning, RVIZ, ROS, CNN
- Utilizing a single image to estimate the position and pose of gates in the body frame.
- Leveraging the power of PilotNet, a proven deep learning model, to achieve high accuracy in gate pose estimation.
Side Projects
Ticket Monitor
keywords: Line Bot, Beautiful Soup, UI
A project that automates the process of tracking user-assigned events on ticket-selling websites. Objective of the project is to notify users via Line notification where tickets become available due to users ordering but not completing the payment within the specified time frame.
Project Link:
Lan-NCTU
keywords: Midi Protocol, MCU, VCV Rack
A modern midi instrument with RGB programmable lights patterns and 9DOF imu sensor.
Project Link:
https://github.com/showaykerker/lan_nctu
Home Security Project
keywords: IOT, Flask, RPi, MCU, Line Bot
A home security project that monitors unauthorized door opening event constructed by Linkit 7697, Raspberry Pi, and IFTTT service.
Project Link:
https://github.com/showaykerker/Linkit7697_DoorMonitor