From Traditional Geometric-based Vision Methods to AI Experiences —— the Evolution of Robotics

Date: 2023/11/10 - 2023/11/10

Academic Seminar: From Traditional Geometric-based Vision Methods to AI Experiences —— the Evolution of Robotics

Speaker: Tong Qin, Associate Professor, Global Institute of Future Technology, Shanghai Jiao Tong University

Time: 10:00 - 11:30, November 10, 2023 (Beijing Time)

Location: CIMC Auditorium (Room 300), JI Long Bin Building

Abstract

This talk will introduce the trend of AI (Artificial Intelligence) for robotics. The speaker will give detailed examples of autonomous driving to illustrate how to deploy AI technologies into the real product. Specifically, the speaker will elaborate on the neural networks used for Autonomous Valet Parking, crowed-sourcing data collection for automatic map generation, NeRF (Neural Radian Field) technology used for 3D reconstruction, and GPT(Generative Pre-trained Transformer)-based systematic design for end-to-end autonomous driving.

Biography

Tong Qin, the tenure-track associate professor from Global Institute of Future Technology, Shanghai Jiao Tong University. Before joining the university, he was an expert at the autonomous driving solution department, Huawei, top minds. He got a Ph.D. degree at the Hong Kong University of Science and Technology (HKUST). He was the first author of the open-source VINS (Visual-inertial Navigation System), which was widely used in robotic applications. His research interests focused on SLAM, artificial intelligence for autonomous driving. He was dedicated to fully autonomous driving vehicles. He got the best paper honorable mention award at Transaction of Robotics (T-RO), and the best student paper at IROS.