Conference Papers

Robotic Grasping in Dynamic Environments

  • Iretiayo Akinola$^\star$, Jingxi Xu$^\star$, Shuran Song, Peter Allen
  • Preprint
  • website, arXiv (coming soon), video (coming soon)

Learning Your Way Without Map or Compass: Panoramic Target Driven Visual Navigation

  • David Watkins-Valls$^\star$, Jingxi Xu$^\star$, Nicholas Waytowich, Peter Allen
  • International Conference on Intelligent Robots and Systems (IROS 2020)
  • 8th Northeast Robotics Colloquium
    • 20-min oral presentation (675)
  • website, arXiv, video

Accelerated Robot Learning via Human Brain Signals

  • Iretiayo Akinola$^\star$, Zizhao Wang$^\star$, Junyao Shi, Xiaomin He, Pawan Lapborisuth, Jingxi Xu, David Watkins-Valls, Paul Sajda, Peter Allen
  • International Conference on Robotics and Automation (ICRA 2020)
  • website, arXiv, video

Workshop Papers

Active Multitask Learning with Committees

  • Jingxi Xu, Da Tang, Tony Jebara
  • Workshop on Adaptive and Multitask Learning, International Conferences on Machine Learning (ICML), 2019
    • with Travel Award
  • paper, poster

Online Robotic Grasping for Moving Objects

($\star$ indicates euqal contribution)

Project Highlights

Built a robot task and motion planning system on a PR2 robot, integrating perception, actively learned (using Gaussian processes) action primitives, planning, control and execution.
Learning and Intelligent Systems Group, CSAIL, MIT

Developed efficient active and multitask learning algorithms for large-scale personalization systems using limited number of queries.
Columbia University

Integrate eye-tracking with brain computer interface (BCI) system for assistive robots. Implmented under ROS environment using a simulated Gazebo world with Fetch robot visualized by RViz.
Robotics Group, Columbia University

Developed deep learning models (LSTM, 3D-convolution, etc.) for automatic personality analysis from interview videos. This project aimed at helping companies to automatically select proper candidates
DVMM, Columbia University

In order to handle the challenge of both memorization and generalization, we introduce a new method called contented-based DNN (deep neural network) with transfer learning and pseudo-MF (matrix factorization).
Columbia University

Developed a Hybrid Hardware/Software (C++ and Verilog) Simulation system to help ArcSim simulator to achieve both fastness and cycle-accurateness.
School of Informatics, The University of Edinburgh


I am a teaching assistant for the following courses at Columbia University:

  • COMS 4733 Computational Aspects of Robotics (Fall 2019)
    • Labs authored: rrt
  • COMS 6731 Humanoid Robots (Spring 2019)
  • COMS 4733 Computational Aspects of Robotics (Fall 2018)
  • COMS 4771 Machine Learning (Sping 2018)

Recent Posts

Some comments on why I chose to do a MS in Computer Science at Columbia over a fully-funded DPhil studentship in Computer Science at Oxford University



Honours and Awards

  • Andrew P. Kosoresow Memorial Award for Excellence in Teaching and Service (Columbia, 2019)
    Awarded each year to up to three students for outstanding contributions to teaching in the department and exemplary service to the department and its mission
  • CA Fellowship (Columbia, 2018)
    To students with top GPA and have done exceptional TA work (tuition covered with $\$$5000 stipend)
  • Class Medal (Edinburgh, 2017)
    Overall average ranked 1st among all students in Computer Science and Electronics class
  • 2+2 Program Scholarship (Edinburgh, 2015-2017)
    Awarded to students selected to the highly competitive 2+2 program (£2500 per year)
  • Dalian Mathematics Contest for University Students (Dalian, 2014)
    3rd Prize
  • Zhuhai Mathematics Contest for High School Students (Zhuhai, 2010)
    3rd Prize

Key Skills

  • Programming Languages
    Python, C/C++, Verilog, Java, MATLAB/Octave, HTML/CSS
  • Others
    ROS, LaTeX, Shell Script, Assembly, FPGA, Unix/Linux, Compiler, SQL

Course Highlights

At Columbia University

  • Computational Aspects of Robotics (A+)
  • Machine Learning (A)
  • Deep Learning for Computer Vision (A+)
  • Advanced Machine Learning (A+)

At University of Edinburgh

  • Robot Learning and Sensorimotor Control
  • Parallel Architectures
  • Operating Systems
  • Computer Communications and Networks
  • Computer Architectures
  • Database Systems
  • Biosensors


  • jingxi`dot`xu`at`columbia`dot`edu

“Look deep into nature, and then you will understand everything better.”

                                                                                                    –Albert Einstein