This is Tianxiang’s Homepage.
My name is Tianxiang Lin. I am currently a first-year MSR student at Carnegie Mellon University. I am advised by Prof. Michael Kaess in Robot Perception Lab (RPL) at The Robotics Institute.
Prior to that, I obtained my M.S. degree in Information Networking at Carnegie Mellon University under the advice of Prof. Michael Kaess. I also obtained my B.E. degree in Software Engineering at University of Electronic Science and Technology of China (UESTC), advised by Prof. Yong Liao in Embedded Real-time Computing Laboratory at UESTC.
Contact me by email: txlin [at] cmu [dot] edu
M.S. in Robotics, 2023-2025
Carnegie Mellon University
M.S. in Information Networking, 2020-2023
Carnegie Mellon University
B.E. in Software Engineering, 2016-2020
University of Electronic Science and Technology of China
Underwater robots typically rely on acoustic sensors like sonar to perceive their surroundings. However, these sensors are often inundated with multiple sources and types of noise, which makes using raw data for any meaningful inference with features, objects, or boundary returns very difficult. While several conventional methods of dealing with noise exist, their success rates are unsatisfactory. This paper presents a novel application of conditional Generative Adversarial Networks (cGANs) to train a model to produce noise-free sonar images, outperforming several conventional filtering methods. Estimating free space is crucial for autonomous robots performing active exploration and mapping. Thus, we apply our approach to the task of underwater occupancy mapping and show superior free and occupied space inference when compared to conventional methods.
16-833 Robot Localization and Mapping
Instructor: Prof. Michael Kaess
Lab: Robot Perception Lab (RPL)
Advisor: Prof. Michael Kaess
Track: Occupancy Mapping with Imaging Sonar & Acoustic SLAM.
Advisor: Prof. Xuejin Chen
Track: 3D Semantic Segmentation.
H0900220, Computing Evolution
Instructor: Prof. Richard Decker
F0919830, Embedded System Design
Instructor: Prof. Yong Liao