Shaoshu Su

Shaoshu Su

Welcome 👋

Welcome to my page!

I am a Ph.D. student working with Prof. Chen Wang in SAIR Lab at State University of New York at Buffalo (UB) on the intersection of deep learning and visual-based SLAM.

And previously I also worked in the Autonomous Driving Group of Mechanical Systems Control Lab at UC, Berkeley with Prof. Masayoshi Tomizuka.

I obtained my bachelor’s Degree at Beijing Institute of Technology and Master’s Degree at UC, Riverside, worked with Prof. Wei Ren in Cooperative Vehicle Networks Lab.

I am an active researcher who has rich experience in Visual-based SLAM, Motion Planning and Control in Robotics.

Research Interests: Visual SLAM, Machine Learning, Motion Planning & Control, Multi-Robot System, Reinforcement Learning, SLAM, Autonomous Driving, Unmanned Aerial Vehicle (UAV)

Recent News

Education

 
 
 
 
 
Ph.D. in Computer Science
State University of New York at Buffalo
Aug 2023 – Jun 2028 Buffalo, New York
 
 
 
 
 
Master of Science in Electrical Engineering
University of California, Riverside
Sep 2019 – Mar 2022 Riverside, California
 
 
 
 
 
Bachelor of Science in Aerospace Engineering
Beijing Institute of Technology
Sep 2015 – Jun 2019 Beijing, China

Research Experience

Double-Iterative Gaussian Process Regression for Modeling Error Compensation in Autonomous Racing
Autonomous racing control is a challenging research problem as vehicles are pushed to their limits of handling to achieve an optimal lap time; therefore, vehicles exhibit highly nonlinear and complex dynamics.
Shaoshu Su, Ce Hao, Catherine Weaver, Chen Tang, Wei Zhan, Masayoshi Tomizuka
Last updated on Dec 1, 2022
Double-Iterative Gaussian Process Regression for Modeling Error Compensation in Autonomous Racing
Multi-Robot Fully Distributed Active Joint Localization and Target Tracking
In this paper, we study the problem of multi-robot active joint localization and target tracking (AJLATT), where a team of robots mounted with sensors of limited field of view actively estimate their own and the target’s states cooperatively.
Shaoshu Su, Pengxiang Zhu, Wei Ren
Last updated on Nov 30, 2022
Multi-Robot Fully Distributed Active Joint Localization and Target Tracking
Deep Reinforcement Learning Based Distributed Active Joint Localization and Target Tracking
We aim to solve a multi-robot active joint localization and target tracking (AJLATT) problem, where a team of robots with sensors of limited field of view cooperate with other robots to actively plan their individual motions so as to achieve better performance for self-localization and target tracking while avoiding collisions with their team members, the target, and the environment.
Shaoshu Su, Wei Ren
Last updated on Dec 26, 2022
Deep Reinforcement Learning Based Distributed Active Joint Localization and Target Tracking

Projects

RGB-D Camera Based Target Detection and Active Tracking
In this project, we designed a perception-tracking framework to detected moving target with unknown future motion and then following that target with a TurtleBot robot. We applied the YOLOv3 object detection network to detect the moving target in real-time with an RGB camera in ROS Gazebo Simulation Environment.
Shaoshu Su, Boyu Hou, Ziying Deng
RGB-D Camera Based Target Detection and Active Tracking
Robot Trajectory Planning for a Ball-Kicking Game with Real-World TurtleBot
In this project, we need to drive the robot to get to the desired endpoint end and kick the ball (green point) in a gate (bule lines). In the project, we need to design a path to avoid all the obstacles and accurately reach the goal point.
Shaoshu Su
Robot Trajectory Planning for a Ball-Kicking Game with Real-World TurtleBot