用隐式最大似然估计，让机器人用更少数据、更快生成动作。
IMLE Policy: Fast and Sample Efficient Visuomotor Policy Learning via Implicit Maximum Likelihood Estimation
- 基于隐式最大似然的生成架构，单步完成动作预测。
- 比基线少38%数据即可达到相同性能，推理速度提升97.3%。
- 适合数据稀缺、算力受限的机器人场景，实测有效。
近期基于生成模型（如扩散模型）的模仿学习进展使策略能够捕捉复杂的多模态动作分布。然而，这些方法通常需要大量数据和多步推断，对机器人领域中高成本数据采集和有限算力构成挑战。为此，我们提出IMLE Policy，一种基于隐式最大似然估计（IMLE）的行为克隆新方法。该方法在低数据条件下表现优异，平均仅需38%更少的数据即可达到基线方法的性能水平，且能实现单步动作生成，相比扩散策略（Diffusion Policy）推理速度提升97.3%，同时优于单步流匹配（Flow Matching）。我们在模拟与真实世界多种操作任务中验证了该方法的有效性，证明其在数据受限下仍能捕捉复杂行为。项目视频与代码已公开：https://imle-policy.github.io/。
原文摘要 · Abstract (English)
Recent advances in imitation learning, particularly using generative modelling techniques like diffusion, have enabled policies to capture complex multi-modal action distributions. However, these methods often require large datasets and multiple inference steps for action generation, posing challenges in robotics where the cost for data collection is high and computation resources are limited. To address this, we introduce IMLE Policy, a novel behaviour cloning approach based on Implicit Maximum Likelihood Estimation (IMLE). IMLE Policy excels in low-data regimes, effectively learning from minimal demonstrations and requiring 38\% less data on average to match the performance of baseline methods in learning complex multi-modal behaviours. Its simple generator-based architecture enables single-step action generation, improving inference speed by 97.3\% compared to Diffusion Policy, while outperforming single-step Flow Matching. We validate our approach across diverse manipulation tasks in simulated and real-world environments, showcasing its ability to capture complex behaviours under data constraints. Videos and code are provided on our project page: https://imle-policy.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。