2023/10/07 by Yuqi Xiang, Xiang, Yuqi, Feitong Chen +13
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms #Reinforcement Learning in Robotics #Robot Manipulation and Learning #Robotics (cs.RO)
paper · pdf · doi:10.48550/arxiv.2310.04930
openalex publication_date 2023/10/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The capability to transfer mastered skills to accomplish a range of similar yet novel tasks is crucial for intelligent robots. In this work, we introduce Diff-Transfer, a novel framework leveraging differentiable physics simulation to efficiently transfer robotic skills. Specifically, Diff-Transfer discovers a feasible path within the task space that brings the source task to the target task. At each pair of adjacent points along this task path, which is two sub-tasks, Diff-Transfer adapts known actions from one sub-task to tackle the other sub-task successfully. The adaptation is guided by the gradient information from differentiable physics simulations. We propose a novel path-planning method to generate sub-tasks, leveraging Q-learning with a task-level state and reward. We implement our framework in simulation experiments and execute four challenging transfer tasks on robotic manipulation, demonstrating the efficacy of Diff-Transfer through comprehensive experiments. Supplementary and Videos are on the website https://sites.google.com/view/difftransfer