Liang-Chien Liu

Liang-Chien Liu has five years of professional experience. In 2023, they began working as a Software Engineer at Agility Robotics. In 2022, they moved to Ainstein as a Robotics Engineer, where they designed an algorithm that uses radar-based EKF multi-object tracking to compute radar odometry, performed sensor fusion on GPS and IMU data for state estimation, and applied Monte Carlo Localization and occupancy grid mapping using stereo 4D imaging radars. In 2020, they worked as a Research Assistant at the National Taiwan University, where they developed a multi-camera edge computing system that integrated real time surveillance with activity recognition, constructed a live video streaming service using MQTT and ZeroMQ for multiple clients, and modified a 3D ResNet model for activity recognition by fusing visual features with time series data to improve the F-1 score. In 2019, they worked as a Machine Learning Intern at LILEE Systems, where they employed the instance segmentation method, LaneNet, for lane-detection, optimized the lane detection performance by applying homography based inverse perspective mapping, and implemented YOLO algorithm on pedestrian, vehicle, and traffic light detection on ROS. Liang-Chien also worked as a Research Intern at China Motor Corporation in 2019, where they developed a camera surveillance system to detect workpiece displacement during endurance tests using Canny edge detection and contour tracking, and designed a user interface for workers to select the ROI.

Liang-Chien Liu obtained a Bachelor's degree in Mechanical Engineering from National Taiwan University between 2015 and 2019. Liang-Chien then went on to pursue a Master's degree in Electrical and Computer Engineering at the University of California, Los Angeles from 2021 to 2022.