Machine Learning and AI in the FIELD

Avatar

Weijiang Xiong

Msc in Robotics

Aalto University, Finland

About Me

Weijiang Xiong (熊伟江) is a second-year robotics master student at Aalto University. He is now working on his master thesis as a research intern at Nokia Technologies. His is broadly interested in Artificial Intelligence, but with a focus on the application of visual perception and machine learning.

In the Vision4Robotics Group at Tongji University, he began his academic exploration from Visual Object Tracking for UAV. He then explored Bayesian Deep Learning methods in his summer project at Aalto PML Group, and applied Normalizing Flows to model the probabilistic distribution of the aleatoric uncertainties for neural networks. During his exchange at EPFL, he completed a project at the VITA Lab, where he utilized body poses as an intermediate representation to recognize pedestrian’s actions. For his thesis, he is studying self-/semi-supervised methods for object detection in aerial images.

His academic path has made him realize the gap between academic state-of-the-art and down-to-the-ground applications, and stimulated his eager for gaining insights into reliable AI applications in the field. His latest resume could be found here, and here are the combined slides for his past research projects.

Interests

  • Machine Learning
  • Artificial Intelligence
  • Domain Adaptation

Education

  • Msc in Robotics, minor Machine Learning, 2020 - 2022

    School of Electrical Engineering, Aalto University

  • Exchange study in Robotics, 2021 Fall

    School of Engineering, EPFL

  • Bsc in Mechanical Engineering, 2015 - 2020

    School of Mechanical Engineering, Tongji University

Experience

 
 
 
 
 

Research Assistant

VITA lab at EPFL

Sep 2021 – Feb 2022 EPFL, Switzerland
 
 
 
 
 

Research Assistant

Probabilistic Machine Learning Group

Jun 2021 – Aug 2021 Aalto University, Finland
 
 
 
 
 

Research Assistant

Vision4Robotics Group, Tongji University

Nov 2018 – Jul 2020 Shanghai, China

Projects

Summary Slides

*

Action recognition with poses

Self-driving cars and delivery robots are set to shape the future of transportation, but they still have to learn how to co-exist with …

Normalizing Flows

This is my summer project at PML Group, where I worked on Bayesian Deep Learning. Generally, there are two kinds of uncertainties in …

Bayesian

This is the course project for CS-E5710 Bayesian Data Analysis, which I completed together with my friend Haoping Xiao. Road traffic …

MinSeg

This is the course project of ELEC-E8101 Digital and Optimal Control at Aalto University. It is somewhat like the inverted pendulum I …

Point Cloud Object Detection

During my internship at Hesai Tech, I worked on the point cloud-based object detection problem. This picture is from Waymo Open …

Chain Reaction

In 2018 Open-Source Hardware and Programming, I organized a mechanical experiment as the TA lead. This module consist of 5 …

Inverted Pendulum

An inverted pendulum is a pendulum that has its center of mass above its pivot point. It is unstable and without additional help will …

PEB in PUMA

PACE is an international collaborative competition. We took part in the PACE 2018 Forum with excellent team mate from TU Darmstadt and …

Self-Driving Simulation

The Deep Learning course in Tongji University (2019 FALL) contains the following contents: Machine learning basics: Linear regression …

Supply Station

In Superpower Robot Team, I took the responsibility of the mechanical design of the supply station. My team participated in RoboMaster …

Contact

  • weijiangxiong1998@gmail.com