Hi there! Welcome to my academic website.

I am a senior student majoring in Mechanical Engineering at Zhejiang University and University of Illinois at Urbana-Champaign.
GPA: 3.97/4.3 (ZJU) & 3.92/4.0 (UIUC).

My research interests include Deep Reinforcement Learning Tactile Based Manipulation Legged Locomotion.

profile photo

Education

ZJU-UIUC Institute 09/2022 – Present
B.E. in Mechanical Engineering | GPA: 3.97/4.3
University of Illinois at Urbana-Champaign 09/2024 – 09/2025
B.E. in Mechanical Engineering | GPA: 3.92/4.0
Zhejiang University Expected 05/2026
Ph.D. in Control Science and Engineering | Advisor: Prof. Hua Chen

Publications

Beyond Robustness: Learning Unknown Dynamic Load Adaptation for Quadruped Locomotion on Rough Terrain
Leixin Chang, Yuxuan Nai, Hua Chen*, Liangjing Yang*
ICRA, 2025
Bilevel Optimization of Heli-Logging Assignment for a Quadrotor with Cable-Suspended Payload
Yuxuan Nai, Ding Jiang, Ziyin Han, Chengyu Yang, Sheng Cheng*, Naira Hovakimyan*
IEEE Robotics and Automation Letters (RAL), 2025 (Under Review)

Research Experience

Learning Based Stable Pose Selection with Tactile Modality 05/2025 – 09/2025
RoboTouch Lab, UIUC | Advisor: Prof. Wenzhen Yuan
  • Realized stable pose selection via a tactile-feedback-driven learning-based planner.
  • Enabled stability prediction of poses by training a model with data collected on the Taccel simulator.
Bilevel Optimization of Quadrotor Payload System 10/2024 – 10/2025
AVIATE Center, UIUC | Advisor: Dr. Sheng Cheng, Prof. Naira Hovakimyan
  • Developed minimum-snap trajectory with flatness for smooth transitions between taut and slack cable states.
  • Improved trajectory fidelity to real maneuvers via bilevel optimization of release parameters.
  • Validated control strategies through simulation testing on Gazebo.
RL for Legged Unknown Dynamic Load Adaptation 05/2024 – 07/2024
Physical Intelligence Lab, ZJU-UIUC | Advisor: Prof. Hua Chen, Prof. Liangjing Yang
  • Facilitated blind walking by implementing a teacher-student reinforcement learning framework.
  • Enabled quadruped locomotion under unknown payloads with a proprioception-based payload estimator.
  • Validated through MuJoCo simulations and sim-to-real deployment.
Unmanned Mining Truck Route Planning 05/2023 – 05/2024
Academic Training SRTP, ZJU | Advisor: Prof. Jian Chen
  • Simplified route planning for unmanned mining trucks, overcoming traditional method limitations.
  • Developed a two-step strategy: front-end path planning and back-end trajectory optimization.
  • Used Hard-Constraints and Minimum-Snap to ensure safe, dynamically feasible paths.

Internship

A3 Humanoid Locomotion 01/2026 – 03/2026
AGIBOT | Advisor: Taiyu Li
  • Developed a unified policy for full-scale A3 humanoid locomotion.
  • Trained a single policy for multiple walking-base locomotion tasks.
  • Implemented perceptive parkour for terrain-aware agile locomotion.

Projects

Three-axis Robotic Arm Control for Trajectory Following 01/2025 – 05/2025
Course Project from Robot Dynamics and Control (ME446, A+) | UIUC
  • Designed trajectories to accomplish multiple tasks—egg pressing, obstacle avoidance, and peg-in-hole insertion.
  • Developed a PID controller with a feedforward term for enhanced performance.
  • Validated on a CRS robotic arm, achieving smooth and rapid task execution.
Identification of Informative COVID-19 English Tweets 01/2025 – 05/2025
Course Project from Programming Methods for Machine Learning (ECE364, A+) | UIUC
  • Designed a classification network to identify informative tweets.
  • Explored and evaluated various training methods for the network.
  • Achieved 0.89 accuracy, ranking 3rd overall in the competition.
Reaction-Based Motion Planning with Deep Reinforcement Learning 02/2024 – 03/2024
Project Reproduction | ZJU-UIUC
  • Reproduced a project integrating Artificial Potential Field (APF) with DDPG to mitigate local minima issues.
  • Developed advanced motion planning leveraging DDPG's continuous actions.
  • Validated approach in ROS Gazebo simulations, achieving robust navigation with dynamic obstacles.

Honors and Awards

Leadership