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 $\textit{Diff-Transfer}$, a novel framework leveraging differentiable physics simulation to efficiently transfer robotic skills. Specifically, $\textit{Diff-Transfer}$ 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, $\textit{Diff-Transfer}$ 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 $\textit{Diff-Transfer}$ through comprehensive experiments. Supplementary and Videos are on the website https://sites.google.com/view/difftransfer

翻译：掌握已习得技能以完成一系列相似但新颖的任务，对于智能机器人至关重要。本研究提出 $\textit{Diff-Transfer}$ 框架，利用可微物理仿真高效迁移机器人技能。具体而言，$\textit{Diff-Transfer}$ 在任务空间中探索可行路径，将源任务导向目标任务。沿该任务路径的每一对相邻点（即两个子任务），$\textit{Diff-Transfer}$ 将已知动作从一子任务调整以成功应对另一子任务。该调整过程通过可微物理仿真的梯度信息进行引导。我们提出一种新颖的路径规划方法，利用任务级状态与奖励的 $Q$-学习生成子任务。通过仿真实验构建框架，并在机器人操作领域执行四项具有挑战性的迁移任务，综合实验证明了 $\textit{Diff-Transfer}$ 的有效性。补充材料与视频见网站 https://sites.google.com/view/difftransfer