Max Robotics — Global Service Robot Directory + US Certification

About

Yung-Shan Chou is a robotics researcher specializing in autonomous manipulation, mobile robotics, and deep learning-based control systems. Her work focuses on integrating computer vision and imitation learning to enable robots to perform complex tasks with minimal human intervention. In her most cited paper (2019, 8 citations), she proposed a novel end-to-end multi-task imitation learning architecture using deep convolutional neural networks to solve the visually guided pick-and-place problem for omnidirectional mobile manipulators. This work demonstrated how robots can learn to coordinate mobility and manipulation from visual inputs alone. She further advanced this approach in a 2018 study (3 citations) applying similar end-to-end learning to 6-degree-of-freedom manipulators. Chou has also contributed to practical mobile robot design, implementing a compact 18 cm × 18 cm × 21 cm robot (2024, 3 citations) capable of road detection, sign recognition, and obstacle avoidance using a CPU, GPU, 2D LiDAR, and dual fisheye cameras. Her research bridges the gap between theoretical deep learning and real-world robotic applications, with a particular emphasis on data-driven control systems that reduce the need for explicit programming.