基于强化学习的软体机器人手内操作控制器的持续策略蒸馏
Continual Policy Distillation of Reinforcement Learning-based Controllers for Soft Robotic In-Hand Manipulation
AI总结：
本文提出持续策略蒸馏框架，通过策略蒸馏与样本回放缓解灾难性遗忘，训练通用软体手内操作控制器以旋转不同物体。
摘要：
灵巧操作通常由多指机器人手实现，对现实世界应用具有重要影响。软体机器人手因其柔顺特性，在物体抓取和操作过程中提供了灵活性和适应性。然而，这些优势也带来了挑战，特别是在手指协调的控制开发方面。强化学习（RL）可用于训练针对特定物体的手内操作策略，但这限制了适应性和泛化能力。我们提出了一种持续策略蒸馏（CPD）框架，用于获得一个通用的手内操作控制器，以在四指软体夹爪中旋转不同形状和尺寸的物体。该框架利用策略蒸馏（PD）将专家策略中的知识迁移到一个持续演化的学生策略网络中。随后集成基于样本回放的方法，以缓解灾难性遗忘并增强泛化能力。CPD框架在不同回放策略上的性能表现证明了其在整合多个专家知识以及实现手内操作任务中通用和自适应行为方面的有效性。
英文摘要：
Dexterous manipulation, often facilitated by multi-fingered robotic hands, holds solid impact for real-world applications. Soft robotic hands, due to their compliant nature, offer flexibility and adaptability during object grasping and manipulation. Yet, benefits come with challenges, particularly in the control development for finger coordination. Reinforcement Learning (RL) can be employed to train object-specific in-hand manipulation policies, but limiting adaptability and generalizability. We introduce a Continual Policy Distillation (CPD) framework to acquire a versatile controller for in-hand manipulation, to rotate different objects in shape and size within a four-fingered soft gripper. The framework leverages Policy Distillation (PD) to transfer knowledge from expert policies to a continually evolving student policy network. Exemplar-based rehearsal methods are then integrated to mitigate catastrophic forgetting and enhance generalization. The performance of the CPD framework over various replay strategies demonstrates its effectiveness in consolidating knowledge from multiple experts and achieving versatile and adaptive behaviours for in-hand manipulation tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
