用扩散模型与Mamba实现粗到细动作的高效学习与控制
DiSPo: Diffusion-SSM based Policy Learning for Coarse-to-Fine Action Discretization
- 结合扩散模型与Mamba SSM，从粗粒度技能中学习并生成多尺度动作
- 在三个基准测试中成功率最高提升81%，且推理效率更高
- 适合需要灵活控制粒度的机器人仿真与真实操作任务
我们旨在解决从示范中学习粗到细技能的问题。传统方法依赖大量细粒度示范或泛化能力有限的动力学模型来提升精度。为实现高效记忆与灵活粒度调整，我们提出基于扩散-状态空间模型（SSM）的策略（DiSPo），利用Mamba SSM从多样化的粗粒度技能中学习，并通过步长缩放方法生成不同控制精度的动作。评估显示，采用Mamba和所提步长缩放方法后，DiSPo在三个粗到细基准测试中表现优于基线，成功率最高提升81%。此外，DiSPo在非关键区域生成粗动作，显著提升推理效率。最后，我们在仿真和真实机器人操作任务中验证了其动作可扩展性。代码与视频见 https://robo-dispo.github.io。
原文摘要 · Abstract (English)
We aim to solve the problem of generating coarse-to-fine skills learning from demonstrations (LfD). To scale precision, traditional LfD approaches often rely on extensive fine-grained demonstrations with external interpolations or dynamics models with limited generalization capabilities. For memory-efficient learning and convenient granularity change, we propose a novel diffusion-state space model (SSM) based policy (DiSPo) that learns from diverse coarse skills and produces varying control scales of actions by leveraging an SSM, Mamba. Our evaluations show the adoption of Mamba and the proposed step-scaling method enable DiSPo to outperform in three coarse-to-fine benchmark tests with maximum 81% higher success rate than baselines. In addition, DiSPo improves inference efficiency by generating coarse motions in less critical regions. We finally demonstrate the scalability of actions with simulation and real-world manipulation tasks. Code and Videos are available at https://robo-dispo.github.io.
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。