用迁移学习提升机器人复杂操作的采样效率，实测成功率最高提升23%。
Sample-efficient Low-level Motion Planning for Robotic Manipulation Tasks via Zero-shot Transfer Learning
- 将简单任务参数迁移到复杂任务，指导低层运动规划。
- 通过任务分解重设计奖励函数，使堆叠和上架成功率提升23%。
- 在真实机械臂上验证可行，适合需要快速部署的工业场景。
随着机器人系统日益复杂，其运动规划模型的复杂度与训练时间不断增长，带来显著挑战。近期，基于高效知识复用策略的样本高效交叉熵方法（iCEM）在低层实时规划中展现出良好潜力。尽管在多数控制任务中表现优异，iCEM在需堆叠、滑动及货架放置等复杂场景中性能受限。本文提出一种新型iCEM+TL框架，显式引入迁移学习（TL），将简单上游任务中的关键iCEM参数迁移至更复杂的下游任务中以提供引导。同时，针对堆叠与货架放置任务，通过任务分解实施奖励重设计（RR），优化特定任务表现。仿真结果表明，该框架可实现最高达23%的成功率提升。进一步在真实Franka Emika机器人上对堆叠任务进行验证，证明了其在实际部署中的可行性。
原文摘要 · Abstract (English)
As robotic systems become more sophisticated, the growing complexity of their motion planning models and the longer training times pose substantial challenges. Evolutionary algorithms such as the Sample-efficient Cross-Entropy Method (iCEM) have recently demonstrated promising potential for low-level real-time planning by leveraging efficient knowledge reuse strategies to improve performance. Although effective in many control tasks, iCEM's performance can be constrained in more complex scenarios, particularly those requiring stacking, sliding, and shelf placement. In this work, we propose a novel iCEM+TL framework that explicitly leverages Transfer Learning (TL), where key iCEM parameters are transferred from simpler upstream tasks to guide more complex downstream tasks. Additionally, we applied Reward Redesign (RR) through task decomposition for stacking objects and shelf placement to optimize task-specific performance. Results from the simulation show that our framework achieves success rate improvements of up to 23%. The framework is further validated on a real Franka Emika robot in a stacking task, demonstrating its practical feasibility for real-world deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。