用线性路径替代传统调度，让扩散模型更稳定易调。
Adaptive Linear Path Model-Based Diffusion
- 用受流匹配启发的线性概率路径替代原调度方式
- 在多个基准上保持强性能且降低调参复杂度
- 通过强化学习动态调整步数和噪声，适合复杂环境
将基于模型的控制与扩散模型结合的研究日益增多。尽管在复杂任务中已取得令人瞩目的机器人控制成果，但扩散模型性能对调度参数极为敏感，参数调优成为关键挑战。本文提出线性路径模型基扩散（LP-MBD），用受流匹配启发的线性概率路径替代保持方差的调度方式，实现几何可解释且解耦的参数化，降低调参复杂度，提供稳定适应基础。在此基础上，提出自适应LP-MBD（ALP-MBD），利用强化学习根据任务复杂度和环境条件动态调整扩散步数与噪声水平。在数值实验、Brax基准及移动机器人轨迹跟踪任务中，LP-MBD简化了调度并保持优异性能，ALP-MBD进一步提升鲁棒性、适应性与实时效率。
原文摘要 · Abstract (English)
The interest in combining model-based control approaches with diffusion models has been growing. Although we have seen many impressive robotic control results in difficult tasks, the performance of diffusion models is highly sensitive to the choice of scheduling parameters, making parameter tuning one of the most critical challenges. We introduce Linear Path Model-Based Diffusion (LP-MBD), which replaces the variance-preserving schedule with a flow-matching-inspired linear probability path. This yields a geometrically interpretable and decoupled parameterization that reduces tuning complexity and provides a stable foundation for adaptation. Building on this, we propose Adaptive LP-MBD (ALP-MBD), which leverages reinforcement learning to adjust diffusion steps and noise levels according to task complexity and environmental conditions. Across numerical studies, Brax benchmarks, and mobile-robot trajectory tracking, LP-MBD simplifies scheduling while maintaining strong performance, and ALP-MBD further improves robustness, adaptability, and real-time efficiency.
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。