|
|
Sen LI | 李森
CV_ENG | CV_CN |
|
|
|
Sen LI | 李森
CV_ENG | CV_CN |
|
LI Sen is a fourth-year Ph.D. candidate at the Southern University of Science and Technology, advised by Assistant Professor Fan Wan. He obtained his Master of Engineering in Control Science and Engineering, advised by Associate Prof. Zhifeng Huang and his B.Eng. in Electronic Engineering from Guangdong University of Technology. His research interests include soft robotics, deep learning, biomimetic strategies, trajectory planning, dynamics, control, and algorithmic applications.
Ph.D. candidate, Intelligent Manufacturing and Robotics
Postgraduate student at MainDL Lab & BionicDL Lab
Advisor: Assistant Prof. Fan Wan and Assistant Prof. Chaoyang Song
Master of Engineering, Control Science and Engineering
Postgraduate student at Jet Power & Humanoid Robotics
Lab
Advisor: Associate Prof. Zhifeng Huang
Guang Dong and Hong Kong Joint College of Robotics
Advisor: Dr. Hong Wang and Prof. Zexiang Li
Bachelor of Engineering, Electronic Engineering
Admission into postgraduate exempt from examination
Visitor student at Winter School on Design Science
Advisor: Prof. Jianxi Luo
Research Assistant at Robotics Institute, HKUST (RI)
|
|
Biomimetic Flip-and-Flap Strategy of Flying Objects for Perching on Inclined Surfaces Brief Description: A flip-and-flap biomimetic strategy is presented that enables a high-speed flying object to perch on inclined surfaces without speed reduction before touchdown. Responsibilities: Analyzed the motions of flying objects by building a mathematical model that simulated the flip-and-flap process; Performed progressed analysis and compiled the paper for publication. |
|
|
Determinants of Robotic Wall-Flip Strategy
Brief Description:
The key metrics for enabling the robot to perform a wall-flip parkour motion were investigated by analyzing the movements of parkour practitioners. By leveraging dynamics and incorporating the geometry and contact properties of the environment, the robot’s locomotion performance was significantly improved compared to conventional approaches.
Responsibilities: Implemented a simplified model and identified key determinants to facilitate analysis and feedback control design for the robotic wall-flip strategy. Developed dynamic simulations of the multi-link robot (Atlas) in PyBullet for further validation.
|
|
|
ActiveSPN: Active Soft Polyhedral Networks With Pose Estimation for In-Finger Object Manipulation Brief Description: This letter introduces Active Soft Polyhedral Networks (ActiveSPN), a gripper design that leverages an active, non-biomimetic surface for precise in-hand manipulation. A vision system integrated directly into the fingers further facilitates accurate pose estimation of the in-finger object. Responsibilities: Designed and fabricated the ActiveSPN mechanical structure; developed the pose estimation and kinematic algorithms; planned and executed experiments with data analysis; compiled the paper for publication. |
|
|
Multi-Modal Vision-Based Deformable Perception for In-Finger Manipulation with Soft Active Surfaces Brief Description: We propose ActiveSPN2, a robot gripper with a soft active surface designed for in-finger manipulation in constrained environments, featuring multi-modal perception through a vision-based deformable perception architecture. By tracking the real-time deformation of the internal Soft Polyhedral Network, we achieve real-time, multi-modal vision-based perception that provides 6D forces and object pose estimation during in-hand manipulation. Responsibilities: Designed and fabricated the ActiveSPN2 structure; developed multi-modal estimation algorithms; conducted a series of experiments with data analysis; compiled the manuscript for submission. |
|
|
Active Surface with Passive Omni-Directional Adaptation for In-Hand Manipulation Brief Description: In this study, we present the design of a soft robotic finger with an active surface on an omni-adaptive structure, which can be easily installed on existing grippers and achieve stability and dexterity for in-hand manipulation. Responsibilities: Designed a soft robotic finger integrating an active surface with an omni-adaptive structure, conducted finite element simulations and analyses, and compiled the paper for publication. |
|
|
Teaching oral care via vision-based deformation perception Brief Description: This study presents a novel, cost-effective sensor platform based on Vision-based Deformation Perception for community oral health education. The system integrates a 3D-printed thermoplastic polyurethane soft structure with a rigid resin frame and an ArUco marker to encode interaction information, including the contact region and six-dimensional force and torque. Responsibilities: Completed model rendering and conducted finite element analysis. |
|
|
ADAP: Adaptive & Dynamic Arc Padding for Predicting Seam Profiles in Multi-Layer Multi-Pass Robotic Welding Brief Description: This study introduces the Adaptive & Dynamic Arc Padding (ADAP) approach. ADAP employs a novel representation of weld bead profiles using image-based boundary and primitive arc geometries defined by arc center and radius. Responsibilities: Designed a high-temperature-resistant flexible structure with a haptic learning framework, performing coarse weld path localization based on 3D visual recognition and real-time trajectory correction using haptic feedback, achieving precise weld tracking. |
|
|
Trajectory Tracking on Universal Robots Brief Description: This research proposes a method for calibrating a dual manipulators system using a motion capture system, and completes a trajectory tracking motion of the dual robotic arms.
|
|
|
Coordinate Measuring Machine (CMM) Project
Brief Description: This project is to realize the precise positioning and process-ing of the workpiece.
Given a template file or coarse position of the workpiece, the CMM could output the precise measuraments
of the workpiece by sampling point clouds automatically generated on the workpiece’s surface.
Responsibilities: Design algorithms to automatically generate measurement path on
the surface of the workpiece by collected a few sampling data. The measurement was performed with
errors less than 2 μm.
|
|
|
Research on algorithm of cooperative work of Dual Six-Axis Manipulator
Brief Description: Designed an algorithm of how the slave manipulator follows the master manipulator and
how the slave manipulator independently performs trajectory overlay.
Responsibilities: Completed the simulation of position and attitude planning algorithms, and design
the trajectory tracking and trajectory overlay algorithm.
|
|
|
HKUST One Million Dollar Brief Description: Robotics startups – Ten entrepreneurial teams from 30 renowned institutions, came to Beijing to present their projects and roadshows. Responsibilities: Discussed and determined the course schedule with YUAN Ye, LIU Jun and LIU Song, assisted professors in giving lessons, led visits to well-known companies (DJI, Inovance Technology), helped students complete prototype designs and advance their projects.
|
|
|
Rock–Paper–Scissors based on vision Brief Description: Dynamic gesture tracking and recognition program that recognizes opponent’s hand gestures in the "rock-paper-scissors" games based on image classification technique, and instantly responds to defeat human players. |
|
|
Gesture Control of Moving Chassis
Brief Description: Using a customized data glove controls the Mecanum wheel cart moves in all directions
by gesture.
Responsibilities: Implemented the chassis program development, including driving
the chassis and decoding the remote control.
|
|
|
ROBOCON Brief Description: Two robots on top of the previous badminton robot were designed for two consequetive National University Robot Competitions, “Clean energy recharging the world” and “Asobi: the landing disc", to further polish my engineering skills. Responsibilities: Participated in the design of badminton robot, clean energy robots, frisbee robot, and serve as the operator of the badminton robot. Mainly responsible for the control of the chassis of the mecanum wheel and the control of the launcher. |
|
|
Self-stabilization of Quadrotor Brief Description: Use open source flight control with only IMU to drive the quadcopter and achieve self-stabilization. |
|
|
Auto-tracking Brief Description: The circuit design was designed using the NAND gate and simplified by K-map. |
Orcid
