Sparse Diffusion Policy：一种用于机器人学习的稀疏、可复用且灵活的策略
Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning
AI总结：
本文提出 Sparse Diffusion Policy（SDP），通过在 transformer 扩散策略中引入 MoE 实现专家与技能的选择性激活，从而以极少活跃参数支持多任务、持续学习与任务迁移。
摘要：
机器人技术中任务复杂性的不断提高，要求采用高效的多任务与持续学习策略。传统模型通常依赖一个适用于所有任务的通用策略，因此在学习新任务时面临高计算成本和灾难性遗忘等挑战。为解决这些问题，我们提出了一种稀疏、可复用且灵活的策略——Sparse Diffusion Policy（SDP）。通过在基于 transformer 的扩散策略中采用 Mixture of Experts（MoE，专家混合），SDP 能够选择性地激活专家和技能，从而在无需重新训练整个模型的情况下实现高效且面向特定任务的学习。SDP 不仅减轻了活跃参数的负担，还促进了专家在各类任务之间的无缝整合与复用。在仿真和真实世界的多种任务上进行的大量实验表明，SDP：1）在多任务场景中表现优异，且活跃参数的增加可以忽略不计；2）在持续学习新任务时能够防止遗忘；3）能够实现高效的任务迁移，从而为先进机器人应用提供了一种有前景的解决方案。演示和代码可在 https://forrest-110.github.io/sparse_diffusion_policy/ 获取。
英文摘要：
The increasing complexity of tasks in robotics demands efficient strategies for multitask and continual learning. Traditional models typically rely on a universal policy for all tasks, facing challenges such as high computational costs and catastrophic forgetting when learning new tasks. To address these issues, we introduce a sparse, reusable, and flexible policy, Sparse Diffusion Policy (SDP). By adopting Mixture of Experts (MoE) within a transformer-based diffusion policy, SDP selectively activates experts and skills, enabling efficient and task-specific learning without retraining the entire model. SDP not only reduces the burden of active parameters but also facilitates the seamless integration and reuse of experts across various tasks. Extensive experiments on diverse tasks in both simulations and real world show that SDP 1) excels in multitask scenarios with negligible increases in active parameters, 2) prevents forgetting in continual learning of new tasks, and 3) enables efficient task transfer, offering a promising solution for advanced robotic applications. Demos and codes can be found in https://forrest-110.github.io/sparse_diffusion_policy/.
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。
