LiMoDE: 从动态专家混合视角重新思考终身机器人操作
LiMoDE: Rethinking Lifelong Robot Manipulation from a Mixture-of-Dynamic-Experts Perspective
AI总结：
提出一种两阶段终身学习方案LiMoDE，通过动态专家混合结构实现多任务预训练和任务自适应，有效缓解灾难性遗忘并促进知识迁移。
摘要：
构建一个能够利用先验知识进行连续任务适应的通用机器人仍然是一个重大挑战。先前的工作通过参数高效微调来缓解灾难性遗忘问题，用于单任务适应。然而，它们未能提取可重用技能并有效建模与其他技能的交互。最近的工作尝试通过学习提示来解决这些问题。不同的是，本文提出了一种关于终身动态专家混合（LiMoDE）的架构视角，这是一种用于终身机器人操作的新型两阶段学习方案。具体来说，在多任务预训练阶段首先提出一种动态MoE结构来学习先验知识，其中根据运动信息激活不同数量的异构专家以处理不同的短期操作。随后，在任务适应阶段，我们设计了一种终身MoE适应机制，该机制学习终身专家并动态地将它们与冻结的专家组合以处理新任务，从而促进适应过程中的知识迁移。所提出的LiMoDE在模拟终身学习基准和真实世界任务上进行了评估。大量实验表明，通过引入适度数量的额外可训练参数和推理开销，它在实现卓越性能和强终身适应方面是有效的。
英文摘要：
Building a generalist robot that can leverage prior knowledge for continuous task adaptation remains a significant challenge. Previous works alleviate the catastrophic forgetting problem by parameter-efficient fine-tuning for single-task adaptation. However, they fail to extract reusable skills and model the interaction with other skills effectively. Recent works try to address these issues by learning prompts. Differently, this paper presents an architectural perspective on the Lifelong Mixture of Dynamic Experts (\textit{LiMoDE}), a novel two-stage learning scheme for lifelong robot manipulation. Specifically, a dynamic MoE structure is first proposed in the multi-task pre-training stage to learn prior knowledge, where a varied number of heterogeneous experts are activated based on the motion information to address different short-term manipulations. Subsequently, in the task adaptation stage, we design a lifelong MoE adaptation mechanism % (LiMoEAM) that learns lifelong experts and dynamically combines them with frozen ones for new tasks, facilitating the knowledge transfer during adaptation. The proposed \textit{LiMoDE} is evaluated on both the simulated lifelong learning benchmark and real-world tasks. Extensive experiments demonstrate its effectiveness in achieving superior performance and strong lifelong adaptation by introducing a moderate number of additional trainable parameters and inference overhead.
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。
