Responsible for the development of perception detection algorithms for cameras, lidar, and other sensors.
Debugging and testing; Responsible for deep learning target detection, semantic segmentation, and other model building.
Requirements
Master’s degree or above in Computer Engineering, Software Engineering, Robotics, Automation, or related fields.
Good foundation in mathematics, algorithms, and programming development experience, proficient in C++.
Familiar with Linux systems, with ROS experience preferred.
Familiar with point cloud processing algorithms, such as point cloud filtering, segmentation, clustering, fitting, tracking, etc.
Familiar with basic vision algorithms, such as object detection and tracking, lane line detection and tracking, camera calibration, optical flow, distance estimation, etc.
Familiar with basic machine vision algorithms, such as optimization algorithms, traditional classifiers, CNN, RNN, GAN, NAS, etc.
Practical project experience is preferred.
Familiar with Lidar 3D point cloud processing and registration, 3D computer vision, SLAM, VIO, State estimation theory, real-time multi-sensor data processing and fusion (GNSS, IMU, wheel speed sensors, etc.), filtering techniques such as EKF/PF/UKF.
