用基因筛选优化扩散模型，5步内完成机器人操作，效率提升20%。
Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoising
- 通过基因筛选策略选择低异常风险的去噪路径
- 仅需2次神经函数评估即解决复杂任务，性能提升20%
- 适合对推理速度敏感的机器人控制场景
扩散模型如扩散策略在模仿专家示范的机器人操作中达到顶尖水平。尽管扩散模型最初用于图像与视频生成，其推断策略常被直接迁移至控制领域而未适配。本文发现，若针对具身智能任务（特别是动作分布结构化、低维特性）定制去噪过程，扩散策略可仅用5次神经函数评估（NFE）即有效运行。基于此，我们提出基于种群的采样策略——基因去噪，通过筛选低分布外风险的去噪轨迹，提升性能与稳定性。该方法在仅2次NFE下即可解决挑战性任务，性能优于或匹配现有方法。我们在D4RL和Robomimic的14个机器人操作任务上评估，涵盖多动作时序与推理预算。在超过200万次评估中，本方法持续优于标准扩散策略，实现最高20%的性能提升，且显著减少推理步骤。
原文摘要 · Abstract (English)
Diffusion models, such as diffusion policy, have achieved state-of-the-art results in robotic manipulation by imitating expert demonstrations. While diffusion models were originally developed for vision tasks like image and video generation, many of their inference strategies have been directly transferred to control domains without adaptation. In this work, we show that by tailoring the denoising process to the specific characteristics of embodied AI tasks -- particularly structured, low-dimensional nature of action distributions -- diffusion policies can operate effectively with as few as 5 neural function evaluations (NFE). Building on this insight, we propose a population-based sampling strategy, genetic denoising, which enhances both performance and stability by selecting denoising trajectories with low out-of-distribution risk. Our method solves challenging tasks with only 2 NFE while improving or matching performance. We evaluate our approach across 14 robotic manipulation tasks from D4RL and Robomimic, spanning multiple action horizons and inference budgets. In over 2 million evaluations, our method consistently outperforms standard diffusion-based policies, achieving up to 20\% performance gains with significantly fewer inference steps.
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。