Research

Adversarial-based Algorithm for Motion Balancing Control of Legged Robots

Legged robot control, Shanghai Jiao Tong University, 2024

Separate legged robot balance control into two separate agents, stance and swing legs. Stance legs controlled with WBC method are responsible for generating acceleration to track target velocity. While swing legs controlled with RL method are responsible for balance the robot.

Manipulate as Human: Learning Task-oriented Manipulation Skills by Adversarial Motion Priors

Robot Arm control, Shanghai Jiao Tong University, 2024

In recent years, there has been growing interest in developing robots and autonomous systems that can interact with humans in a more natural and intuitive way. One of the key challenges in achieving this goal is to enable these systems to manipulate objects and tools in a manner that is similar to how humans do. In this paper, we propose a novel approach for learning human-style manipulation skills by using adversarial motion priors.