Chenghao Xu

PhD Student | EPFL

profile.jpg
"Anything one man can imagine, other men can make real." -Jules Verne

I am currently pursuing my Ph.D. advised by Prof. Olga Fink and Dr. Malcolm Mielle at École Polytechnique Fédérale de Lausanne (EPFL), Switzerland. Before this, I completed my M.Sc. in Robotics at Delft University of Technology (TU Delft), Netherlands, and a B.Eng. in Mechanical Engineering with Excellent Graduate Honor from Southern University of Science and Technology (SUSTech), China.

During my master studies, I worked on robust dynamic visual SLAM systems and realistic dynamic environment simulations with Prof. Aamir Ahmad at the Max Planck Institute for Intelligent Systems (MPI-IS), Tübingen, Germany. During my bachelor period, I conducted research on passive assistive exoskeletons and constructed a functional prototype with Prof. Hongqiang Wang. Additionally, I closely collaborated with Prof. Jianwen Luo, focusing on the mechanical design of quadruped robots.

Inspired by the fantasies of Jules Verne and Isaac Asimov, I am captivated by the unparalleled elegance of intelligent systems, which propels me to further explore the intersections between the physical world and artificial intelligence. Currently, my research interests lie in 3D vision and scene reconstruction, especially in multimodal reconstruction for building assessment and renovation.

  News

May 7, 2023 Our work was accepted to ICRA 2023 Workshop on Active Methods in Autonomous Navigation
May 6, 2023 Our work was accepted to ICRA 2023 Workshop on Pretraining for Robotics
Dec 31, 2022 GRADE was accepted as presentation at NVIDIA GTC 2023
Jun 30, 2022 I will work as a research assistant at MPI-IS this summer.
Feb 10, 2022 I will work on novel and impactful solutions with Spot robots in YES! Delft Impact Lab 🐕
Feb 1, 2022 I am currently working as a Computer Vision R&D Engineer at Lely Technologies 🐄
Jul 1, 2021 First time in Beijing: I will work as a control engineer at ROKAE Robotics.
Aug 25, 2020 Admission to Master Robotics at Delft University of Technology 🏰
Jun 30, 2020 I graduated from Southern University of Science and Technolgy with Excellent Graduate Honor!

  Experience

  • Feb 2022 - Jul 2022

    Full-time internship for 6 months, focusing on the video stitching on multi-cameras with multi-depth to obtain better panoramas of the farm.

  • Mar 2022 - Jul 2022

    Part-time internship for 6 months, focusing on the autonomous navigation function for Spot robots. Collaborate with construction company VolkerWessels to develop impactful solutions for their requirements.

  • Jul 2021 - Sep 2021

    Full-time internship for 3 months, focusing on the control algorithm and simulation of 6-axis industrial manipulators.

  • Jun 2019 - Dec 2019

    Part-time project, focusing on the mechanical design and prototype construction of quadruped robots.

  • Jun 2019 - Sep 2019

    Full-time internship for 4 months, focusing on the development and verification of upper-limb assisted exoskeleton.

  Featured Publications

  1. PAPER
    DynaPix SLAM: A Pixel-Based Dynamic Visual SLAM Approach
    C. Xu, E. Bonetto, and A. Ahmad
    arXiv preprint, Mar 2024
    arXiv Code
  2. PAPER
    GRADE: Generating Realistic Animated Dynamic Environments for Robotics Research
    E. Bonetto, C. Xu, and A. Ahmad
    arXiv preprint, Oct 2023
    Abs arXiv Code Website
  3. PAPER
    Implementation of a Long-lasting, Untethered, Lightweight, Upper-limb Exoskeleton
    H. Liu, K. Fang, L. Chen, C. Xu, and 7 more authors
    Submitted to TMECH, Jul 2023
    Abs PDF Poster
  4. TALK
    Breaking the Wall of Intensive Work Above Head: Design of Passive Upper-Limb Exoskeleton
    C. Xu
    Falling Walls Lab, Nov 2019
    Abs HTML PDF

  Featured Projects

.js-id-Featured
GRADE: Generating Realistic Animated Dynamic Environments
Code Website SLAM Dataset
With GRADE framework we generate photorealistic indoor environment datasets consisting of static/dynamic scenarios and extended assets (motion blur, sensor noise, etc.). Generated data has been extensively tested on various SLAM frameworks and typical detection/segmentation libraries to prove usability and improved performance.
Upper-Limb Passive Adaptive Assisted Exoskeleton
Video Robot Design Exoskeleton
The passive adjustable arm-exoskeleton is designed based on a spring slider model and four-bar-linkage model. It is a lightweight wearable system with a weight of 2 kg and with a feature of easy adjustability. The lifting force of the mechanism is relatively constant in a wide working range and will step down in the non-working area.
Multi-Camera Real-Time Surveillance Video Stitching
Code Computer Vision Image Stitching In Progress
Based on the AutoStitch framework, the feature matching strategy is developed given the corresponding ROIs since the cameras for surveillance are of constant parameters. Furthermore, seam-based optimization will be implemented to improve the stitching performance of the overlapping area.
Online Trajectory Planning for Manipulators based on Discrete-Time Double S Profile
Code Online Planning
Implemented real-time path following movement based on the PID method and double S profile. The constraint-based PID method can achieve synchronous movement for all joints within dynamics constraints. The discrete-time double S method can achieve its maximum kinematic properties for each joint.
TIAGo Robot for Expiring Items Picking in Retail Environment
Video Course YOLOv5 Behavior Tree
Constructed ROS behavior tree architecture to dynamically adjusts goals and performs items picking/placing in sequence.
Machine Learning for Car Racing Games
Course Machine Learning
Developed the Random Forest and Convolutional Neural Network models for multi-class classification, which used the current top-view image as input and outputted the control action (accelerate, steer left/right, brake).
Obstacle Detection and Avoidance for Autonomous Vehicle
Course ROS C++
Developed software on ROS to achieve autonomous driving in a simulated test track. Designed ROS nodes to detect obstacles and pedestrians from LiDAR pointclouds and camera images using PCL and OpenCV, and use these detections to generate simple control instructions.
Path Planner for Quadrotor based on Kinodynamics RRT* and k-PRM Methods
PDF Code Planning In Progress
Developed RRT* and k-PRM path planner to generate collision-free path to verify the robustness on 3D random obstacle map. Furthermore, vehicle routing problem will be implemented to achieve path planning for multi-rbots with multiple goals,