Yusong Jin

About

Yusong Jin is a leading researcher in soft robotics, specializing in the design, modeling, and control of soft manipulators for unstructured interactions. His major contributions lie in developing hierarchical and model-less control strategies that enable soft robotic arms to perform complex, real-world tasks—such as opening doors and pulling drawers—despite their inherent nonlinearity and viscoelastic behavior. Jin’s work bridges the gap between theoretical control and practical application, as evidenced by his highly cited 2021 paper on hierarchical control (132 citations) and his foundational two-level inverse kinematics approach (56 citations). He has also pioneered the use of reinforcement learning for soft robot motion control under pose constraints, notably with Q-learning methods that leverage rough simulators to improve sample efficiency. Jin’s innovative Honeycomb Pneumatic Network (HPN) arm design, detailed in his 2020 paper, demonstrates a unique balance of compliance and load capacity. With over 240 total citations, his research is shaping the future of safe, adaptive robots capable of seamless human-robot interaction in daily environments.

Research Focus

Key Achievements

Top Papers

1. 1
   Hierarchical control of soft manipulators towards unstructured interactions

   132 citations · 2021
2. 2
   A two-level approach for solving the inverse kinematics of an extensible soft arm considering viscoelastic behavior

   56 citations · 2017
3. 3
   Model-less feedback control for soft manipulators

   26 citations · 2017
4. 4
   A Reinforcement Learning Method for Motion Control With Constraints on an HPN Arm

   11 citations · 2022
5. 5
   A Q-learning Control Method for a Soft Robotic Arm Utilizing Training Data from a Rough Simulator

   10 citations · 2021
6. 6
   Design, Control, and Applications of a Soft Robotic Arm

   7 citations · 2020

Key Collaborators

Contact & Links